broomva

@broomva source repo

116 skills
0 followers
4 hours ago last updated

▌
Autoany 2 · broomva bundle
Evaluator-Governed Recursive Improvement (EGRI) framework for turning ambiguous goals into safe, measurable, rollback-capable recursive improvement systems. Use when the user wants to: (1) build a self-improving system for any domain (ML, RAG, workflows, ETL, UI, compiler tuning, etc.), (2) formalize a vague optimization goal into a bounded loop with evaluator, harness, and promotion policy, (3) create an autoresearch-style system beyond ML training, (4) design a mutable-artifact + immutable-evaluator architecture, (5) scaffold a problem-spec for recursive improvement, (6) turn "make X better" into a safe, auditable optimization process. Triggers on: "self-improving", "autoresearch", "autoany", "EGRI", "recursive improvement", "optimization loop", "evaluator-governed", "harness + evaluator", "mutable artifact", "problem compiler", "benchmark loop", "mutation surface".

0
installs
▌
Symphony 2 · broomva bundle
Expert guidance for Symphony — the Rust orchestration engine for coding agents. Use when users ask about installing Symphony (cargo install, curl|bash, docker), initializing projects (symphony init), configuring WORKFLOW.md for Linear or GitHub trackers, running in daemon or one-shot mode, setting up the control metalayer (CONTROL.md, setpoints), configuring lifecycle hooks (after_create, before_run, after_run, pr_feedback), monitoring with HTTP dashboard and Prometheus /metrics, extending with new trackers, or troubleshooting agent/hook failures. Triggers on "symphony", "WORKFLOW.md", "coding agent orchestration", "issue tracker automation", "control metalayer", or "agent dispatch".

0
installs
▌
Symphony Forge · broomva bundle
Expert assistance for symphony-forge — a CLI that scaffolds next-forge projects with a composable control metalayer for AI agent governance. Triggers on questions about initializing projects with symphony-forge, adding metalayer layers (control, harness, knowledge, consciousness, autoany), running entropy audits, configuring EGRI self-improvement loops, and setting up AI-agent-ready development workflows. Also serves as a skill creator — use this to bootstrap new projects with built-in agent skills.

0
installs
▌
Autoany · broomva bundle
Evaluator-Governed Recursive Improvement (EGRI) framework for turning ambiguous goals into safe, measurable, rollback-capable recursive improvement systems. Use when the user wants to: (1) build a self-improving system for any domain (ML, RAG, workflows, ETL, UI, compiler tuning, etc.), (2) formalize a vague optimization goal into a bounded loop with evaluator, harness, and promotion policy, (3) create an autoresearch-style system beyond ML training, (4) design a mutable-artifact + immutable-evaluator architecture, (5) scaffold a problem-spec for recursive improvement, (6) turn "make X better" into a safe, auditable optimization process. Triggers on: "self-improving", "autoresearch", "autoany", "EGRI", "recursive improvement", "optimization loop", "evaluator-governed", "harness + evaluator", "mutable artifact", "problem compiler", "benchmark loop", "mutation surface".

0
installs
▌
Bstack Upgrade · broomva
Upgrade bstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new.

0
installs
▌
Symphony · broomva bundle
Rust orchestration engine for coding agents. Polls issue trackers (Linear, GitHub), creates isolated per-issue workspaces, and runs coding agent sessions with lifecycle hooks, retry/backoff, concurrency control, and a live HTTP dashboard. Includes control metalayer (CONTROL.md / setpoints) for grounded development workflows.

0
installs
▌
Control Metalayer · broomva bundle
Umbrella skill package containing three complementary skills for persistent consciousness in autonomous AI agent development — control primitives and behavioral governance, agent consciousness architecture, and knowledge graph memory. Install individual skills or use the full stack to give stateless agent sessions the accumulated understanding of all prior sessions. Part of the Broomva Stack (Layers 1-2).

0
installs
▌
Agent Consciousness · broomva bundle
Persistent consciousness architecture for autonomous AI agent development. Synthesizes three substrates — control metalayer (behavioral governance), Obsidian knowledge graph (declarative memory), and conversation log bridge (episodic memory) — into a self-evolving context layer. Use when designing agent memory systems, implementing cross-session context persistence, building knowledge graphs for AI agents, setting up conversation history capture, or architecting feedback loops that let agents learn from prior sessions. Triggers on "agent memory", "session persistence", "knowledge graph", "conversation history", "consciousness stream", "cross-session context", "agent learning", or "self-evolving development".

0
installs
▌
Control Metalayer Loop · broomva bundle
Create and maintain a control-system metalayer for autonomous code-agent development in any repository. Use when you need explicit control primitives (setpoints, sensors, controller policy, actuators, feedback loop, stability and entropy controls), repo command/rule governance, and a scalable folder topology that lets agents operate safely and keep improving over time.

0
installs
▌
Knowledge Graph Memory · broomva bundle
Bridge Claude Code conversation logs to an Obsidian knowledge graph for persistent agent memory. Transforms .entire/ event logs and ~/.claude/ transcripts into searchable, wikilinked markdown docs with full conversation threads, tool call details, and session metadata. Use when setting up conversation history capture, configuring knowledge graph traversal for agents, building episodic memory from session logs, or connecting agent work to an Obsidian vault. Triggers on "conversation history", "session logs to obsidian", "knowledge graph memory", "agent episodic memory", "conversation bridge", "session documentation", or "knowledge traversal".

0
installs
▌
Skills Showcase · broomva bundle
Generate a polished Remotion video and X thread showcasing the full agent skills inventory. Use when creating social media content about skills, rendering category-based skill visualizations, or producing animated showcases of agent capabilities. Triggers on "skills video", "showcase skills", "skills thread", "render skills", "social content for skills", or requests to visualize the skills inventory.

0
installs
▌
Kg · broomva bundle
Load relevant entities from the bstack knowledge graph (research/entities/) for a given topic. Two-tier scoring: tier-1 (catalog-only, ~5ms — slug + tags + claim + links + sources match against docs/knowledge-index.md) is the fast first pass and the only stage for high-confidence exact-slug/tag queries; tier-2 (body-grep fallback, ~300ms — auto-fires when tier-1 returns < N matches OR its best hit is below the confidence floor, default 18) recovers topics whose vocabulary appears in entity prose but not the dense catalog (hit rate jumps from 70% → 100% on representative queries; this is hit rate ≥1, not true recall@N). Surfaces top-N entity bodies as a single context block the agent reasons over. This is a LOAD skill, not a query DSL — querying is what the agent does once loaded. Implements the LLM-as-index architecture (BRO-1223): substrate canonical, one projection (catalog) routes, agent IS the query engine. Empirical: peak per-query context drops from 29% → 4.6% of 1M (6.3× reduction); cumulative session

0
installs
▌
Tekton · broomva bundle
Tekton — the shared architecture-intent substrate for co-designing systems with the agent. One typed graph across six tiers (system / journey / data / infra / decisions / qualities); views are queries, not separate diagrams. The canonical artifact is a diff-friendly YAML model both human and agent read and write; it renders to Mermaid (agent-legible, GitHub-native) and a self-contained tabbed HTML viewer (human-visual). Cross-tier traceability (`tekton query <from> <to>`) answers "which infra does this user-journey step touch?" as a path query. USE WHEN: designing or thinking deeply about architecture, a system, a data model, user journeys/flows, or a technical plan WITH the agent; when a Category-C HTML doc isn't enough because you need to see AND edit AND traverse the design across tiers; "let's design X", "architect this", "model the system", "draw the flow", "how does this fit together", "diagram this", "/tekton". NOT FOR: a one-off throwaway diagram (use Mermaid inline); prose-only ADRs (write the ADR);

0
installs
▌
Unslop · broomva bundle
Remove the "vibecoded" / AI-slop look from an arbitrary frontend codebase at the ROOT, autonomously, and prove the result clears a crafted floor. Full-repo traversal (any framework) → root-cause attribution (the one file that declares each default: font, icons, color/radius/shadow tokens, gradient/glass, motion, copy voice) → fix once at the root, never at forty call sites → the substance tells no detector covers (legal routes, loading/empty/error states, placeholder and fake content, real product evidence) → render at 1280+390 → deterministic gate (scripts/unslop_gate.py, exit 0 = clear). Composes the impeccable detector (64 rules) and commands, Anthropic frontend-design for direction, broomva-design as the house example; reimplements none of them. USE WHEN: a site or app "looks vibecoded", "looks AI-generated", "looks like every other AI site", "feels generic/templated/slop", "make it feel premium / crafted / intentional", "de-slop / unslop this", "does this pass the vibecoded test", or before shipping any

0
installs
▌
Haima · broomva bundle
Agentic finance engine for the Agent OS — x402 machine-to-machine payments, on-chain settlement, per-task revenue billing, and wallet management. Integrates with Arcan (agent runtime), Autonomic (economic homeostasis), and Lago (event-sourced persistence) to give agents real financial agency. Use when: (1) adding payment capabilities to an agent or agent-controlled API, (2) implementing x402 protocol support for HTTP-native machine payments, (3) wiring per-task billing so agents can charge for completed work, (4) managing agent wallets (secp256k1 keypair, encrypted storage), (5) configuring payment policies (auto-approve, spend caps, rate limits), (6) integrating Coinbase CDP or self-hosted facilitators for on-chain settlement, (7) bridging on-chain USDC with Autonomic's micro-credit state. Triggers on 'agent payments', 'x402', 'machine payments', 'agentic finance', 'haima', 'payment port', 'wallet management', 'per-task billing', 'USDC payments', 'agent revenue', '402 payment required'.

0
installs
▌
Ccr · broomva bundle
ccr — reversible payload compression: shrink any blob (tool output, log, RAG chunk, file) BEFORE it enters an LLM's context, while caching the full original locally so it can be expanded byte-for-byte on demand. The payload-axis counterpart to a knowledge-graph loader (the retrieval axis): the model sees a compact lossy view + a handle (ccr://<sha256>), and calls retrieve(handle) only when it needs the bytes back. Content-routed deterministic compactors (json skeleton / code outline / text head-tail); stdlib-only, no ML. Lifted from the CCR component of github.com/chopratejas/headroom. USE WHEN — a tool output / log / RAG chunk / file is too large for context and you want to compress it reversibly; "compress this payload", "shrink this before the model", "reversible compression", "cache the original and give me a handle". NOT FOR — loading knowledge-graph entities (that's the kg loader, the retrieval axis); lossless whole-file compression (use gzip); semantic summarization that does not need byte-exact recove

0
installs
▌
Bitnet · broomva bundle
Microsoft BitNet — 1-bit LLM setup, inference, and benchmarking on CPU. Automates the full workflow: clone bitnet.cpp, create conda env, download GGUF models from HuggingFace, build optimized ternary kernels, and run inference. Supports official Microsoft models (2B) and community models (0.7B-10B). Use when: (1) setting up BitNet/bitnet.cpp for local CPU inference, (2) downloading and running 1-bit/ternary LLMs, (3) benchmarking BitNet vs full-precision models, (4) building edge/agentic inference pipelines without GPU, (5) converting HuggingFace models to GGUF for bitnet.cpp. Triggers on: 'bitnet', '1-bit llm', '1.58-bit', 'ternary model', 'ternary weights', 'edge inference', 'cpu inference', 'bitnet.cpp', 'bitlinear', 'no gpu inference'.

0
installs
▌
Talkback · broomva bundle
Speak an explanation out loud while working in any project — tiered text-to-speech with a pluggable backend (ElevenLabs by default and quota-guarded, macOS `say` via `--fast` for free instant local speech, local OmniVoice as an unlimited private tier). Markdown-aware, so code fences, URLs and deep paths collapse to short spoken placeholders instead of being dictated character by character, while snake_case identifiers survive intact so the listener can still search for them. Every utterance is saved to disk for later replay. Includes an optional Stop hook that speaks a short readback when a turn ends — off by default, and when on it speaks only on turns the agent explicitly marked, so acknowledgements never become audio. Use when the user asks to hear something rather than read it — an explanation of a change, a walkthrough of what just happened, a summary they want while looking away from the screen.

0
installs
▌
What · broomva bundle
Explain the CONCEPTS a session used, at the operator's register, grounded in what actually ran. After an agent works, you are handed results built out of vocabulary you did not choose — primitive short-names, entity slugs, library names, terms of art from the diff. `/what` names those terms, ranks them by what actually blocks understanding, defines each one, and anchors it to where it appeared and to its knowledge-graph entity. Fired mid-conversation with a short slice it degrades to the re-pitch case: "that did not land, say it again with more context and a simpler register." USE WHEN: /what, "wait what", "what did you just do", "explain that again", "I don't follow", "you lost me", "what do those terms mean", "re-pitch that", "explain the concepts", "what is all this jargon", after an autonomous arc or a long PR when the vocabulary outran the operator. NOT FOR: a summary of actions taken (that is the P1 Bridge session log); state for the next agent (that is /handoff); teaching a whole body of work to master

0
installs
▌
Omnivoice · broomva bundle
Local TTS, voice cloning, voice design, and video dubbing via the OmniVoice Studio MCP server (open-source ElevenLabs alternative; nothing leaves the machine, runs on MPS/CUDA/CPU). Use when: (1) generating speech from text in any of 646 languages, (2) cloning a voice from a 3-second reference clip, (3) designing a voice by gender/age/accent/pitch/style, (4) dubbing a video into another language, (5) listing voice profiles or personality presets, (6) producing narration where privacy, cost, or absent API keys matter, (7) non-English narration where Edge TTS/kokoro fall short, (8) batch audio for blog posts or content pipelines. Triggers: 'omnivoice', 'voice clone', 'clone this voice', 'tts', 'narrate', 'generate speech', 'voice synthesis', 'dub video', 'voice design', 'local tts', 'multilingual voice', 'narrate this post', 'elevenlabs alternative'.

0
installs
▌
D1 CLI · broomva bundle
Shop Tiendas D1 (Colombia, d1.com.co) from the command line — search the catalogue, resolve your nearest physical store, price a basket against that store's real stock, and quote delivery. D1 runs VTEX IO (account `d1tiendas`), so this drives its public storefront API with no admin key at all — catalogue and cart work fully anonymously, and a one-time emailed code unlocks order history. Handles the two traps that make naive D1 automation wrong — availability is regionalized (an unregioned query reports a national catalogue nobody can actually buy from) and prices arrive in two different units (search reports whole pesos, checkout reports hundredths, a silent 100x). Builds and prices baskets; it deliberately cannot pay, handing a checkout URL to a human instead. USE WHEN the user wants to find D1 products or prices, check whether D1 delivers somewhere, build or cost a D1 grocery basket, compare D1 items, or review their D1 orders. NOT FOR other Colombian retailers (Éxito, Jumbo, Ara, Alkosto), and not for comp

0
installs
▌
Swapit · broomva bundle
Stateful, local-first household toxics inventory + swap engine. Identify the items in a home that carry endocrine disruptors and persistent chemicals (BPA/BPS, phthalates, PFAS/PTFE, parabens, flame retardants, VOCs, microplastics), score each by *real* exposure (severity x presence x how it's used x condition), and track the swap to a safer alternative from "flagged" -> "sourced" -> "swapped". Ships a grounded, cited knowledge graph of ~20 hazards, ~40 item-classes, and ~40 alternatives. Hands sourcing off to the `procurer` skill. The skill's state is the source of truth — the agent is the app.

0
installs
▌
Keel · broomva bundle
Measure whether a codebase's verification actually touches the world, or whether it is checking itself. Keel gathers the verification edges it can read in a target (GitHub Actions, CircleCI, GitLab CI, Travis, package scripts, Makefile, Rakefile, pyproject and a dozen tool configs) — and reports the surfaces it recognised but could not parse, so blindness never passes for absence. It classifies each edge as anchored, self-referential, or unknown by asking whether the actor being verified can write to the signal's producer, and reports a grounding ratio. Novel cases are judged by the agent and then crystallized into probes — small reviewable scripts — so repeat shapes get cheaper every run. Then routes each ungrounded check to an anchored signal that already exists in the same graph. Use when: (1) auditing whether AI-generated or agent-maintained work is genuinely verified, (2) assessing how AI-native a codebase actually is — measured by what fraction of its verification the agents cannot author, (3) reviewing

0
installs
▌
Gasgo · broomva bundle
Answer "where should I go right now for the best gas deal in Colombia?" — an engine over live, per-station Colombian fuel-price open data (SICOM GNCV via datos.gov.co Socrata, plus historical gasoline/diesel). Ranks nearby stations by a price + distance cost model and returns a best-deal recommendation with an explicit freshness verdict (🟢 live GNCV vs 🟡 historical gasoline/diesel) and honest coordinate resolution (open GNCV coords are municipal centroids, so distances are shown approximate and intra-municipality ranking is by price). Dependency-free bun core. USE WHEN the user asks where to buy the cheapest gas/fuel/GNCV near a Colombian location, wants to compare station prices, or wants to build/extend fuel-price ingestion. NOT FOR non-Colombian markets or real-time gasoline/diesel (open data is GNCV-only live; gasoline/diesel is frozen ≈2022 — the SICOM birest endpoint is empty and Google Places needs a licensed key).

0
installs
▌
Ltx Video · broomva bundle
Set up, configure, and run LTX-2/LTX-2.3 (Lightricks) for AI video and audio generation. Use when: (1) Installing LTX-2 locally or via ComfyUI, (2) Generating video from text, image, audio, or keyframes, (3) Running inference with the 22B dev/distilled models, (4) Fine-tuning with LoRA/IC-LoRA, (5) Configuring upscalers (spatial/temporal), (6) Optimizing VRAM usage (FP8, quantization, low-VRAM modes), (7) Building content-generation pipelines with LTX-2, (8) Writing prompts for video generation, (9) Integrating LTX-2 into ComfyUI workflows. Triggers on: ltx, ltx-video, ltx-2, lightricks video, text-to-video generation, video diffusion model.

0
installs
▌
Video Cut · broomva bundle
Edit raw footage into a finished cut by conversation, fully local. Drop clips in a folder, describe the video you want, get edit/final.mp4 back. Local-first raw-footage video editor — the editorial counterpart to the generative Remotion/launch-video skills. Uses a two-layer reading system (local faster_whisper word-level transcript + on-demand timeline_view composite) so the agent cuts with word-boundary precision without ever dumping video frames — llm-as-index applied to video. Swaps cloud ElevenLabs Scribe for local faster_whisper: free at any volume, nothing leaves the machine, no API key. Removes filler/dead-air, color-grades per segment, burns subtitles, composes overlay animations via Remotion, and self-evaluates the render before showing you. USE WHEN: edit this footage, cut these clips, make a video from this raw footage, remove filler words from video, trim this recording into a video, edit talking head, montage, tutorial cut, interview edit, turn these clips into a launch video. NOT FOR generating

0
installs
▌
Livecoding · broomva bundle
Algorave-grade livecoded music workflow — TidalCycles patterns (Haskell DSL driving SuperDirt over OSC) + Hydra-synth visuals (browser or VS Code Simple Browser via a local HTML page that loads hydra-synth from CDN). Wraps the boot ritual (SuperCollider → SuperDirt → Tidal → Hydra), a vibe-descriptor pattern generator (industrial, ambient, DnB, footwork, techno, algorave-glitch), and a reference tunnel-visuals page for the @lo.fi.sci.fi-projected aesthetic. Mac-first; ports to Linux with package-name swaps.

0
installs
▌
P9 · broomva bundle
Something is running and you are stuck waiting on it — CI checks on a PR you just pushed, a deploy going out, a container image build, a slow migration or a long reindex. This skill puts a watcher on the wait and spends the wait on the next piece of work, instead of watching a spinner or calling `sleep`. Also use it for a wait already in flight: "is the watcher running?", "did it notify?", "if I close my laptop does the wait just evaporate?", "I want my phone to buzz when it finishes or when it dies". Invoke it on the wait alone. You do NOT need the PR number, the URL, the branch, or the polling command first — locating the target is the skill's own first step, not a precondition for loading it. Asking the user which PR / which command / which watcher instead of invoking is the known failure mode here, and it is never the right move. Not for a wait nobody is waiting on any more — checks already landed, run already finished, PR already merged, a red result handed to you cold to debug. A failure your own watche

0
installs
▌
Checkit · broomva bundle
Ingest-and-integrate an artifact someone points at with a terse, deliberately under-articulated directive — "check this out", "lets research this", "look into this", "wdyt" — followed by a URL, repo, paper, file, image, or pasted document. Infers the actual request from a fully-contextualized frame (who is asking + what they're working on + what's already known) WITHOUT bouncing a clarifying question back, then runs the pipeline: contextualize → deep research (verify every source) → analyze → connect → document the finding → suggest ranked next steps. The artifact ends up metabolized into knowledge and action, not left as a one-paragraph summary. Composes existing research/search/memory tools; it does not reimplement them. USE WHEN: check this out, checkit, /checkit, lets research this, research this, look into this, dig into this, wdyt, what do you think of this, found this, take a look + an artifact; or whenever an artifact is shared with an underspecified ask. NOT FOR: retrospective "what have I been doing

0
installs
▌
Skillify · broomva bundle
Skillify-as-a-verb — distill a working session (or a pointed-at chat history) into a permanent, TESTED, registered skill at the end of a workflow. The bstack-native composition of Garry Tan's 10-step "skillify it": look-back extraction → CreateSkill scaffold → latent/deterministic split → unit tests → resolver-eval (role-x.py eval) → script-test gate (bstack skills audit --require-tests) → P20 cross-review → bookkeeping file. Composes existing primitives; reimplements nothing. The deterministic core (scripts/skillify_check.py) makes "a feature that doesn't pass all ten is not a skill" machine-checkable, per TIER: D (deterministic — tests + mutation), J (judgment — admission test, rubric, held-out cases, cross-model judge, measured agreement floor), or L (lens — a both-polarity routing eval). A skill with no pure function is not exempt from gating; it is gated on a different axis. USE WHEN: "skillify it", "skillify this", "package this as a skill", "distill this into a skill", "make this a skill", "turn this i

0
installs
▌
Procurer · broomva bundle
Grounded procurement research for any real-world need. Turn a problem ("reduce bedroom noise from the avenue", "add air conditioning", "hire an accountant", "buy a TV mount", "replace the kitchen sink") into 3–5 ranked alternatives spanning DIY-retail → mid-retail → specialty → contractor → consultant/turnkey, each with cited price bands (low / typical / high), confidence scores, locale-aware currency, and a final recommendation with budget. Output is decision-shaped (recommendation + budget envelope), not research-shaped (knowledge artifact).

0
installs
▌
Bstack · broomva
bstack primer — the Broomva Stack: twenty irreducible automation primitives (P1–P20) that turn an agent-driven workspace into a self-operating system. This is the AGENT-READABLE PRIMER (primitive contract + short-name index + when each fires), NOT the CLI. The bstack CLI + governance substrate (bin/, doctor, templates, hooks) is a separate product installed by clone + bootstrap (git clone https://github.com/broomva/bstack && ./bin/bstack bootstrap) — do NOT `npx skills add broomva/bstack` (it drops bin/scripts, the repo-root SKILL.md case of vercel-labs/skills#1523). Use this primer to reason with the primitives: Bridge (P1), Gate (P2), Tickets (P3), Pipeline (P4), Fanout (P5), Bookkeeping (P6), Freshness (P7), Janitor (P8), Wait (P9), Hygiene (P10), Empirical (P11), Persist (P12), Dream (P13), Dep-Chain (P14), Snapshot (P15), Crystallize (P16), Lens (P17), Audience (P18), Orchestrate (P19), Cross-Review (P20). Triggers on 'bstack', 'Broomva Stack', 'the primitives', 'P1'..'P20', 'primitive contract', 'bstack

0
installs
▌
Health · broomva bundle
Personal health knowledge graph — local-first ingest of Garmin (Apple Health, Whoop, Oura, CGM in v2+) traces into SQLite, projected to Obsidian daily-note frontmatter, synthesized into validated longevity-proxy metrics (HRV-CV, CTL/ATL/TSB, VO2max arc). Hex architecture so new sources drop in as adapters. NOT a coaching surface in v1.

0
installs
▌
Goodies · broomva bundle
Ingest, contextualize, and index curated resources (websites, tools, design references, research papers, UI kits) into a public GitHub Pages vault while automatically linking them to the local Knowledge Graph via /checkit and P6 bookkeeping. Dynamically resolves and expands category ontologies, generates client-side search indices, and publishes the updated vault database to a public repository. USE WHEN: /goodies, goodies, goodies add, add to goodies, bookmark this site, save to goodies, bookmark good resource, curate website. NOT FOR: internal-only notes without public vault indexing; general web searches without curating a resource.

0
installs
▌
Arc · broomva bundle
Use when the user is handing over an unattended run and will not be there to answer: they are going to bed, stepping away, or leaving it overnight, and they want the work carried to an end state that is both finished and clean rather than to a stopping point. Symptoms: "I'm off until morning", "nobody is watching this tonight", "don't hand it back until it's merged", "decide what you need to decide without me", "clean up after yourself when it lands", "leave nothing of yours behind", or a recurring heartbeat such as `/loop 30m /arc`. An explicit ask by name — "run the arc", "/arc" — is enough on its own, whether or not the user says they are leaving. Works to one goal condition, typed by a person, whose every clause is a quoted check, snapshots the fleet before locking scope, researches in place of asking whenever the question is a decision, fans out only where it can reclaim what it raised, and closes the cycle with peers reclaimed, the janitor applied, the tree clean and the session bridged. Triggers on "ru

0
installs
▌
Orcahand · broomva bundle
Full-stack skill for the ORCA Hand — 17-DOF tendon-driven robotic hand (ETH Zurich). Implements agentic-control-kernel Plant interface with typed schemas, safety shields, multi-rate loops. Lifecycle: 3D print + assembly, MuJoCo sim (orca_sim), RL training (macOS + remote GPU), teleoperation (AVP/Rokoko/MediaPipe via orca_retargeter), sim-to-real, EGRI improvement. Use when: building/assembling OrcaHand, orca_sim environments, teleoperating, training grasp policies, sim-to-real transfer, control-kernel Plant schemas, EGRI loops. Triggers: "orcahand", "orca_core", "orca_sim", "dexterous hand", "robotic hand", "tendon-driven", "dynamixel hand", "hand simulation", "teleoperate hand", "grasp policy", "sim-to-real hand", "3d print hand".

0
installs
▌
Make Spec · broomva bundle
Scaffold a substantive human-readable design doc (spec / plan / ADR / report / PR explainer) as native HTML using the workspace's canonical Broomva dark theme. Implements P18 (Format-Follows-Audience) for Category-C native artifacts — distinct from `bookkeeping render`, which projects Category-B markdown canonicals to HTML. Use when: (1) drafting a substantive design doc a human will actually read (>100 lines OR contains tables/diagrams/decision matrices), (2) writing an ADR (architectural decision record), (3) producing a plan a non-agent stakeholder will review, (4) writing a PR explainer for a substantive PR, (5) producing a report that synthesizes prior research. The skill ships theme.css + the spec HTML template, and generates the plan / adr / report / pr-explainer variants from that same theme + the prose skeletons below — so the agent doesn't rebuild the 70-line :root + h1-h4 + table + callout boilerplate every time. Triggers on "spec", "plan", "ADR", "decision record", "design doc", "explainer", "repo

0
installs
▌
Remote Gpu · broomva bundle
Orchestrate a headless GPU server (NUC, cloud VM, or any SSH-accessible machine) from a local Mac or workstation. Use when: (1) Running GPU workloads remotely (training, inference, video generation), (2) Triggering Claude Code sessions on a remote machine, (3) Launching autoany EGRI loops, symphony orchestrations, or training scripts on remote hardware, (4) Managing jobs on a headless GPU server (submit, monitor, cancel, download results), (5) Setting up SSH tunnels or API bridges to a GPU machine, (6) Orchestrating multi-machine agent workflows. Triggers on: remote gpu, headless server, gpu server, remote training, remote inference, ssh gpu, nuc server, remote claude code, remote agent, gpu orchestration.

0
installs
▌
Arcan Glass · broomva bundle
BroomVA trademark web styling system — Arcan Glass design language for Next.js + Tailwind v4 + shadcn/ui projects. Use when creating or styling BroomVA web interfaces, implementing glass/frosted UI effects, setting up brand-consistent dark-first themes, or integrating ArcanBG brand tokens (AI Blue

0
installs
▌
Brand Icons · broomva bundle
Brand icon and visual identity management for BroomVA projects. Helps the agent produce favicons, app icons, Open Graph images, and social media avatars from brand assets, keeping a consistent visual identity across web, mobile, and social platforms. Use when: (1) generating favicon sets (ICO, PNG, SVG) for a web project, (2) creating app icons for iOS/Android, (3) generating Open Graph and Twitter Card images, (4) producing social media profile/banner images, (5) ensuring brand consistency across platforms.

0
installs
▌
Dogfood · broomva bundle
Per-bstack-P11 reflex 7+16 — explicitly trigger the Dogfood Plan + per-stack cookbook + Dogfood Receipt sequence. Auto-detects the tech stack from repo signals (Cargo.toml + src-tauri/ → tauri-sidecar; next.config.* → nextjs; app.json + expo → expo-rn; Cargo.toml solo → rust-cli; openapi.* or REST framework deps → rest-api; mcp.{json,yaml} → mcp-server), loads the matching cookbook entry from bstack/references/dogfood-patterns.md (broomva/bstack ≥ 0.13.0), produces a six-row Dogfood Plan (entry surface · driver · evidence · smoke · end-to-end · receipt anchor), optionally executes via the named surfaces (Interceptor mandatory for visual deploy verification; gstack, cliclick, screencapture, curl+jq, xcrun simctl compose per stack), and produces the final receipt with binary anti-rationalization check. Three subcommands: /dogfood (full sequence — plan → execute → receipt), /dogfood plan (plan only), /dogfood receipt (receipt only, assumes plan exists in PR body or AGENTS.md). Inherits from broomva/bstack: cookb

0
installs
▌
Citable · broomva bundle
Make authored content survive the two selection surfaces it now faces: human engagement and LLM retrieval for citation. These partially anti-correlate, and the tactics that raise reactions are in two measured cases the ones that suppress citation. Encodes effect sizes from published causal studies (Scrunch, 12,000 ChatGPT observations via double machine learning; Semrush, 325,000 prompts over 89,000 cited URLs) rather than folklore, and ships a linter that enforces the mechanical half. Use when: (1) about to publish a post, article, headline, bio, or profile field and wanting it cited by AI answer engines, (2) auditing existing content for the unicode/link-in-comments/thin-specificity failures, (3) deciding whether a piece should be a short post or a long-form article, (4) converting existing long-form work (specs, ADRs, docs) into publishable articles, (5) choosing between optimizing for reach and optimizing for citation. NOT FOR: website/page markup, meta tags, JSON-LD, llms.txt or Core Web Vitals (use seo-

0
installs
▌
Sourcer · broomva bundle
Crawl a set of sites into a verified entity graph — companies, the people who run them, the relationships between them — where every claim points at the bytes it came from and nothing expands until it verifies. Agents read pages that are already on disk and return byte spans; a fetch daemon is the only thing that may put bytes there, so fabricating evidence is not a callable path rather than something a check must catch. Twelve gates run over what the run left on disk, eleven of them fail closed, and the suite proves itself each time by planting known-false claims its own gates must reject. Use it to supply the entities and edges that parallax and data-provider have no source for. USE WHEN map a company, who runs this company, find the relationships between these organisations, crawl this site into a graph, build an entity map, sourcer, recursive search, whole-site traversal, sitemap crawl, extract entities and relationships, verified crawl, expand only what verifies. NOT FOR reading one page you already have

0
installs
▌
Phronesis · broomva bundle
AI-native advisory practice for the Broomva ecosystem. Encodes top-firm consulting methodology (Three Horizons, MIT CISR digital maturity, JTBD, Value Proposition Canvas, RICE/ICE/WSJF, NPV + Real Options, QuantumBlack ML lifecycle, Wardley Mapping) as runnable typed primitives. Produces 7 Discovery-grade deliverables in two modes — consultant CLI or autonomous Life Runtime endpoint. Use when: (1) running an AI/digital consulting engagement, (2) building a maturity assessment, (3) generating prioritized use-case dossiers, (4) designing an innovation roadmap, (5) modeling ROI for AI initiatives, (6) designing controlled pilots, (7) extracting reusable IP from completed engagements. Triggers on 'consulting', 'consultancy', 'advisory', 'fast discovery', 'discovery sprint', 'AI maturity', 'digital maturity', 'use case ideation', 'use case prioritization', 'innovation roadmap', 'roi model', 'consultoría', 'evaluación de madurez', 'hoja de ruta'.

0
installs
▌
Premortem · broomva
Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'what could go wrong', 'am i missing anything', 'poke holes in this', 'where will this break', 'devil's advocate this'. Do NOT trigger on simple feedback requests, factual questions, or LLM Council requests. DO trigger when someone has a plan or commitment where the cost of being wrong is high.

0
installs
▌
Launch Video · broomva
Produce polished product launch videos using the Liquid Glass aesthetic — dark void backgrounds, 3D perspective floating UI panels, particle effects, spring animations, and cinematic pacing. Built on Remotion with Imagen 4.0 for frames and Veo 3.1 for B-roll. Use when: (1) creating a product demo or launch video, (2) showcasing a UI/app/tool with cinematic polish, (3) building a social-ready video from screenshots and renders, (4) applying the liquid glass floating panel style, (5) composing Remotion videos with 3D transforms and spring animations. Triggers on: 'launch video', 'product video', 'liquid glass video', 'demo video', 'showcase video', 'remotion video', 'floating panel', 'glass aesthetic'.

0
installs
▌
Drift Check · broomva
Compares stated priorities against where time and effort actually went, and produces a strategy drift report. Uses git log, vault priorities, and project docs to detect misalignment. Use when the user says "drift check", "am I on track", "priority alignment", "where did my time go", "strategy drift", or wants to audit focus vs intention.

0
installs
▌
Agentic Vps · broomva bundle
Provision and harden a fresh Linux VPS into an autonomous-agent dev host using the capability-preserving model — the box IS the sandbox: full agent autonomy inside it (non-root sudo user, open egress, YOLO mode, any toolchain), contained by ISOLATION (non-root + VPN-only access + snapshot + no-long-lived-secrets), not by restricting the agent. Composes an idempotent provisioning script, a staged firewall/VPN lockout-safe sequence, and a deterministic verification gate. USE WHEN setting up a new VPS/cloud box for Claude Code / agentic development, hardening a machine to run coding agents unattended, "set up another machine like srv1692698", provisioning an agent dev host, or auditing whether a box meets the agentic-host security invariants. NOT FOR generic server hardening with no agent on it (that's standard CIS/Lynis), desktop/laptop setup, or Kubernetes/multi-tenant clusters. Triggers on "set up a vps for agents", "agent dev host", "harden a box for autonomous agents", "new agent machine", "provision agenti

0
installs
▌
Unhobble · broomva bundle
Audit and rightsize a context surface — CLAUDE.md, AGENTS.md, a SKILL.md, a system prompt, or a single prompt — against the Claude-5 context-engineering reversals. Measures the surface (token budget, how much of it is phrased as hard rules vs judgment, near-duplicate sections, contradiction candidates, filesystem-derivable content, progressive-disclosure gaps), then adjudicates each section keep / relocate / delete using a grounding-aware predicate: prose backed by an independent mechanism is decorative and free to cut, prose that is the only carrier of a behavior is a real bet. Also rewrites prompts and skills from prohibition-form into judgment-form. Anthropic deleted >80% of Claude Code's system prompt for Claude 5 with no eval loss; this is the repeatable version of that cut. Use when: (1) a CLAUDE.md or AGENTS.md has grown and you want to know what is safe to remove, (2) an agent is ignoring or colliding with its own instructions, (3) a prompt is long and over-constrained and underperforming, (4) auditin

0
installs
▌
Braindump · broomva
Takes raw unstructured thoughts, voice transcript dumps, or stream-of-consciousness text and auto-files them into the right Obsidian vault folders with tags, backlinks, and proper frontmatter. Use when the user says "braindump", "brain dump", "capture this", "dump my thoughts", "I'm thinking about...", or provides a long unstructured block of text to organize.

0
installs
▌
Parallax · broomva bundle
Drive Parallax — a simulation runtime whose results carry how much of them was real. Point it at a context (a directory, an agent workspace, a table list), it proposes an ontology built from what is actually there, a human accepts that proposal before it can run, and only then does it roll the accepted model forward under candidate decisions. Every answer is typed observed or simulated. Use this skill to run the propose → answer → accept → run → receipt flow from the CLI or the agent tool surface, to decide the next command from `parallax status --json` rather than from conversation history, and to turn a typed refusal into the right remedy instead of paraphrasing its reason. USE WHEN parallax, simulate this change before applying it, what happens if we change this policy, propose an ontology, accept the ontology, roll it forward, run receipt, observed vs simulated, RECONCILIATION_UNACKNOWLEDGED, BLOCKING_QUESTIONS_OPEN, parallax status, parallax propose, parallax accept, parallax run. NOT FOR general Monte-C

0
installs
▌
Pre Mortem · broomva
Assumes a project has already failed, works backward to identify the top causes, scores them by likelihood and impact, and outputs a mitigation plan. Use when starting a new project, before a major launch, evaluating risky decisions, or when the user says "pre-mortem", "what could go wrong", "risk analysis", "failure modes", "red team this plan".

0
installs
▌
Broomva CLI · broomva
CLI for broomva.tech — manage prompts, skills, and context from the terminal. Pull/push prompts, browse the skills roster, and query project conventions.

0
installs
▌
Colab Remote · broomva bundle
Orchestrate Google Colab Pro/Pro+ GPU instances as remote training backends via SSH. Compounds /agent-browser (to launch Colab sessions and install colab-ssh) with SSH (to operate the runtime remotely). Use when: (1) launching a Colab notebook for GPU training, (2) running training jobs on Colab from the local terminal, (3) transferring datasets/checkpoints to/from Colab, (4) monitoring GPU utilization on a Colab instance, (5) integrating Colab GPU compute with /autoany EGRI optimization loops, (6) reconnecting to a Colab session after timeout. Triggers on: "colab", "colab-remote", "colab ssh", "colab training", "remote GPU", "colab pro", "train on colab", "google colab".

0
installs
▌
Comprehend · broomva
Agent→human teach-to-mastery loop. Turns the agent into a wise, effective teacher whose single objective is that YOU deeply understand a body of work — the problem and why it existed, the solution and why it was resolved that way (design decisions, edge cases), and the broader context (why it matters, what it impacts). Stage-gated (confirm mastery before advancing), active-recall driven (you restate first; the agent fills gaps; quizzes via AskUserQuestion), and goal-bounded (the session does not end until your understanding is verified). Default subject = the current session/diff; pass a PR number, file, or subsystem to teach that instead. The pedagogical INVERSE of grill-me: grill-me stress-tests YOUR forward plan; comprehend transfers mastery of EXISTING work to you. Distinct from handoff (agent→agent narrative) and Bridge/Bookkeeping (agent→KG). Use when: (1) you want to deeply understand what was just built, (2) onboarding yourself or a teammate onto a PR / file / subsystem, (3) post-mortem learning after

0
installs
▌
Resume · broomva bundle
Restore an arc that was killed mid-flight by something external — API 529 / 500, ENOTFOUND, ConnectionRefused, an expired login, a laptop that slept, a Ctrl-C. The operator restarts, types `resume`, and means *continue as though nothing had stopped you*: same arc, same plan, subagents and workflows that died put back on their feet. It does NOT mean "wrap up what you can". Nothing was written down in advance — the session did not intend to stop — so state is reconstructed forensically from the transcript, from the dead agents' surviving output files on disk, and from the tree. Distinct from `handoff` (a doc written on purpose for the next agent), `handback` (a message written on purpose for the human), and `persist` (a loop that restarts contexts by design). All three assume a VOLUNTARY stop that left an artifact. `resume` is the involuntary case. USE WHEN: "resume", "continue", "keep going", "carry on", "pick up where you left off", "as you were", "continue /autonomous", "resume the loop", or any session whos

0
installs
▌
Role X · broomva bundle
bstack P17 — Lens-Routed Request Articulation. The typed routing layer above P5 parallel-agent dispatch. On every substantive user input, the first-touch agent reflexively selects role lens(es) from `roles/<name>.md`, loads substantive context (files, conventions, domain checklists), and decides single-agent (augment) vs surfaced prompt-refinement (rewrite) vs parallel-team plan (decompose). No "act as X" persona theater — substantive context grounding only. Use when starting any session, before responding to any substantive user input. Composes with P5 (parallel-agent typing), P14 (the lens's quality_bar IS the domain-specific dep-chain trace), P15 (state snapshot feeds signals), and P13 (dream cycle consolidates lens rules from telemetry).

0
installs
▌
Blog Post · broomva bundle
Full-stack blog post production — turns a topic, idea, or brief into a complete publishing package across written, social, and multimedia surfaces. Generates broomva.tech .mdx posts (or Substack/other long-form), X posts and threads, LinkedIn posts, Instagram posts and reel scripts, plus multimedia asset plans (images, video, audio, GIFs). Outputs a structured content package to /broomva/posts/. Use when: (1) creating a new blog post or article, (2) turning an idea into multi-platform content, (3) producing a content package for a topic, (4) writing and distributing a post across channels, (5) generating social content from a long-form piece. Triggers on: 'blog post', 'new post', 'write a post about', 'content package', 'publish about', 'create post', 'blog-post'.

0
installs
▌
SEO Llmeo · broomva bundle
SEO and LLM Engine Optimization (LLMEO) skill for BroomVA content. Analyzes pages for traditional search-engine signals (meta tags, structured data, Core Web Vitals, internal linking) and for LLM discoverability (llms.txt, semantic headings, FAQ schema, citation-friendly structure). Generates actionable audits and rewrites. Use when: (1) auditing a page or site for SEO health, (2) optimizing content for LLM citation and AI search surfaces, (3) generating meta tags and structured data, (4) creating or updating llms.txt, (5) improving content structure for both Google and AI answer engines.

0
installs
▌
Disambiguate · broomva bundle
Rewrite a requirement so it can only be read one way. Distilled from ASD-STE100 Simplified Technical English — forty years of aerospace evidence about what a reader misreads when they cannot ask the author what he meant. Turns a vague ask ("handle errors gracefully", "the system should support X") into something atomic, owned, bounded, and testable, and says which of five reader-questions each defect leaves open. Ships a deterministic checker (scripts/disambiguate.py, stdlib only) that catches the mechanical ambiguity — agentless passive, noun stacks, weak modals, unquantified deltas, compound obligations, over-length sentences, condition-after-action, synonym drift — so judgment goes to the parts that need it. USE WHEN: sharpening a requirement, acceptance criterion, ticket, spec line, PRD, API contract, error message, runbook step, or agent prompt. Also when a review comment says "unclear" or "what does this mean", when two people read the same line differently, and when writing instructions for someone who

0
installs
▌
Content Engine · broomva bundle
Full-stack AI content studio — orchestrates visual DNA compilation, cinematic generation (via Higgsfield CLI or MCP), browser-automated tool execution, and multi-platform distribution into a unified content pipeline. Compiles brand identity, character sheets, and style guides into persistent knowledge (Karpathy compile-then-query pattern), then generates premium cinematic content using Higgsfield (30+ models including Soul V2, Nano Banana 2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2), Soul Cinema, Weavy, and ComfyUI with consistent character identity and intentional visual direction. Triggers on: 'content engine', 'generate campaign', 'compile brand', 'cinematic content', 'AI content studio', 'batch generate', 'content pipeline', 'visual DNA', 'character consistency', 'higgsfield', 'marketing studio', 'product photoshoot', 'soul character'.

0
installs
▌
Weekly Review · broomva
Scans the vault for updates from the past week, surfaces what changed, and flags what needs attention. Produces a structured weekly review. Use when the user says "weekly review", "week in review", "what happened this week", "weekly summary", "end of week review", or at the end of a work week.

0
installs
▌
Broomva Design · broomva bundle
Materialize and apply Broomva's platform-neutral calm blue-axis design system across digital products. Includes a portable DESIGN.md contract, semantic styling foundations, general React/web primitives, product-pattern and platform-adaptation guidance, and an optional agentic-work extension. Use for Broomva-branded web, native mobile, desktop, commerce, content, analytics, SaaS, internal tools, communication products, design reviews, or when a request mentions Broomva design, the blackhole mark, blue-axis styling, Undertow, receipts, DESIGN.md, or the Broomva component library.

0
installs
▌
Design Distill · broomva bundle
Distill a visual style from reference sites/products the user likes, then articulate it into a validated, dual-mode design system and a ready-to-run Claude Design ("Create Design System") handoff. Crystallized from the agents-dashboard run (checkit on handrovermeulen/Obsidian-Dashboard → moodboard → dual-mode tokens → Claude Design brief). It is a COMPOSITION skill — it fires existing tools (agent-browser capture, the Obsidian-Dashboard moodboard method, P18 format discipline, P11 dogfood validation, arcan-glass / ui-ux-pro-max) in sequence; it does not reimplement them. Core principle: MEASURED, NOT INFERRED — the palette and type come from computed styles extracted via headless browser, never from the model guessing at a screenshot. USE WHEN: distill a style, capture references, build a moodboard, "I like the look of X / use these as references", extract a palette from a site, design tokens from screenshots, create a design system from references, dual-mode (dark+light) design system, make a Claude Design b

0
installs
▌
Bookkeeping · broomva bundle
Universal knowledge engine — scores, promotes, and compounds knowledge across all sources into a permanent, query-able entity graph

0
installs
▌
Handoff · broomva bundle
Fresh-session handoff doc drafting. Produces a stable, single-file human-readable narrative state for the NEXT agent context (fresh session, after `/clear`, after persist iteration, after a tab close). The artifact lives at `docs/handoffs/YYYY-MM-DD-<arc>.md` and follows a stable shape: TL;DR + State-of-the-world (P15 snapshot) + What-was-delivered (PR table with SHAs) + First action + Pickup state. Distinct from P12 persist's `PROMPT.md` (machine-state for cross-context loop) and the P1 Bridge session log (raw transcript) — the handoff is the narrative bridge a human reads in ten seconds and a fresh agent reads in thirty. Use when: (1) ending a substantive session that another agent will continue, (2) preparing a fresh-session pickup point mid-arc, (3) needing to compress a multi-PR arc into a single resumable document, (4) the user says "write a handoff" / "fresh-session handoff" / "let me come back to this tomorrow". Triggers on "handoff", "fresh-session", "fresh session", "pickup", "where we are", "leave

0
installs
▌
Persist · broomva bundle
bstack P12 — Persistent Loop Discipline. Cross-context restart loop where state lives in the filesystem (PROMPT.md + git tree + state.jsonl), not in the conversation. Each iteration spawns a fresh agent context. Solves the 'context rot' failure mode where long-horizon agentic work (>1h, METR's 80%-reliability ceiling) degrades silently past ~100K tokens. Validation backpressure comes from compilers/tests/linters, not model self-grading. Use persist when: (1) starting work that may span hours and exceed the model's reliability horizon, (2) detecting context drift mid-session (token usage past 100K, repeated failed iterations on the same fix), (3) coordinating long-horizon work that needs to survive crashes / context exhaustion, (4) running parallel work streams (one persist loop per worktree, composed with bstack P5). Triggers on 'persist', 'long-horizon loop', 'context restart', 'fresh-context iteration', 'P12', 'Ralph loop', 'filesystem-state loop'.

0
installs
▌
Decision Log · broomva
Captures a decision with context, alternatives considered, and rationale, then links it to the relevant project doc in the vault. Creates a searchable decision record. Use when the user says "decision log", "log this decision", "record this choice", "document why we chose", "decision record", "ADR", or has just made an important decision.

0
installs
▌
Attempt Audit · broomva bundle
Find absence-assertions that carry no attempt-record — code that returns the same empty value whether the work RAN and found nothing or was SKIPPED entirely, so the caller cannot tell the two apart. Detects the concrete syntactic shape: a boolean parameter gates real work, and the function falls through to an empty sentinel that records nothing. Zero config, one command, plain-language findings; reports what it could not parse rather than letting a clean run and an empty run look identical. USE WHEN a check "passed" and you are not sure it ran, a manifest reports "no results / no findings / no speech", a gate went green after a rename, a test suite is suspiciously fast, or before trusting any tool that emits a negative verdict. NOT FOR general linting, dead code, or type errors — it answers exactly one question.

0
installs
▌
Creative Review · broomva
Meta-review skill for validating generated creative assets (videos, images, designs) against a reference style brief. Extracts frames, compares against style criteria, scores adherence, and produces actionable feedback for iteration. Self-improving feedback loop: each review refines the style brief for the next generation. Use when: (1) reviewing a generated video against a reference style, (2) validating visual quality of AI-generated content, (3) scoring style adherence of a Remotion composition, (4) comparing before/after creative iterations, (5) building a self-improving creative pipeline. Triggers on: 'review video', 'check style', 'creative review', 'style adherence', 'compare to reference', 'validate video', 'review reel', 'quality check'.

0
installs
▌
Handback · broomva bundle
Terminal-message contract for an autonomous arc that has run out of agent-executable work and genuinely needs a human. Produces a WORK ORDER — asks first, each one an imperative addressed to the reader, carrying a default so silence is never fatal (the exception is narrow and must be named: irreversible, externally visible, or spends money) — followed by the unchanged nine-item receipt. Distinct from `handoff` (same arc, different reader: `handoff` writes `docs/handoffs/` for the NEXT AGENT; `handback` writes the chat message for the HUMAN AS DECISION-MAKER). Asking is the last resort, not the interface: no ask may exist until the seven-rung autonomy ladder has been climbed and recorded. Use when: (1) an autonomous arc is stopping and at least one ask is open, (2) the user asks "what do you need from me" / "what's blocking", (3) a lane has parked on a human dependency and the arc is notifying, (4) writing any message whose purpose is to obtain a decision. Triggers on "handback", "hand back", "what do you need

0
installs
▌
Revenuecast · broomva bundle
revenuecast — turn a real-world capability into a self-demonstrating, high-throughput generative-AI revenue engine (the "Kleos" method). It is "/skillify for revenue": skillify turns a workflow into a tested skill; revenuecast turns a capability into a revenue engine whose own output IS the advertisement. The bstack-native composition of the 2026 "show-then-sell-the-system" creator loop (realosias, aivideoskool, GenHQ): Brand-Lock -> Show -> Distribute -> Hook -> Sell -> Moat, where the showcased output's desirability + accessibility-via-AI creates demand for the method, and you monetize the reproducible system. Composes content-engine (the factory), content-creation, blog-post, seo-llmeo, arcan-glass, social-intelligence, strategy-skills, and symphony/arcan (autonomous runtime). Its deterministic core (scripts/revenuecast_check.py) gates an engine-instance manifest on the design canon — own-the-audience, a real moat (not leakable prompts), the compliance/survival pillar (FTC v. Air AI / EU AI Act Art.50 / NO

0
installs
▌
Ocean Genomics · broomva bundle
Comprehensive bioinformatics and ocean genomics skill for eDNA metabarcoding, metagenomics, protein structure prediction, and marine biodiversity analysis. Use when: (1) Working with DNA/RNA sequences (FASTQ, FASTA, SAM/BAM, VCF files), (2) Running BLAST, QIIME2, Kraken2, or Nextflow pipelines, (3) Predicting protein structures via ESMFold2, AlphaFold, or ColabFold, (4) Analyzing environmental DNA (eDNA) from marine samples, (5) Querying marine databases (OBIS, BOLD, DOO, GenBank, UniProt), (6) Using biological foundation models (Evo 2, ESMC/ESMFold2, ProGen3), (7) Setting up MCP servers for bioinformatics (gget-mcp, bio-mcp), (8) Building agentic bioinformatics workflows, (9) Ocean biodiversity research, deep-sea species discovery, extremophile enzyme characterization, (10) Any task involving genomics, proteomics, transcriptomics, or computational biology.

0
installs
▌
Prompt Library · broomva bundle
Manage and retrieve reusable prompts from broomva.tech or any compatible prompt repository. Pull prompts by slug, category, or tag; push new prompts or update existing ones; list available prompts with filtering. Supports remote push/update/delete via authenticated API using OAuth session tokens. Use when: (1) user asks for a prompt, system instruction, or agent directive, (2) user wants to save a prompt for reuse, (3) user mentions "prompt library", "prompt repo", "save this prompt", "get prompt", "pull prompt", (4) agent needs a reusable system prompt for a task like code review, research, or architecture analysis, (5) user says "use the X prompt" referring to a named prompt. Default distribution endpoint: https://broomva.tech/api/prompts

0
installs
▌
Skills Catalog · broomva bundle
Canonical reference inventory of the 99 agent skills in the broomva/skills monorepo, organized into 23 single-noun category buckets that mirror the skills/<category>/ directory layout, with a Remotion video showcase generator and X thread copy. Use when discovering available skills, browsing the full skills catalog, generating skills showcase content, or understanding what capabilities are available across governance, orchestration, tooling, knowledge, research, strategy, cadence, publishing, video, audio, design, finance, compute, models, messaging, robotics, aerospace, neuroscience, healthcare, science, simulation, commerce, and everyday utilities. Triggers on "skills inventory", "list all skills", "what skills are available", "skills catalog", "skills showcase", "skills video", "showcase skills", "skills reference", or any request to browse, search, or visualize the skills monorepo.

0
installs
▌
Sdr Satellite · broomva bundle
Software-defined radio (SDR) and satellite reception toolkit — what to install, what you can hear from space, and how to compose the open-source stack (SatDump, SatNOGS, GNU Radio, rustradio, satkit). Covers hardware abstraction (SoapySDR, rtl-sdr-rs), DSP frameworks (GNU Radio, liquid-dsp, rustradio, radiorust), receiver UIs (SDR++, SDRangel, Gqrx, CubicSDR), satellite decoders (SatDump for NOAA APT, Meteor-M LRPT, GOES HRIT, Inmarsat), ground-station orchestration (SatNOGS network, sgoudelis/ground-station, Hamlib), orbit mechanics (SGP4 in Python + Rust, satkit astrodynamics, dSGP4 differentiable). Use when: (1) the user wants to receive satellite signals — weather imagery, ISS SSTV, telemetry, (2) building a ground station or scheduling observations on SatNOGS, (3) decoding TLEs and computing satellite passes, (4) composing SDR tooling into a Rust pipeline (e.g. for Life Agent OS, Opsis world-state events, or arcan/sensorium), (5) explaining what an RTL-SDR or HackRF actually does, (6) deciding between Sa

0
installs
▌
Cross Review · broomva bundle
bstack P20 — Cross-Model Adversarial Review Gate. The model that wrote the code cannot be the final judge of the code. Before substantive PRs merge, fire a cross-model adversarial gate — different evaluator than writer, anti-slop scoring ≥7/10, a dynamic round budget (3 free, 4-7 earned by a continuation verdict carrying a falsifiable prediction, >=8 human), verdict logged in PR. Three strata: (A) Codex CLI cross-vendor for true different-model verdict, (B) fresh-context subagent under devils-advocate brief, (C) composed existing adversarial-review skills always parallel. Use cross-review when: (1) about to push a substantive PR (>200 LOC OR public API OR multi-file OR governance-class), (2) reviewing a draft plan/design before implementation, (3) auditing a feature spec against single-model blind spots, (4) integrating with the /autonomous skill's pre-push gate. Triggers on 'cross-review', 'P20', 'adversarial review', 'anti-slop', 'cross-model gate', 'different evaluator', 'devils advocate gate', 'self-revie

0
installs
▌
Eve Forge · broomva bundle
Forge a personalized eve agent for a business end-to-end — absorb the business's artifacts, author the eve agent/ dir, validate, deploy to Vercel (or a VPS), smoke-test against ground truth, register, and evolve. The deterministic core is three safety gates distilled from a driven benchmark (BRO-1677): deploy-safety (never ship auth:none), validate (eve info --json → 0 diagnostics + tools registered), and smoke (drive the deployed agent, assert vs a ground-truth example). USE WHEN building/onboarding an eve agent for a tenant, "forge an eve agent", "deploy an eve agent", "onboard <business> onto eve", or when the Claude-Code orchestrator/forge must turn absorption inputs into a running eve operator. NOT FOR benchmarking frameworks (that's a one-off), running the operator itself (the forge builds it; the operator runs cheap on eve), or non-eve agent frameworks.

0
installs
▌
Format First · broomva bundle
Decide WHAT SHAPE of content to make, and refuse the platform folklore that circulates as fact. Encodes a claim set traced to primary sources — Meta's own engineering writeup and Transparency Center system cards, Mosseri's actual posts, and the psychology literature behind "hooks" and repetition — separating what is documented, what is hypothesis, and what is unsupported. Ships a linter that GRADES each claim — refuted, contested, unverified, folklore — and errors only on the ones contradicted by a primary source that was actually loaded, because "no source found" is a statement about a search, not about the world. The core move is choosing a FORMAT (visual grammar x script structure) as the invariant and letting topic vary, rather than the reverse. Use when, PRE-PRODUCTION: (1) choosing what shape a piece should take before it is written, (2) deciding how often to repeat a format and when to rotate it, (3) verifying a platform/algorithm claim from a course, thread, or guru, (4) auditing a draft or strategy d

0
installs
▌
Brainrot For Good · broomva
Produce high-retention, dopamine-aware video content using brainrot editing techniques — fast cuts, word-by-word captions, sound design, visual velocity, pattern interrupts — all in service of genuinely valuable content. The Fireship model: brainrot pacing meets real substance. Built on Remotion with Imagen/Veo for assets. Use when: (1) creating edutainment content that competes with brainrot for attention, (2) making technical content accessible to younger audiences, (3) producing TikTok/Reels/Shorts that teach while entertaining, (4) applying engagement psychology ethically, (5) adding brainrot energy to a launch video or product demo. Triggers on: 'brainrot', 'edutainment', 'fast-paced video', 'tiktok style', 'shorts style', 'dopamine video', 'high retention', 'fireship style', 'brainrot for good'.

0
installs
▌
Openrocket Sim · broomva bundle
Headless rocket design, simulation, and optimization using OpenRocket's Java core engine. Includes rocket-sim CLI tool for batch simulations and parameter sweeps, plus an AI-driven optimization loop using Claude. Use when: (1) designing model rockets programmatically, (2) running headless flight simulations, (3) optimizing rocket designs for altitude/stability/velocity, (4) batch-processing .ork files, (5) parameter sweeps over launch conditions, (6) AI-driven design optimization, (7) building a simulation pipeline or API wrapper, (8) exporting designs for 3D printing or laser cutting, (9) user mentions 'openrocket', 'rocket simulation', 'flight sim', 'rocket design', 'model rocket', 'rocketry', 'apogee optimization', 'thrust curve', 'rocket-sim'.

0
installs
▌
Morning Briefing · broomva
Reads open action items, this week's priorities, and recent vault updates, then produces a focused "start your day" brief. Use when the user says "morning briefing", "daily brief", "what's on my plate", "start my day", "what should I focus on today", or at the start of a work session.

0
installs
▌
Autonomous · broomva bundle
Use when the user has agreed on a plan or selected from suggested options and wants the agent to execute the work autonomously without further instruction. Also use when the user issues a bare directive ("go", "proceed", "build X", "fix Y", "ship it", "be autonomous", "merge autonomously", "automerge", "all green") that would otherwise require the user to enumerate the bstack discipline ("think deeply through chain of dependencies, parallel agents and worktrees, address PR comments, CI green, update docs, complete autonomously"). Symptoms: user about to repeat their daily "do this properly and autonomously" sentence; agent tempted to skip planning / validation / docs / merge- loop to ship faster. Replaces a ~50-word ritual instruction with one invocation. Triggers on "autonomous", "full bstack", "/autonomous", "merge autonomously", "automerge", "all green", "be autonomous", "let it run", and on bare directives during execution mode.

0
installs
▌
Data Provider · broomva bundle
Turn a question about the world into a table Parallax can accept, with every field typed observed or simulated at the moment it is written. You do the searching — WebSearch, WebFetch, whatever reaches the corpus — and this skill owns the parts that must be identical every time and checkable afterwards: recording a finding against the artifact it was read from, hashing that artifact, judging each column observed or simulated by a stated rule rather than by feel, and emitting the exact `parallax propose --kind business-data` invocation. Use it to supply the business-data ingress, which otherwise has no supplier and depends on a human typing a table list by hand. USE WHEN find companies, find leads, find prospects, find suppliers, research a market, build a table from search, prospect for clients, gather evidence into a table, supply business-data, data provider, feed parallax, observed vs simulated for search results. NOT FOR general web research you are going to read rather than model (just search); scraping a

0
installs
▌
Design Engineering · broomva bundle
Premium design engineering skill for agentic workflows — produces high-end, distinctive UI designs using DESIGN.md as the portable contract across Pencil MCP (in-IDE canvas), Figma MCP (team handoff + design tokens), and Google Stitch (vibe exploration + AI generation). Enforces anti-generic principles, WCAG 2.2 AA accessibility, perceptually uniform color, tiered animation timing, and screenshot-driven visual validation at every stage. Use when: (1) creating or reviewing UI designs from an agent, (2) generating DESIGN.md for a project, (3) implementing designs from Pencil .pen files or Figma URLs, (4) enforcing visual quality standards on AI-generated interfaces, (5) setting up a multi-tool design pipeline, (6) converting between design tools and production code. Triggers on: 'design engineering', 'design system', 'DESIGN.md', 'premium design', 'high-end UI', 'pencil design', 'figma to code', 'stitch design', 'vibe design', 'visual design review', 'glass design', 'design tokens', 'UI quality'.

0
installs
▌
Finance Substrate · broomva bundle
Personal finance and tax management substrate for Colombian residents. Imports bank transactions, tax certificates, and DIAN data. Projects annual tax liability (Form 210) with certificate-level accuracy. Handles password-protected PDFs from Colombian banks. Zero external paid services — all data stays local.

0
installs
▌
Wealth Management · broomva bundle
Wealth management, financial planning, and investment analytics skill. Compounds on finance-substrate for Colombian tax-optimized wealth building. Runs descriptive (portfolio health), predictive (compound growth projections, Monte Carlo), and prescriptive (allocation, rebalancing, tax-efficient withdrawal) analytics. Use when: (1) projecting long-term wealth growth, (2) optimizing asset allocation, (3) running scenario/stress tests on a portfolio, (4) planning tax-efficient contributions or withdrawals, (5) generating a wealth dashboard or net worth timeline, (6) goal-based financial planning (retirement, housing, education). Triggers on: 'wealth management', 'compound interest', 'asset allocation', 'portfolio projection', 'net worth forecast', 'retirement planning', 'investment strategy', 'rebalancing', 'monte carlo', 'financial plan'.

0
installs
▌
Stakeholder Update · broomva
Takes one set of project facts and generates three versions: technical for engineering, business-impact for leadership, and customer-facing for success teams. Use when the user says "stakeholder update", "write an update", "communicate this to different audiences", "translate for leadership", "customer-facing version", or needs to communicate the same information to different audiences.

0
installs
▌
Legal Readiness · broomva bundle
Build or adversarially audit an evidence-first legal-readiness system for a software product, SaaS, AI app, API, marketplace, or website. Inventory every public and contractual claim; determine jurisdiction, operator, customer, data-role, payment-channel, and product-behavior applicability; compare prose with repository, live, vendor, registry, contract, and operational evidence; close authorized code/documentation gaps; and leave counsel, tax, filing, entity, and external-account blockers explicit. Use when asked for a legal audit, legal shield, SaaS legal baseline, terms/privacy/consent/payment review, compliance gap analysis, legal readiness, legal standing setup, product-claim substantiation, or to make an app legally safer before launch. NOT FOR giving legal advice, declaring a product compliant or legally secure, forming an entity, filing registrations or taxes, signing contracts, inventing operator facts, or replacing licensed counsel.

0
installs
▌
Strategy Critique · broomva
Reads a strategy doc and writes a red-team critique with gaps, risks, and missing assumptions. Adopts an adversarial but constructive stance. Use when the user says "strategy critique", "red team this", "critique my strategy", "find the holes", "stress test this plan", "what am I missing", or provides a strategy document for review.

0
installs
▌
Prove The Negative · broomva bundle
Verify a claim whose evidence is an ABSENCE — blocked, denied, unreachable, isolated, not-logged, no-longer-present. Enforces that every denial is paired with a positive control that must SUCCEED, because "everything is denied" and "nothing ran at all" are the same observation. Ships a verdict gate that returns INVALID (exit 2) rather than PASS when the controls did not fire. USE WHEN validating a security boundary or sandbox, writing an eval whose passes are denials, confirming a capability was removed, checking that data is unreachable, or concluding from a probe that returned nothing. NOT FOR claims whose evidence is a presence (an output, a value, a rendered page) — those fail loudly on their own and need no control.

0
installs
▌
Colombia Conflict · broomva bundle
Knowledge engine over the Colombian Truth Commission (CEV) final report "Hay Futuro Si Hay Verdad" (2022) — the findings, statistics, armed-actor responsibilities, differential harms, coined lexicon, and the 67-recommendation roadmap for non-repetition (no repetición). Uses a kg/LLM-wiki retrieval architecture (substrate-canonical knowledge pages + a dense catalog projection for tier-1 routing + body-grep tier-2 + the agent as query engine) plus data-backed tools, including an `align` check that scores a proposed policy/action against the report's recommendation roadmap. USE WHEN reasoning about the Colombian armed conflict, peace process, transitional justice, victims, reconciliation, paramilitarism, the FARC-EP/ELN, narcotrafficking and drug policy, land/agrarian questions, the enemigo interno, falsos positivos, the Unión Patriótica genocide, social-leader killings, differential harms (ethnic peoples, women and LGBTIQ+, children, exiles, campesinado), territorial/human security, memory, or non-repetition; w

0
installs
▌
Heretic Abliteration · broomva bundle
Heretic — fully automatic LLM censorship removal (abliteration) and serving the result via Ollama. Wraps p-e-w/heretic: directional ablation (difference-of-means refusal directions, orthogonalizing attn.o_proj + mlp.down_proj) with an Optuna/TPE search that co-minimizes refusal count and KL divergence. Automates the full local workflow with the dependency + device fixes that make it actually run: clean-venv install (+ kernels/jinja2 fixes), device-correct run (CPU on Apple Silicon — MPS is blocked by a PyTorch GQA matmul bug; CUDA for real models), and the HF→GGUF→Ollama bridge. Includes a no-compute fast path: pull a pre-abliterated GGUF straight into Ollama. Use when: (1) decensoring / uncensoring an open-weight LLM locally, (2) running heretic-llm and hitting install or MPS/CUDA errors, (3) converting a Heretic/abliterated HF model to GGUF and serving it via Ollama CLI, (4) pulling a ready-made abliterated model into Ollama, (5) understanding abliteration as an evaluator-governed (EGRI) optimization loop.

0
installs
▌
Content Creation · broomva bundle
Full-stack content creation pipeline: idea or reference to published blog post, audio narration, video, and social media distribution. Orchestrates research, reference extraction, storytelling, AI visual assets (Nano Banana, Veo 3.1), TTS audio (Voicebox, kokoro-tts, Edge TTS), Remotion video, and social copy into a complete content package. Use when: (1) creating a blog post, case study, or writing entry, (2) turning an idea or experience into structured narrative, (3) using a reference post/video (X, LinkedIn, YouTube) as inspiration, (4) generating visual content (AI images, clips, screenshots, GIFs), (5) generating audio narration for posts, (6) creating social media content (X threads, Instagram carousels) from long-form writing, (7) packaging and distributing content across platforms. Triggers on 'new post', 'blog post', 'case study', 'content creation', 'write about', 'content pipeline', 'social content from post', 'use this as reference', 'generate audio', 'tts', 'narration'.

0
installs
▌
Audit Harness Usage · broomva bundle
Audit token usage and estimated API-equivalent cost across local agent harness traces from Codex CLI, Claude Code, Gemini CLI, and Cursor usage exports, plus quota-window status from a running Google Antigravity app, IDE, or CLI. Ships a read-only, standard-library Python scanner that normalizes incompatible cache/input/output semantics, deduplicates streaming records, implements CodexBar-derived lineage-aware Codex accounting locally, preserves Cursor list cost separately from charged cost, reports pricing coverage, renders self-contained HTML dashboards with improvement signals, and never copies prompt or response content into output. USE WHEN: the user asks how CodexBar or ccusage-style accounting works; wants token or cost statistics across coding agents; wants to find expensive models, cache efficiency, usage concentration, anomalous spikes, or unpriced models; says "token usage", "agent costs", "CodexBar cost", "Claude usage", "Gemini stats", "Antigravity quota", "Cursor usage export", "compare harnesse

0
installs
▌
Investment Management · broomva bundle
Investment management skill — portfolio construction, analysis, and execution. Compounds finance-substrate (accounting/tax) + wealth-management (projections/goals) into a full financial framework. Covers traditional investing (stocks, ETFs, bonds), alternatives (crypto, prediction markets, real estate, VC), quantitative analytics (factor models, Monte Carlo, optimization), and platform integration (Alpaca, Coinbase, Polymarket, agent-browser for Colombian platforms). Embodies philosophies from Buffett, Dalio, Bogle, Munger, and Marks. Use when: (1) building or analyzing a portfolio, (2) screening stocks/ETFs/crypto, (3) running backtests or factor analysis, (4) executing trades or rebalancing, (5) tracking investments across platforms, (6) researching market data or fundamentals, (7) making investment decisions with structured frameworks. Triggers on 'investment', 'portfolio', 'stocks', 'ETF', 'bonds', 'crypto', 'trading', 'backtest', 'factor model', 'rebalance', 'Polymarket', 'Alpaca', 'asset allocation'.

0
installs
▌
Claude Code Channels · broomva bundle
Set up Claude Code messaging channels for Telegram and Discord — bot creation, plugin installation, token configuration, access control (pairing, allowlists, guild channels), and troubleshooting. Use when the user asks to connect Claude Code to Telegram or Discord, configure a messaging bot, set up channel access, enable guild channels or threads, troubleshoot MCP server failures, or manage channel permissions. Triggers on "telegram channel", "discord channel", "claude code channels", "messaging bot", "set up telegram", "set up discord", "pairing code", "discord bot", "telegram bot", "channel access", "--channels".

0
installs
▌
Social Intelligence · broomva bundle
Autonomous social engagement + knowledge extraction loop for Moltbook and X/Twitter. Runs the engagement loop (post substantive comments, solve verification challenges, reply to mentions, quote-tweet), extracts knowledge from all interactions into the broomva research vault, and compounds with /blog-post and /content-creation to turn discovered insights into published content. Integrates with knowledge-graph-memory for cross-session persistence. Use when: (1) running the social engagement loop, (2) extracting knowledge from recent interactions, (3) generating content from trending ideas found in social threads, (4) planning X outreach or Moltbook engagement strategy, (5) turning community insights into blog posts or threads. Triggers on: "social loop", "engagement loop", "moltbook", "extract insights", "knowledge from interactions", "what's trending on moltbook", "run the loop", "social intelligence", "outreach strategy".

0
installs
▌
Capx Agentic Robotics · broomva bundle
Agentic robotics with CaP-X — LLM-driven robot manipulation via code generation. Use when: (1) Setting up CaP-X / CaP-Gym environments for robot manipulation benchmarks, (2) Running CaP-Bench evaluations across LLMs/VLMs on robotic tasks, (3) Building or extending CaP-Agent0 agentic harnesses (skill libraries, visual differencing, parallel reasoning), (4) Training robot coding agents with CaP-RL (GRPO on code generation), (5) Developing perception APIs (SAM3, Molmo, depth, point clouds) or control APIs (IK solvers, grasp planners), (6) Sim-to-real transfer for Franka Panda, R1Pro humanoid, or other robot platforms, (7) Designing auto-synthesized skill libraries for physical manipulation (Voyager-style), (8) Integrating agentic robotics with Life Agent OS (Arcan orchestration, Spaces agent networking, Lago persistence), (9) Any task involving LLM-based robot control, manipulation benchmarks, robotic code synthesis, or embodied AI agents.

0
installs
▌
Founder Mode Oncology · broomva bundle
Personalized cancer treatment navigation — maximal diagnostics, parallel therapy, therapeutic development, structure-based protein design. Use when (1) researching cancer treatments or combinations, (2) designing diagnostic strategies, (3) evaluating neoantigen vaccines or radioligand therapies, (4) navigating FDA expanded access or IRB processes, (5) interpreting ctDNA/MRD data, (6) building bioinformatics pipelines, (7) scRNA-seq target discovery, (8) AlphaFold/RFdiffusion/ProteinMPNN for neoantigen validation or de novo binder design, (9) patient advocacy. Keywords — cancer, oncology, neoantigen, vaccine, immunotherapy, radioligand, ctDNA, scRNA-seq, FAP, AlphaFold, RFdiffusion, ProteinMPNN, personalized medicine.

0
installs

116 published skills · page 1 of 2