akillness
- 475 skills
- 0 followers
- 57 repo stars
- 2 days ago last updated
- ▌ Codebase Design 2 · akillness bundleShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
- ▌ Moneyprinter V2 · akillness bundleOperate FujiwaraChoki/MoneyPrinterV2 (MPV2), the AGPL-3.0 Python CLI that automates online-income workflows: YouTube Shorts generation and upload, a Twitter/X posting bot, Amazon affiliate pitches, and Google-Maps-based local-business outreach. Use when the user names MoneyPrinterV2, MPV2 or its `src/main.py` menu, `config.json`, `.mp` cache or `src/cron.py` and needs a fit check, install, configuration, offline preflight, a run, scheduling, or troubleshooting. Do not use for harry0703/MoneyPrinterTurbo (use `moneyprinter-turbo`), generic video production, or bulk unsolicited email and platform-evasion automation. Triggers on: MoneyPrinterV2, MoneyPrinter V2, MPV2, 유튜브 쇼츠 자동화, 트위터 봇, 제휴 마케팅 자동화, 콜드 메일 자동화, 돈 버는 프로그램.
- ▌ Open Ontologies · akillness bundleOperate fabio-rovai/open-ontologies, the Rust RDF/OWL semantic planning and verification engine: inspect and validate ontologies, plan changes, query/reason, produce certificates, or connect its MCP interface. Use when users name Open Ontologies, `open-ontologies`, `oo-cert`, or ask for change-impact/certified ontology operations. This is an ontology engine and CLI/MCP server, not a visual ontology editor; route visual editing to Protégé or a workbench skill.
- ▌ Shopping Shorts · akillness bundle상품 링크나 권리 확인된 제품 사진을 근거 중심의 9:16 쇼핑 쇼츠 패키지로 전환한다. Use when 쇼핑 쇼츠·상품 추천 숏폼·어필리에이트 영상·AI 제품 광고를 조사, 기획, 생성, 검수하거나 YouTube·Instagram Reels·TikTok·X·네이버 클립과 YPP·쿠팡·지그재그 등 한국 크리에이터 수익 경로를 현재 공식 조건으로 비교할 때. Open-Generative-AI를 영상 생성 표면으로 연결하되 가짜 체험담, 경쟁 영상 복제, 대량 양산, 무고지 제휴, 승인 없는 가입·유료 생성·업로드에는 사용하지 않는다.
- ▌ Agent Principles 2 · akillness bundleCore principles for collaborative development with AI agents. Defines divide-and-conquer, context management, abstraction-level selection, automation philosophy, and verification/retrospectives. Apply optimal collaboration patterns when using any AI agent. Also the owner of the retired `agent-development-principles` name (merged 2026-09-19). Triggers on: agent principles, agentic development principles, AI collaboration principles, context-management strategy, how to work with coding agents.
- ▌ Deep Agents Core · akillness bundleINVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
- ▌ Design Taste · akillness bundleOperate madebymustafa/design-taste as a selective genre-and-craft reference for a brief-led marketing page or portfolio. Use when the user names Mustafa, madebymustafa/design-taste, its corporate-trust or editorial-minimal packs, or asks to choose among that repository's genre identities. Route ordinary anti-generic frontend work and Leonxlnx dial-based taste work to design-taste-frontend; route visual-effect recipe discovery to web-design.
- ▌ Jolt Physics · akillness bundleOperate jrouwe/JoltPhysics for native C++ physics integration, pinned builds, body lifecycle, collision queries, determinism checks, or Jolt-specific failures. Use when the request names Jolt Physics, its JPH API, or this repository. Route ordinary Godot physics settings, unrelated physics engines, and JavaScript binding work to their own owners; this skill does not install or build anything by activation.
- ▌ Better Design · akillness bundleOperate marvkr/better-design as a schema-checked design MCP and shadcn registry workflow: retrieve focused guidance, choose an approved system, inspect tokens and component payloads, and review a UI with explicit evidence. Use when the user names Better Design, better-design.com, its MCP tools, or a Better Design registry URL. Keep general design-token and primitive API governance in design-system and visual recipe selection in web-design.
- ▌ Helix Foundry · akillness bundleOperate HelixDB/helix-foundry, the local-first company-data workspace that connects databases, hosted providers, APIs, files, Stripe, WorkOS and PostHog into an ontology backed by HelixDB and DuckDB. Use when the user names Helix Foundry, asks to install/start/diagnose its Docker Compose stack, inspect its local API or SDK, connect a source, run a sync/query/pipeline, review an ontology proposal, or back up/restore/upgrade an installation. Keep setup local and loopback-only; distinguish read-only inspection from data, credential, network, cloud-cost, and destructive operations.
- ▌ Hyper Extract · akillness bundleOperate yifanfeng97/Hyper-Extract, the Python `he` CLI for extracting structured knowledge from documents with templates, provider configuration, indexing, search and an MCP server. Use when users name Hyper-Extract, `he`, or ask about this document-to-knowledge CLI. It is a configurable extraction workflow, not a general-purpose ontology editor or database; route graph pipeline questions to Semantica and visual OWL/SKOS editing to OrionBelt.
- ▌ Jev Ultrafast · akillness bundleOperate browser-use/jev-ultrafast, the MIT-licensed Python browser agent that combines TypeSafe Jev choices with Browser Harness. Use when inspecting or pinning its checkout, running offline tests and browser guards, launching the loopback inspector, or reviewing a library/demo run. Triggers on Jev Ultrafast, jev-ultrafast, `uv run jev`, or its browser-agent loop. Require separate approval for package downloads, provider calls or spend, page/DOM egress, live-site navigation or actions, and recording artifacts. Route generic browser automation to `browser-harness` or `playwriter`, and hosted Jev API work to `typesafe-ai`.
- ▌ Meshoptimizer · akillness bundleOperate zeux/meshoptimizer for source-pinned native or JavaScript/WASM integration, meshopt simplification, meshlets and codecs, or preservation-aware gltfpack conversion. Use when the request names meshoptimizer, meshopt APIs, gltfpack, MeshoptDecoder or EXT/KHR_meshopt_compression. Route generic mesh modeling, unrelated compressors and Three.js gameplay to their own tools; this is not a renderer or general game-development guide.
- ▌ Ozz Animation · akillness bundleOperate guillaumeblanc/ozz-animation for pinned-source preflight, glTF or FBX-to-ozz conversion, CMake/runtime integration, animation-job debugging, and format migration. Use when the request names ozz-animation, gltf2ozz, fbx2ozz, SamplingJob, BlendingJob, or LocalToModelJob. Preserve engine boundaries and asset rights; route generic Three.js animation to threejs-animation and The Forge integration to the-forge. Installing this guide does not install the library, SDKs, tools, or assets.
- ▌ Paper Shaders · akillness bundleIntegrate and diagnose Paper Shaders from paper-design/shaders: choose vanilla or React packages, mount a named shader, tune uniforms and rendering bounds, freeze motion, and release its WebGL resources. Use when the request names Paper Shaders, @paper-design/shaders, @paper-design/shaders-react, or asks to adopt their MeshGradient or ShaderMount. Route generic shader authoring, Three.js scenes, and UI Layouts component adoption to their own owners.
- ▌ Craft Anything · akillness bundleOperate storytold/craft-anything, the open-source pure-Rust clean-room software reverse engineering and AI rebuilding engine, its desktop app, `craft-anything-cli`, and MCP server. Use when a user asks to inspect how shipped software works (binaries, Electron/JS, Android APK, .NET, WebAssembly, firmware, packet captures), run clean-room or deep analysis, execute `craft-anything-cli rebuild` to study and rebuild software with coding agents (Claude Code, Copilot, Grok), run `craft-anything-cli doctor/setup/mcp`, manage investigation memory (briefs, plans, hypotheses, findings, handoffs), or inspect source-pinned checkouts. Keep code execution, device changes, live network targets, and agent configuration writes approval-gated. Route generic repository searches to `codebase-search` and browser automation to `browser`.
- ▌ Diagram Design · akillness bundleUse when creating source-grounded branded diagrams with cathrynlavery/diagram-design: run its offline preflight, choose a semantic pattern and visual type, author self-contained HTML with inline SVG, verify accessibility and geometry, open or screenshot local output when a browser is available, export manually to SVG or PNG, import and redraw Mermaid, draw.io, or Excalidraw content, and adapt the style guide to approved brand tokens. Keep static output, local paths, and font/network boundaries explicit. Never install or publish without approval. Route editable .drawio diagrams and draw.io CLI exports to `drawio`, academic paper figures to `paperbanana`, and slide decks to `slides-grab` or `presentation-builder`.
- ▌ Langchain Bmad 2 · akillness bundleUse when the user needs BMAD-style phased delivery for a LangChain, LangGraph, or Deep Agents project and wants the right framework skill at the right BMAD phase. Triggers on: langchain bmad, bmad langchain, langgraph bmad, deep agents bmad, structured agent development, phase-gated langchain workflow, framework-aware bmad, and BMAD for agent frameworks.
- ▌ Material Maker · akillness bundleOperate RodZill4/material-maker for procedural PBR node graphs, 3D texture painting, profile-aware CLI exports, version-fit source packaging, and Material Maker failures. Use when the request names Material Maker, its .ptex workflow, or this repository. Route generic Godot shaders, other material editors, and Terrain3D work elsewhere. Respect upstream prohibition on AI/LLM or agentic pull requests; activation does not install or launch the app.
- ▌ Lightpanda · akillness bundleOperate lightpanda-io/browser, the headless browser for AI and automation: offline preflight, release selection, approved fetch and CDP/MCP integration. Use when users name Lightpanda or need its source-pinned setup and runtime boundaries; route generic browser automation to browser-harness or playwriter.
- ▌ Memmachine · akillness bundleOperate MemMachine/MemMachine, the agent long-term memory server, Python/TypeScript clients and MCP integration. Use when a task names this exact repository, its server, memory APIs, deployment or MCP tools. For general memory architecture selection use agent-memory-architecture; for generic MCP design use mcp-builder.
- ▌ Pixeltable · akillness bundleBuild or operate applications with pixeltable/pixeltable, the Python multimodal database and `pxt` catalog CLI. Use for tables/views, computed columns and indexes, media ingestion/query workflows, schema reconciliation, local daemon/configuration, or Pixeltable Cloud/service operations. Distinguish its multimodal data model from ontology catalogs and Markdown knowledge graphs.
- ▌ Trickle UI · akillness bundleInspect and integrate akaieuan/trickle-UI-kit text animations through its shadcn-style registry, or review TextRoot and Typewriter lifecycle behavior. Use when the user names Trickle UI Kit, tricklekit.dev, its registry JSON, CSS text reveals, or its Typewriter integration. Route unrelated React Bits components to react-bits and page-wide animation profiling to optimize-web-animations.
- ▌ UI Layouts · akillness bundleSelect and adapt UI Layouts components and blocks from ui-layouts/uilayouts: inspect registry payloads, reconcile imports and dependencies, preserve responsive behavior, and verify interaction semantics. Use when the request names UI Layouts, ui-layouts.com, its responsive modal, or a specific UI Layouts block. Route generic responsive strategy, shared primitive architecture, Paper Shaders runtime integration, and unrelated cursor libraries to their own owners.
- ▌ Blender MCP · akillness bundleOperate ahujasid/blender-mcp, the MIT-licensed MCP server plus Blender addon that lets an AI client drive Blender for scene inspection, modeling, materials, rendering, asset import, and GLB or FBX export. Route one request to one mode: fit-check the project; preflight the host, addon, and port; install and wire a client such as Claude Desktop, Cursor, VS Code, Codex, or OpenCode; harden the arbitrary-code path with safe mode; control telemetry and privacy before touching client work; source or generate 3D assets under their licences; export to disk; or troubleshoot a broken connection. Use when a user wants an AI agent to control Blender. Triggers on: blender-mcp, MCP for Blender, control Blender with Claude, execute_blender_code, BLENDER_MCP_SAFE_MODE, Poly Haven, Hyper3D Rodin, Hunyuan3D, Sketchfab import, Poly Pizza, Blender addon port 9876.
- ▌ Opencreator · akillness bundleOperate krillinai/OpenCreator, the Codex CLI-based creator workspace: choose the Desktop, CLI, or Server path; inspect a pinned checkout; configure integrations; use creator tasks; manage Skills, MCP, and schedules; or troubleshoot an output. Use when the user names OpenCreator, KrillinAI, its local Runtime, or its creator/agent workspace. Require separate approval before installers or source dependencies, credentials or provider linking, paid generation or credit purchases, downloads, MCP or scheduled execution, external publication, network exposure, or deletion. Route code-first video production to `video-production`, long-form clipping to `autoclip`, local timeline editing to `opencut`, and general skill authoring to `skill-standardization`.
- ▌ Superdesign · akillness bundleOperate Superdesign canvas UI drafts through its CLI: prepare approved source context, resume a saved target, reproduce an existing page, refine a selected direction, compare requested alternatives, or extend a confirmed flow. Use when the user names Superdesign, superdesign-skill, a Superdesign draft/canvas URL, or its create-design-draft and iterate-design-draft commands. Route general visual recipes to web-design and shared token/component governance to design-system; this is not the legacy Superdesign VS Code extension.
- ▌ Voicestudio · akillness bundleUse when operating debpalash/VoiceStudio as a local-first voice cloning, voice design, speech generation, transcription, and video-dubbing repository: inspect the Electron and FastAPI surfaces, check host fit offline, prepare approval-gated installs and launches, map Hugging Face model downloads and licenses, use the local MCP/API, and troubleshoot model, device, port, and media failures without claiming runtime proof. Require documented speaker consent before cloning a real person's voice and refuse impersonation or fraud. Route hosted ElevenLabs TTS to `elevenlabs-tts`, programmatic or templated video assembly to `video-production`, timeline editing to `opencut`, and hosted generative video to `open-generative-ai`.
- ▌ A2a Protocol 2 · akillnessAgent-to-Agent horizontal messaging — Linux Foundation AAIF 2026 standard. Use when multiple agents across systems/vendors need to exchange tasks, results, or capabilities without sharing a runtime.
- ▌ Agent Beacon · akillness bundleOperate Asymptote-Labs/agent-beacon, the cross-harness coding-agent session history and self-improving memory layer. Use when users name Agent Beacon, beacon.sh, Beacon endpoint capture, trace replay, lenses, memory recall/distillation/promotion, or its CLI/MCP integration. Route setup, local/cloud destination choices, private session access, sharing and removal through explicit approval gates. This is the named Beacon project, not a generic tracing SDK, memory-backend selector, or agent-team runtime.
- ▌ Context Mode · akillness bundleOperate mksglu/context-mode, the Elastic License 2.0 MCP and hook/plugin system for temporary-script subprocess execution (not an OS/security sandbox), FTS5 indexing, context-savings telemetry, and session recovery. Use for install, inventory, verification, diagnosis, or measurement on Claude Code, Codex CLI, Gemini, Copilot, Cursor, OpenCode, KiloCode, OpenClaw, Pi, OMP, or another listed client. Also triggers on context-mode, ctx_execute, ctx_search, ctx_doctor, ctx_stats, or MCP/hook routing for this project.
- ▌ Prototype 2 · akillness bundleBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
- ▌ Semantica · akillness bundleOperate semantica-agi/semantica, the Python graph-native knowledge engineering toolkit: choose ingestion, parsing, extraction, graph/triplet/vector stores, CLI, server or MCP entrypoints; diagnose optional integrations and backend configuration. Use when users name Semantica or ask for a modular Python pipeline spanning documents, knowledge graphs, provenance or reasoning. It is an application/library framework, not a single graph database; route a dedicated ontology workbench to OrionBelt or certified ontology change planning to Open Ontologies.
- ▌ Stagehand 2 · akillness bundleOperate Browserbase Stagehand, the MIT-licensed browser-agent SDK and `browse` CLI for local or Browserbase Chromium automation, natural-language `act`, `observe`, and `extract`, typed WebMCP calls, cloud Search/Fetch, Playwright migrations, and Browserbase MCP integration. Use when a user wants to build, run, debug, or migrate a Stagehand browser agent, choose local versus cloud browser execution, or configure the `browse` command surface. Triggers on: stagehand, @browserbasehq/stagehand, browserbase.launch, localBrowser.launch, act(), observe(), extract(), WebMCP, browse CLI, Browserbase MCP.
- ▌ Terrain3d · akillness bundleOperate TokisanGames/Terrain3D for Godot version compatibility, addon installation or source builds, region and heightmap integration, terrain API work, upgrades, and Terrain3D-specific failures. Use when the request names Terrain3D, Terrain3DData, or this repository. Route generic Godot terrain choices, voxel worlds, and other terrain plugins to their own owners; activation never installs or upgrades the addon.
- ▌ The Forge · akillness bundleOperate The Forge graphics framework at its current Codeberg source: inspect pinned Windows/D3D12 scope, audit component licenses, plan example builds, integrate IApp/resources/FSL, and debug graphics ownership. Use when the request names The Forge, The-Forge/The-Forge, ForgeShadingLanguage, or its framework examples. Separate legacy ConfettiFX GitHub versions, commercial platforms, restricted SDKs, and build-started ReloadServer; route standalone ozz work to ozz-animation.
- ▌ Video Use · akillness bundleDrive browser-use/video-use, the open-source conversational video editor for Claude Code, Codex, and coding agents. Drop raw footage into a directory and edit by natural language chat: transcribe and build packed phrase-level transcripts (takes_packed.md), cut filler words and dead space, auto color grade segments, apply 30ms audio fades at cuts, burn custom styled subtitles last in the filter chain, spawn animation overlays (HyperFrames, Remotion, Manim, PIL) via parallel sub-agents, self-evaluate cut boundaries with timeline_view before presentation, and persist session memory in project.md. Use when the user asks to edit raw video footage with Claude Code, cut filler words, color grade, burn subtitles, generate video overlays, or run conversational video editing. Triggers on: video-use, video use, edit video with Claude, conversational video editor, cut filler words, auto color grade, timeline_view, takes_packed.md, edit/final.mp4.
- ▌ Zvec Grep 2 · akillness bundleDrive zvec-grep (`zg`), zvec-ai's local-first workspace search CLI and MCP server, to index code and documents, run hybrid, vector, BM25, or exhaustive managed ripgrep searches, configure agent integrations, and diagnose index or server freshness. Use when a task needs local workspace-grounded retrieval across code, Markdown, text, structured data, or images. Triggers on: zvec-grep, zvec grep, `zg`, @zvec/zvec-grep, local-first workspace search, hybrid workspace search, semantic repository search, zvec MCP, zvec_grep_search, managed ripgrep, `.zvec-grep`, or Remote Embedding authorization.
- ▌ Fastnoise2 · akillness bundleOperate Auburn/FastNoise2 for pinned C++ or C API integration, FastSIMD node graphs, encoded tree loading, deterministic batch noise, or the optional FastNoise2 Node Editor. Use when the request names FastNoise2, its FastNoise:: APIs, FASTNOISE2 build options or Node Editor serialization. Route FastNoise Lite, shader noise and general terrain generation without this library to their own tools; this is not a terrain engine or GPU noise framework.
- ▌ Impeccable · akillness bundleOperate pbakaus/impeccable, the design vocabulary and slop detector for coding agents: offline preflight, collision-aware install planning, routing to its commands (shape, init, document, extract, critique, audit, polish, bolder, quieter, distill, harden, onboard, animate, colorize, typeset, layout, delight, overdrive, clarify, adapt, optimize, live, generate), detector triage, and a standalone method when the upstream skill is absent. Use when users name Impeccable, /impeccable or $impeccable commands, npx impeccable, its design hook or 62-rule detector, or its PRODUCT.md/DESIGN.md workflow. Route generic anti-generic taste work to design-taste-frontend, accessibility remediation to web-accessibility, token governance to design-system, and visual recipes to web-design. Installing this guide does not install Impeccable, its engine or hooks.
- ▌ Fineenvs · akillness bundleInspect and run the source-verified adithya-s-k/FineEnvs environment and dataset projects, including OpenEnv, ORS, NeMo Gym, Verifiers, SkyRL Gym, and GEM dialects. Use when the user names FineEnvs, supplies a checkout, asks for a local smoke or reward-evidence readout, or wants to author an environment against its bundled contracts. Route generic training, RL algorithms, serving, and provider operations to their owning skills.
- ▌ Harness2 · akillness bundleOperate google-research/harness2 (Harness²), the Apache-2.0 framework for recursive agent harnessing: refine the prompts, guardrails, memory, tool guidance, subagents, skills, scripts, and plugins around a fixed model through contrastive Propose-Probe-Compose steps and a per-domain improvement library. Use when a user wants to run the credential-free local demo, preflight or set up the LAB, JobBench, or WorkBuddy benchmarks, budget and launch a parallel or sequential refinement run with OpenCode or Codex executors, judge and report results, start the Codex bridge, or apply the method by hand to design or refine their own agent harness or agent team. Owns the retired `harness` name. Route reusable SKILL.md ratcheting to `skill-autoresearch`, multi-agent coordination evals to `multi-agent-eval-harness`, production tracing to `agent-observability`, and runtime team execution to `paperclip`, `ruflo`, or `zeroshot`.
- ▌ Hyperiux · akillness bundleInspect and integrate Hyperiux Vault effects from Hyperiux-Immersion-Labs/hyperiux-components. Use when the user names Hyperiux, the hyperiux CLI, hyperiux.json, or a Vault effect; choose public-source review, approved project integration, or lifecycle repair. Distinguish MIT tooling from restricted Effects licensing and review installer CSS changes before execution. Not a generic animation library selector or a Pro-access bypass.
- ▌ Pixelrag · akillness bundleOperate StarTrail-org/PixelRAG for screenshot-based visual retrieval: render pages or documents into image tiles, chunk/embed them, build a FAISS index, configure local search, or inspect its search API. Use when the task names PixelRAG, pixelshot, or multimodal visual RAG. It retrieves visual content; it is not a text-only RAG framework, database, or semantic ontology. Route general text-RAG orchestration to langchain-rag.
- ▌ Turbovec · akillness bundleUse the RyanCodrai/turbovec project when integrating its in-process Python or Rust TurboQuant vector index: create an index, quantize/search vectors, persist/load a file, apply ID filters, or choose its framework adapters. Trigger on turbovec or TurboQuantIndex. Route hosted vector databases and replication needs to a server product such as Typesense; turbovec itself is a library, not a network service.
- ▌ Canvas UI · akillness bundleOperate DavidHDev/canvas-ui for selecting and integrating its live-DOM canvas effects, checking framework/renderer packaging, HTML-in-Canvas fallback, lifecycle and license boundaries. Use when the user names Canvas UI, canvasui.dev, @canvas-ui registry items, or its Liquid/ParticleScroll effects. Route ordinary animated React components to react-bits and custom visual recipe discovery to web-design; this is not a general drawing-canvas toolkit.
- ▌ Cocoindex · akillness bundleOperate cocoindex-io/cocoindex when building or troubleshooting incremental Python data flows: declare sources, transformations, targets, app state, CLI updates, live processing, or connectors for RAG/indexing. Use when the request names CocoIndex or needs its change-aware ETL pipeline. CocoIndex is not itself a database or vector store; route database schema design to database-schema-design and ordinary framework RAG work to langchain-rag.
- ▌ Effekseer · akillness bundleOperate effekseer/Effekseer for effect authoring, runtime integration, release selection, build planning, and license review. Use when the user names Effekseer, an .efkefc effect, its Manager API, or an Effekseer renderer/plugin. Route generic game VFX to game-vfx and Blender work to blender-mcp; this is not an engine-neutral particle design guide.
- ▌ Filmcraft · akillness bundleOperate the FilmCraft open-source Rust video editor through its installed `filmcraft-cli` headless CLI/MCP server or desktop loopback control bridge: inspect projects and sequences, import media, run undoable commands, render previews, save `.fcproj` projects, and export media or interchange files. Use when a user asks to edit, automate, inspect, or troubleshoot FilmCraft. Route programmable or templated video generation to `video-production`, OpenCut repository work to `opencut`, and Palmier Pro timeline work to `palmier-pro`.
- ▌ Gitingest · akillness bundleOperate coderamp-labs/gitingest, the MIT-licensed tool that turns a Git repository or local directory into one prompt-friendly text digest (summary, directory tree, file contents, token estimate) through the `gitingest` CLI, the Python `ingest` API, the hosted gitingest.com site, or a self-hosted FastAPI server. Use when the user names gitingest or gitingest.com, wants to replace "hub" with "ingest" in a GitHub URL, or needs a whole-repository digest to paste into an LLM, with include or exclude patterns, size limits, a branch or subdirectory, or a private-repository token. Decide local CLI versus hosted site first. Do not use for repository-aware coding, semantic search of a codebase, or digesting a tree that contains secrets. Triggers on: gitingest, git ingest, hub to ingest, repo to prompt, 깃허브 코드 전체를 프롬프트로, 코드베이스 텍스트 덤프, digest.txt.
- ▌ Memsearch · akillness bundleOperate zilliztech/memsearch, the Markdown-canonical agent memory tool with a Milvus search index: CLI, platform plugins, config, indexing, recall and reset. Use when a request names this exact project. For neutral memory-backend choices use agent-memory-architecture; for other memory products use their operator.
- ▌ Paperclip · akillness bundleOperate Paperclip's agent-company control plane: inspect and configure companies, agents, projects, workspaces, issues, company skills, routines, heartbeats, artifacts, and integrations. Use when the user names Paperclip or paperclipai, asks to manage a Paperclip company, agent, task, skill, routine, or run, or needs Paperclip setup or troubleshooting. Also triggers on agent company, Paperclip heartbeat, or Paperclip control plane. Route local tmux lifecycle work to agent-manager, executive-team app operations to openexecutive, and team architecture to harness.
- ▌ Pm Skills · akillness bundleAI operating system for product managers — 65 skills, 36 commands across 8 plugins encoding PM frameworks by Teresa Torres, Marty Cagan, Alberto Savoia, and other PM thought leaders. Use when doing product discovery, writing PRDs, defining strategy, conducting user research, planning go-to-market, running data analytics, or managing sprints. Triggers on: pm-skills, product manager, product discovery, write PRD, user story mapping, product strategy, north star metric, opportunity solution tree, sprint planning, go-to-market, market research, product roadmap, pretotyping, jobs to be done.
- ▌ Llmfit · akillness bundleOperate AlexsJones/llmfit to inspect detected hardware, rank model fit, estimate plans and storage, run the local REST API, and separate formula-based estimates from measured inference. Use when a user asks what LLMs fit a machine, how much RAM/VRAM a model needs, which runtime is plausible, or whether a result is measured versus estimated. Do not use this skill to install binaries, pull models, benchmark a provider, or submit community results without explicit approval.
- ▌ Memori · akillness bundleOperate MemoriLabs/Memori, its agent-memory SDKs, cloud/BYODB modes, runtime configuration and SQL storage integration. Use when the task names this exact project or its code. For product-neutral memory architecture decisions use agent-memory-architecture; route framework-specific agent work to its owner.
- ▌ Pg Jev · akillness bundleOperate realZachi/pg-jev, the `jev` PostgreSQL extension for plain-language row predicates, probabilities, choices, and scores backed by TypeSafe Jev. Use when a user mentions pg-jev, pgjev, `CREATE EXTENSION jev`, `jev()`, `jev_prob`, `jev_choice`, `jev_score`, `jev_eval`, natural-language SQL filters, or asks to install, configure, query, cost-check, or troubleshoot this extension. Keep database mutation, provider calls, and secret handling explicitly approved.
- ▌ Utopia · akillness bundleOperate deeplethe/utopia, the Rust/Postgres bitemporal knowledge application with ontology-driven ingest, review, search/chat, derivation and per-base MCP. Use when users name Utopia/utopia.bi or ask to deploy, configure, inspect, back up or integrate this exact knowledge platform. This is a full application with a database, not a generic ontology library or a local-only graph engine; route standalone RDF/OWL analysis to Open Ontologies or Python pipelines to Semantica.
- ▌ Wizard 2 · akillness bundleGenerate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
- ▌ Agent S · akillness bundleOperate simular-ai/Agent-S, the Apache-2.0 open-source computer-use agent framework whose Agent S3 (`gui-agents` 0.3.2, `agent_s` CLI) screenshots the desktop, asks a multimodal model plus a grounding model what to do, and executes generated pyautogui code to click, type and scroll on macOS, Windows or Linux. Use when the user names Agent S, Agent-S, Simular, `gui-agents`, `agent_s`, UI-TARS grounding, or an OSWorld-style GUI agent and needs a fit check, install, model and grounding setup, an offline preflight, a supervised run, or troubleshooting. Do not use for ordinary browser automation, tasks with a CLI or API, unsupervised runs on a personal machine, or Agent S4's AWS benchmark evolution. Triggers on: Agent S, Agent-S, gui-agents, agent_s, computer use agent, 컴퓨터 사용 에이전트, 화면 보고 PC 조작하는 AI.
- ▌ Cursify · akillness bundleInspect ui-layouts/cursify cursor effects, assess reuse permission, and plan or review a scoped React cursor enhancement. Use when the user names Cursify, cursify.ui-layouts.com, a Cursify cursor follower, or its pointer/canvas lifecycle. Route generic visual recipes to web-design, React Bits components to react-bits, and measured animation leak audits to optimize-web-animations.
- ▌ Jevgrep · akillness bundleOperate Jevgrep (`jg`) as optional remote-agent discovery over explicitly scoped skills, wiki pages, or graph source documents. Use only when the user explicitly requests Jevgrep and separately approves transmitting source content and queries to the configured provider with potential cost. Preserve native catalog, exact/LSP/zvec retrieval and Graphify query/path/explain as defaults; Jevgrep does not query or rebuild durable graphs.
- ▌ Openrig · akillness bundleOperate mvschwarz/openrig, the Apache-2.0 OpenRig CLI, daemon, TUI and persistent multi-agent rig system for Claude Code, Codex and Pi. Use when a user names OpenRig, the `rig` CLI, @openrig/cli, rig specs, kernel/operator sessions, tmux/Herdr views, or the mvschwarz/openrig repository and needs a fit check, pinned install/setup, preflight, rig launch, status, capture, messaging, teardown, bundle/spec work, or troubleshooting. Do not use for generic agent-team design, generic environment setup, or ordinary log triage.
- ▌ Rowboat · akillness bundleOperate or explain rowboatlabs/rowboat, the open-source personal/team AI work app whose local knowledge graph is an Obsidian-style network of Markdown notes. Use for its setup, knowledge ingestion and graph construction, workspace behavior, configuration, or troubleshooting. Do not route generic graph-database or ontology design here.
- ▌ Artcraft · akillness bundleOperate storytold/artcraft, the dual-licensed Rust/Tauri ArtCraft creator IDE for 2D and 3D scene blocking, hosted AI image, video, audio, mesh, and world generation, release/source-build handoff, exports, and troubleshooting. Use when a user asks to fit-check ArtCraft, inspect its pinned source, install a desktop release, build the app, block a scene, generate media, account for providers or credits, or hand off downloaded assets. Keep remote generation, credentials, downloads, installers, ports, source builds, publishing, and destructive reset actions approval-gated. Route hosted multi-provider generative studio work to `open-generative-ai`, script-to-video storyboard work to `openstory`, Blender scene control to `blender-mcp`, and code-first video assembly to `video-production`.
- ▌ Ask Matt 2 · akillness bundleAsk which skill or flow fits your situation. A router over the skills in this repo. Use when the user asks which of these engineering skills or flows fits their situation. Triggers on: ask- matt, which skill should I use, what flow fits here.
- ▌ Autoclip · akillness bundleOperate artbyjazi/autoclip, the MIT-licensed local-first AI video clipper that turns long-form video into ranked, caption-burned, speaker-tracked 9:16 vertical clips. Run autoclip doctor to check ffmpeg-full (libass/libx264) and Python 3.11/3.12 dependencies, run autoclip clip <url|file> for end-to-end ingestion, Whisper transcription, LLM highlight detection (local Ollama or BYOK Anthropic/OpenAI/Gemini), MediaPipe face/speaker-tracked vertical reframing, animated caption styling (bold_pop, karaoke_fill, clean_lower, boxed), and multi-aspect export (9:16, 1:1, 16:9), or serve the local review web app (autoclip serve). Use when the user wants to convert long videos, podcasts, or webinars into vertical Shorts, Reels, or TikTok clips without uploading video to third-party servers. Triggers on: autoclip, auto clip, AI video clipper, podcast clipper, long to short video, vertical reframing, speaker tracking video, burn animated captions, youtube to shorts clipper.
- ▌ Rea · akillness bundleOperate morluto/rea (Reverse Engineer Anything), the local CLI and MCP server for evidence-backed inspection of native binaries, JavaScript/Electron apps, managed artifacts, Android packages, browser targets, firmware, archives, crashes, and saved captures. Use when the user names REA, rea-agents, reverse-engineer-anything, REA evidence/snapshots, provider selection, `rea doctor`, or REA setup. Route ordinary source-repository analysis and generic browser/debugging work to the narrower project skills instead.
- ▌ Uzu · akillness bundleOperate trymirai/uzu, Mirai's Rust-native local inference engine, on supported Apple Silicon or CPU-oriented source targets. Use when a user needs Uzu preflight, the `mirai` CLI, a pinned source checkout, local model acquisition, chat/server operation, benchmarking, or model-license and platform-fit guidance. Do not route llama.cpp, LM Studio, arbitrary GGUF conversion, CUDA/Linux-GPU claims, or unverified Windows production support here.
- ▌ Zurp · akillness bundleOperate facebookincubator/Zurp, the MIT-licensed Meta bug-bounty research toolkit combining a Burp Suite Java extension with three standalone stdio MCP servers: meta-context, fbdl, and sparta. Use when fitting or preflighting a checkout, building the Jar or MCP package, registering servers, configuring researcher-token/proxy/TLS settings, running controlled FBDL/Meta-context/SPARTA workflows, or troubleshooting 403, token, rate-limit, startup, or SSL failures. Triggers on Zurp, bug-bounty-research, FBDL MCP, Meta Context, SPARTA, zurp.jar, or BB_RESEARCH_TOKEN.
- ▌ Leann · akillness bundleOperate StarTrail-org/LEANN for local document indexing and semantic retrieval: inspect a checkout, configure embeddings/backends, build or incrementally update an index, search it, or troubleshoot index behavior. Use when the task explicitly names LEANN or needs its graph-assisted vector-index workflow. Route code-architecture memory graphs to mex/Graphify, workspace text search to zvec-grep, and other RAG stacks to langchain-rag.
- ▌ Ruflo · akillness bundleUse when operating the source-pinned ruvnet/ruflo repository or Ruflo CLI for fit checks, offline preflight, initialization previews, Claude Code or Codex swarm and hive-mind orchestration, MCP registration, memory inspection, cleanup, rollback, or troubleshooting. Keep the rename boundary explicit: the root package and compatibility CLI expose claude-flow names while current Ruflo docs and the wrapper use ruflo. Separate read-only discovery from commands writing project files, Claude settings, MCP registrations, hooks, helpers, runtime configuration, CLAUDE.md, or memory databases; require approval before installs, package or model downloads, paid or remote calls, servers or ports, credentials, publishing, or destructive cleanup. Route agent-company control-plane work to paperclip, local tmux lifecycle management to agent-manager, graph-based provider-CLI orchestration to zeroshot, specification-first clarification to ooo, and recursive agent-harness optimization to harness2.
- ▌ Anyjev · akillness bundleOperate nokia-applied-research/AnyJev, the Apache-2.0 Python library for training-free typed choice, yes/no, and score decisions from next-token probabilities. Use when pinning or inspecting a checkout, selecting raw/L0 Decider readouts, running approved Tacit checkpoints, configuring HF/vLLM/ SGLang/llama.cpp backends, checking tokenizer or calibration limits, or using the local gateway. Triggers on AnyJev, Tacit, L0, permutation debiasing, llama.cpp logprob, SGLang /generate, or comparisons with hosted TypeSafe AI/Jev. Do not use for TypeSafe hosted services or a generic Jev harness.
- ▌ Autoresearch 3 · akillness bundleOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
- ▌ Ralphmode 2 · akillness bundleConfigure Claude Code, Codex CLI, and Gemini CLI for Ralph-style automation with fewer approval prompts while keeping project boundaries, secret denylists, and sandbox-first safety rules intact. Use when the user needs trusted-folder setup, approval-policy tuning, sandbox-first YOLO boundaries, or checkpoint rules for long-running `ralph` or `omg` loops. Triggers on: ralphmode, trusted folder, bypass approvals safely, Codex sandbox mode, approval policy, checkpoint needed, repo-scoped automation.
- ▌ Tdd 2 · akillness bundleTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
- ▌ Triage 2 · akillness bundleMove issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. Use when issues or external PRs need categorising, verifying, and turning into agent-ready briefs. Triggers on: triage, triage the backlog, review these issues.
- ▌ Caveman 2 · akillnessEnables persistent ultra-compressed technical communication; use for explicit brevity or token-reduction requests, except where fragments risk safety or clarity.
- ▌ Grill Me 2 · akillnessA relentless interview to sharpen a plan or design. Use when the user wants a plan or design stress-tested. Triggers on: grill me, grill this, stress-test my plan.
- ▌ Zoom Out 2 · akillnessGet higher-level architectural perspective: maps modules, callers, dependencies using domain vocabulary
- ▌ Code Review 2 · akillness bundleReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in- progress changes, or asks to "review since X".
- ▌ Write A Skill 2 · akillnessCreates reusable SKILL.md-based agent skills through requirements, drafting, and user review; use to formalize a workflow or add a new agent capability.
- ▌ Grill With Docs 2 · akillnessA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. Use when the grilling session should also leave ADRs and glossary entries behind. Triggers on: grill with docs, grill and document, grill this and write the ADR.
- ▌ Scaffold Exercises 2 · akillnessCreate exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
- ▌ Migrate To Shoehorn 2 · akillnessMigrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
- ▌ Git Guardrails Claude Code 2 · akillness bundleSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
- ▌ Improve Codebase Architecture 2 · akillness bundleScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. Use when the user wants architecture improvement candidates surfaced before choosing one. Triggers on: improve the architecture, find deepening opportunities, where should we refactor.
- ▌ API Documentation 2 · akillness bundleCreate comprehensive API documentation for developers. Use when documenting REST APIs, GraphQL schemas, or SDK methods. Handles OpenAPI/Swagger, interactive docs, examples, and API reference guides.
- ▌ Web Accessibility 2 · akillness bundleImplement web accessibility (a11y) standards following WCAG 2.1 guidelines. Use when building accessible UIs, fixing accessibility issues, or ensuring compliance with disability standards. Handles ARIA attributes, keyboard navigation, screen readers, semantic HTML, and accessibility testing.
- ▌ Skill Autoresearch 2 · akillness bundleAutonomously optimize an existing AI skill by running it repeatedly against binary evals, mutating one instruction at a time, and keeping only changes that improve pass rate. Based on Karpathy-style autoresearch, but applied to SKILL.md iteration instead of ML training. Use when optimizing a skill, benchmarking prompt quality, building evals for a skill, or running self-improvement loops on reusable agent instructions. Triggers on: skill-autoresearch, optimize this skill, improve this skill, benchmark this skill, eval my skill, run autoresearch on this skill, self-improve skill.
- ▌ Testing Strategies 2 · akillness bundleDesign comprehensive testing strategies for software quality assurance. Use when planning test coverage, implementing test pyramids, or setting up testing infrastructure. Handles unit testing, integration testing, E2E testing, TDD, and testing best practices.
- ▌ Changelog Maintenance 2 · akillness bundleMaintain a clear and informative changelog for software releases. Use when documenting version changes, tracking features, or communicating updates to users. Handles semantic versioning, changelog formats, and release notes.
- ▌ Database Schema Design 2 · akillness bundleDesign and optimize database schemas for SQL and NoSQL databases. Use when creating new databases, designing tables, defining relationships, indexing strategies, or database migrations. Handles PostgreSQL, MySQL, MongoDB, normalization, and performance optimization.
- ▌ Security Best Practices 2 · akillness bundleImplement security best practices for web applications and infrastructure. Use when securing APIs, preventing common vulnerabilities, or implementing security policies. Handles HTTPS, CORS, XSS, SQL Injection, CSRF, rate limiting, and OWASP Top 10.
- ▌ Performance Optimization 2 · akillness bundleOptimize application performance for speed, efficiency, and scalability. Use when improving page load times, reducing bundle size, optimizing database queries, or fixing performance bottlenecks. Handles React optimization, lazy loading, caching, code splitting, and profiling.
- ▌ Remotion Video Production 2 · akillness bundleProduce programmable videos with Remotion using scene planning, asset orchestration, and validation gates for automated, brand-consistent video content.
- ▌ Bmad 2 · akillness bundleOrchestrates BMAD workflows for structured AI-driven development. Routes work across Analysis, Planning, Solutioning, and Implementation phases.
- ▌ Bmad Gds 2 · akillness bundleAI-driven Game Development Studio using BMAD methodology. Routes game projects through Pre-production, Design, Architecture, Production, and Game Testing phases with 6 specialized agents. Supports Unity, Unreal Engine, Godot, and custom engines.
- ▌ Bmad Idea 2 · akillness bundleCreative Intelligence Suite for AI-driven ideation, design thinking, innovation strategy, problem-solving, and storytelling. 5 named specialist agents with distinct methodologies — no setup required, all workflows available immediately.
- ▌ Agentation 2 · akillness bundleVisual UI annotation tool — humans click elements, agents receive CSS selectors and React component paths to fix exact code.
- ▌ API Design 2 · akillness bundleDesign RESTful and GraphQL APIs following best practices. Use when creating new APIs, refactoring existing endpoints, or documenting API specifications. Handles OpenAPI, REST, GraphQL, versioning.