AI & ML

orcaqubits Skill

Pre-authorize agent purchases within user-defined constraints for human-not-present flows — the AP2 Intent Mandate concept, now expressed as an open Checkout Mandate carrying allowed-merchant and line-item constraints. Use when building autonomous agent shopping with user-signed intent, expiry, and constraint enforcement.

arjunprabhulal Skill

Frames the mental model for making a running system explain itself — metrics, logs, and traces as complementary signals, RED and USE checklists, SLOs and error budgets, cardinality as the tax paid for detail. Use this whenever the user asks why something broke with no warning, is deciding what to instrument before a service ships, is choosing between a metric, log, or trace, or asks what observability means beyond "we have dashboards." For metric mechanics use `metrics-and-monitoring`, for logs use `log-management`, for tracing use `distributed-tracing`.

arjunprabhulal Bundle

Covers instrumenting and collecting numeric time-series data — the Prometheus data model, choosing between counters, gauges, and histograms, controlling cardinality before it controls your bill, applying RED and USE systematically, and writing recording rules. Use this whenever the user is adding metrics to code, choosing a metric type, debugging a cardinality explosion or a slow metrics query, or deciding between pull and push collection. For turning metrics into paging rules use `alerting`, for visualizing them use `dashboards`, and for the broader signal strategy use `observability`.

hybridaione Skill

Use the configured Zoho MCP server for Zoho CRM, Desk, Mail, Calendar, Books, Projects, WorkDrive, Cliq, Campaigns, and related Zoho business workflows. Use when the user asks to search, summarize, create, update, schedule, send, invoice, escalate, or report on Zoho data through MCP.

hybridaione Bundle

Use Langfuse for LLM observability and evaluation and look up Langfuse documentation. In HybridClaw, data access (traces, observations, sessions, scores, prompts, datasets, metrics) goes through the gateway-proxied langfuse.cjs helper with SecretRef auth — reads are green, writes are grant-gated. Documentation retrieval uses langfuse.com llms.txt, markdown pages, and search-docs. Covers instrumentation, prompt migration, error analysis, and LLM-as-a-judge calibration.

hybridaione Bundle

Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging.

hybridaione Bundle

Use Sokosumi with API-key auth, direct agent hires, coworker tasks, job monitoring, and result retrieval from non-interactive agent environments. Trigger on explicit Sokosumi mentions and Sokosumi-specific API, agent, coworker, task, or job terms. In agentic environments, do not launch the Ink TUI; use the API-first workflow instead.

hybridaione Skill

Maintain a Luhmann-style Zettelkasten. Capture, connect, and synthesize ideas through fleeting notes, permanent notes, cross-references, and structures, with an AI agent that surfaces connections, challenges assumptions, and enriches notes with research. Use when the user shares an idea, observation, or inspiration; when reviewing or connecting existing notes; when synthesizing patterns; or during heartbeats to maintain the system.

hybridaione Bundle

Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live mirroring. Use when the operator wants to clone a colleague, build a coworker from someone's writing, onboard a digital twin, or asks to 'distill', 'clone', or 'mirror' a person. Consent-gated for real humans.

omer-metin Bundle

Agent Tool Builder

omer-metin Bundle

Agent Memory Systems

davidondrej Bundle

Control the cmux macOS terminal app: workspaces, panes, surfaces, browsers, notifications, settings, and hooks. Use only when the user explicitly names cmux. Read before running any cmux command.

davidondrej Skill

Operate and coordinate AI agents running inside Herdr in Ghostty. Use when the user says "Use the Herdr skill," mentions Herdr, or asks to inspect, message, wait for, or coordinate agents in a Herdr workspace. Herdr-specific; do not use for cmux or ordinary terminal sessions.

davidondrej Bundle

Use this when controlling bb. The bb CLI lets you inspect, create, and orchestrate bb threads, automations, projects, providers, and environments.

davidondrej Bundle

Launch a new bb worker thread with the right project, model, worktree, and task brief. Use for nagent, launching a bb session, or a standalone bb agent. Covers thread creation; use bb-cli for managing existing threads.

davidondrej Skill

Draft /goal prompts and explain persistent agent loops. Use for goal or Ralph loops, autonomous run setup, monitoring, and troubleshooting.

davidondrej Bundle

Launch a GPT 5.6 Sol Max code reviewer and return its findings verbatim. Use only when the user explicitly invokes /gpt-review.

davidondrej Skill

Write a new ADR whose body is the user's exact words, nothing added. Use when the user says "adr-verbatim", "document that as an ADR", "new ADR", "record this decision", or gives wording for an ADR. Differentiator: agent adds only title, number and status line; it never drafts, rewrites, or expands the body.

davidondrej Bundle

Write a prompt teammates can give their AI agents to apply a fix, upgrade, or setup change. Use only when the user explicitly invokes /prompt-for-others.

davidondrej Bundle

Launch a Fable 5 Max 1M code reviewer and return its findings verbatim. Use only when the user explicitly invokes /fable-review.

davidondrej Bundle

Use Git worktrees to isolate parallel coding tasks. Use when setting up a task checkout, working in a shared repo, or managing existing worktrees.

davidondrej Bundle

Design a Grok Bot role and create its setup prompt. Use only when the user explicitly invokes /new-grok-bot.

davidondrej Skill

Archive the current bb thread and release its runtime. Use when the user explicitly asks to "self-archive", "archive yourself", or "archive this thread".

davidondrej Bundle

Run Fable and GPT reviews, then combine their findings for the user's approval. Use only when the user explicitly invokes /total-review.

davidondrej Skill

Clarify a feature, change, or refactor through questions, then write a build prompt for another agent. Use for /ask-then-build or requests to ask questions before producing an implementation prompt.

davidondrej Bundle

Reset a stuck Cursor ACP thread in bb and reload its configuration. Use only when the user explicitly invokes /reset-cursor-acp.

davidondrej Bundle

Make minimal prompt edits to reduce false-positive refusals from Fable. Use only when the user explicitly invokes /fable-safe-prompt.

davidondrej Skill

Configure the shared guard against catastrophic shell commands in local AI agents. Use when changing block patterns, adding an agent or machine, or investigating why a command was or wasn't blocked.

davidondrej Skill

Write, review, and debug agent skills. Use when creating or editing SKILL.md files, improving skill structure, or diagnosing invocation and execution problems.

davidondrej Skill

Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when the user asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.

nowledge-co Skill

Check whether Nowledge Mem is reachable from Proma, including MCP status, CLI fallback, API URL, and configuration issues after install or update.

nowledge-co Skill

Import the real current Cursor Agent transcript when the user explicitly asks or automatic stop-hook capture is unavailable.

nowledge-co Skill

Check Nowledge Mem setup, detect your agent, and guide native connector setup. Use when the user asks about setup, configuration, or when memory tools aren't working as expected.

nowledge-co Skill

Check Nowledge Mem setup, detect your agent, and guide native connector setup. Use when the user asks about setup, configuration, or when memory tools aren't working as expected.

nowledge-co Skill

Read your daily Working Memory briefing to understand current context. Contains active focus areas, priorities, unresolved flags, and recent knowledge changes. In Grok Build, invoke this on the first relevant turn because passive startup-hook output is not model context.

vtex Bundle

Apply when designing or implementing the runtime structure of a VTEX IO backend app under node/. Covers the Service entrypoint, typed context and state, service.json runtime configuration, and how routes, events, and GraphQL handlers are registered and executed. Use for structuring backend apps, defining runtime boundaries, or fixing execution-model issues in VTEX IO services.