Ingest a file into the local LLM wiki and update source/entity/concept pages.
Idioma del texto original: inglés
Menú
Skills en este repositorio
SkillsMP ha recopilado 447 skills de jleechanorg/claude-commands. Abre una skill para revisar su origen y sus detalles.
jleechanorg/claude-commandsMostrando 40 de 447 skills recopiladas.
Ingest a file into the local LLM wiki and update source/entity/concept pages.
Idioma del texto original: inglés
Use BEFORE writing wiki/sources, wiki/entities, or wiki/concepts. Routes through /wiki-ingest; bulk generation must also create entity+concept pages.
Idioma del texto original: inglés
Use when proving, rejecting, or deleting backend adjustment registry entries with real LLM evidence and independent disabled-adjustment worktrees.
Idioma del texto original: inglés
Use when spawning, steering, or auditing Agent Orchestrator workers, especially when the user specifies exact AO parameters such as codex, runtime, project, claim-pr, or PR targets.
Idioma del texto original: inglés
Checklist for dispatching AO workers — python venv, commit discipline, branch drift, and post-push CodeRabbit verification
Idioma del texto original: inglés
Run the Dark Factory DOT pipeline runner against a goal. Slash command: /factory. Implements StrongDM's Attractor pattern as an external Python runner — .dot files are the versioned artifact, sealed holdouts live in a separate repo, every step is recorded to…
Idioma del texto original: inglés
Display the Dark Factory pipeline node graphs — spec-review pipelines, factory gates, node types, edge conditions, and handler mappings. Use /factory-spec or /fs to quickly reference the spec graph structure without running a pipeline.
Idioma del texto original: inglés
Run breadth-first research on a topic and optionally ingest results into the local LLM wiki.
Idioma del texto original: inglés
Search the local LLM wiki for matching pages, titles, and content snippets.
Idioma del texto original: inglés
Override the model an `ao spawn` worker uses (e.g. force claude-sonnet-4-6 instead of the project default of wafer.ai/GLM-5.1) WITHOUT mutating ~/.hermes/agent-orchestrator.yaml. Use when the user asks for "claude sonnet with AO", "spawn AO with X model", "AO…
Idioma del texto original: inglés
Create macOS launchd cleanup agents with dry-run verification. Writes cleanup script + plist installer, verifies with --dry-run, then installs and runs live.
Idioma del texto original: inglés
Reference WorldArchitect agent routing priority and modal lock patterns.
Idioma del texto original: inglés
Triage AO lifecycle backfill claim failures and ghost worktree fetch errors.
Idioma del texto original: inglés
Run the autor research and SWE-bench benchmark loop.
Idioma del texto original: inglés
Drive the autor phase-three n=15 per technique loop.
Idioma del texto original: inglés
Monitor OpenClaw task threads in Slack and nudge on stalls or fabrication.
Idioma del texto original: inglés
Enforce CharacterCreationAgent modal exit choices and state transition rules.
Idioma del texto original: inglés
Check worldai-workstreams team agents and summarize status, commits, and beads.
Idioma del texto original: inglés
Copy production Firebase campaigns across users for testing with Admin SDK.
Idioma del texto original: inglés
Define goal criteria without executing — just parse and save
Idioma del texto original: inglés
Define a goal with success criteria and run autonomous convergence loop until criteria are met
Idioma del texto original: inglés
Enforce the Karpathy LLM wiki pattern for ingesting, querying, and organizing sources.
Idioma del texto original: inglés
DEPRECATED — Redirects to the consolidated ZFC leveling skill
Idioma del texto original: inglés
Diagnose and fix MiniMax 401 auth errors in AO workers — the root cause is always a redacted or invalid MINIMAX_API_KEY, not the model name. Use when workers stall at /login, show API Error 401, or when ao-XXXX shows "minimax" in its tmux pane but isn't…
Idioma del texto original: inglés
Design modal agents that cannot be exited until explicit completion choices are selected.
Idioma del texto original: inglés
Diagnose local OpenClaw gateway model routing, runtime status, and WorldArchitect integration.
Idioma del texto original: inglés
Define evidence requirements for end-to-end streaming chunk delivery and timing.
Idioma del texto original: inglés
Record captioned terminal evidence videos and publish them as GitHub PR attachments with portable, sanitized outputs
Idioma del texto original: inglés
Run and test the WorldAI Tools MCP HTTP proxy with real local harnesses.
Idioma del texto original: inglés
Measure zero-touch and one-touch rates from merged PRs — run in evolve loop cycles
Idioma del texto original: inglés
Use Claude Code to control Google Antigravity IDE on macOS via Peekaboo. Explicitly supports targeting either the Agent Manager window or the Editor window (worktree/editor titles), plus auto routing. Covers workspaces, conversations,…
Idioma del texto original: inglés
Properly inspect AO worker tmux sessions to detect working vs idle state
Idioma del texto original: inglés
Safe gateway upgrade/downgrade with pre-flight checks, rollback, and post-verification
Idioma del texto original: inglés
Detailed procedures for hook re-fire short-circuit — sentinel files, CR incremental-mode detection, Branch A caps, stale review dismissal commands
Idioma del texto original: inglés
Document both INPUT and OUTPUT JSON schemas for LLM-driven features to prevent data flow confusion
Idioma del texto original: inglés
API skill for mvp-site-app-dev-i6xf2p72ka-uc.a.run.app. Use when: interacting with this site's APIs, automating workflows, debugging requests. Auth: Unknown — capture may reveal auth mechanism.
Idioma del texto original: inglés
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Idioma del texto original: inglés
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Idioma del texto original: inglés
Use thinclaw MCP server — thin inference-less bridge to OpenClaw Gateway for executing tools
Idioma del texto original: inglés
Pre-report gate — verifies all planned evidence artifacts exist before writing comparison/validation reports
Idioma del texto original: inglés