Menu
Skills in this repository
SkillsMP has collected 447 skills from jleechanorg/claude-commands. Open a skill to review its source and details.
jleechanorg/claude-commandsShowing 40 of 447 collected skills.
Generalized autonomous loop — observe environment, measure health, diagnose friction, fix harness gaps, drive tasks to completion. Repo-agnostic. Use /eloop in any repo. For AO agent-orchestrator-specific patterns, also check the repo-local eloop skill.
Dark Factory spec workflow (/factory-spec, /fs): create a reviewed spec via the spec_gen pipeline, review an existing spec, or display the pipeline node graphs — spec-review pipelines, factory gates, node types, edge conditions, handler mappings. Create mode…
Read and search Gmail for $USER@gmail.com using gog CLI — authoritative method for all Gmail access
Run Claude Code CLI through the MiniMax Anthropic-compatible API endpoint.
Run PR automation jobs with the MiniMax API provider.
Pairv2 implementation philosophy: LLM-decided outcomes, fail-soft file handling, and evidence-first promotion
Reference the distinct PR automation cron workflows and their scopes.
Canonical 7-green PR merge criteria, PR status check pattern, PR freeze discipline, and admin merge protocol
Find and validate rotating GCP Cloud Run preview servers for PR branches.
Reproduce CI smoke test failures locally, especially MCP smoke and streaming contract failures.
Verify gitignored OpenClaw secret files are present and fresh in Dropbox backup.
Use when asked to analyze a video file and add visual description captions or text overlays burned into the output video
Review video evidence by extracting frames with ffmpeg and inspecting key UI states.
Canonical definition of zero-touch-by-operator for PR autonomy measurement. Use when evaluating, reporting, or labeling PR autonomy status.
Use when adding automation scripts. Requires a caller (CI/cron/hook); watchdog scripts need launchd plist template + deploy.sh install step.
Use BEFORE running any automation loop. Requires stating the observable success output (PR, fixed test, push); rejects prediction-only loops.
Standardize br bead follow-ups for PR reviews and code reviews so each bead includes exact implementation instructions, API/function signatures, and acceptance criteria.
Use when creating a new branch or entering a worktree. Sets upstream immediately via `git branch --set-upstream-to=origin/<branch>` after first checkout.
Use when debugging unauthorized/fallback errors. Flags redacted placeholders (e.g. __OPENCLAW_REDACTED__) as invalid tokens; checks env overrides first.
Metric-driven PR code quality review (Short variant for small PRs, Long variant for important/architectural/AI-generated PRs). Cyclomatic / cognitive complexity, duplication, coupling/cohesion, package metrics, code smells, lightweight security patterns,…
Example/seed/fixture files must use placeholders not real credentials. Pre-commit grep check + enforcement hooks.
Use BEFORE `mv`/`rm -rf` on any directory. Verifies pwd does not match target; session cwd cannot recover once its directory is gone.
Use for PRs scoped to deletion. Net production LOC must be ≤0; PR lifecycle time-boxed at 30 min; document, do not substitute, the deletion.
Use when fixing broken automation (CI, gates, hooks). A commit is NOT a fix; verify the fix is active post-deploy; restart gateway after config.yaml changes.
Use when editing GitHub Actions in private repos. Requires self-hosted runners; flags ubuntu-latest as policy drift unless explicitly approved.
Use when /harness is invoked or fixing a harness rule violation. Matches fix durability to severity (nit=memory, wrong=CLAUDE.md, silent-sub=hook+commitment).
Use after every /integrate invocation. Mandates /learn before reporting done; integrate without learn is incomplete execution.
Use when installing/modifying any ~/Library/LaunchAgents plist. Requires template in repo that owns the job; @HOME@ placeholders; install-launchagents.sh cleanup.
Use when adding/troubleshooting MCP servers. Installs to stable paths (npm -g, uvx, uv tool); updates ~/.config/mcp-daemon/start-mcp-daemons.sh for HTTP MCPs.
Search, write, and inspect the shared Hermes mem0 qdrant memory store.
Use when adding/changing a metric (zero-touch, smoothness, etc.). Wires canonical doc, README, AGENTS.md, CLAUDE.md, monitor script in the same pass.
Use when persisting rewards_box or any data structure to Firestore. ALL paths (streaming/polling/passthrough) must canonicalize before writing.
Use BEFORE any cost/latency optimization. A/B control MUST be deployed prod config; gate code-start on stated $X/mo savings; reject forced-OFF controls.
Use when writing PR descriptions. Enforces 6 sections in order: Background, Goals, Tenets, High-level description, Testing, Low-level details.
Use after every `git push` on a PR — enumerates ALL current gate failures, fixes ALL in one local pass, and pushes once. The fix-all-before-push invariant. Pairs with the CLAUDE.md PR driver loop contract and babysit DRIVER mode.
Use BEFORE creating a new PR. Checks existing open PRs in same scope; stops at ≥3; rebase/cherry-pick from closed PRs instead of duplicating.
Reproduce a bug, then drive a root-cause-classified fix. Use when asked to /repro a bug, file a REPRO issue, or escalate a regression. Triggers on the words: repro, reproduce, regression, root cause, "what broke", "file an issue".
Use at the start of bug-fix/feature sessions. State primary deliverable (file + behavior) before code; time-box CI gate work to 30 min.
Use BEFORE infra specs (CI/runner routing/deploy config). Confirm key behavioral decisions explicitly; flag infeasible numeric targets as STOP.
Use BEFORE claiming a UI bug fix is complete. Enforces RED-before-GREEN: reproduce the bug, verify the broken element, disclose environment gaps.