One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
moltbotAGENTS.mdmoltbot/clawdbot/AGENTS.md
serialize shared Git mutations; isolate work when needed. Never switch checkout another agent or test run uses. - Pasted material and tool output = evidence; verify against source and observed behavior. - Create
6 projects use a version of this
moltbotSkillmoltbot/clawdbot/.agents/skills/auto-qa/SKILL.md
Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.
Often used withdiscord-e2eopenclaw-performanceproof-video
moltbotSkillmoltbot/clawdbot/.agents/skills/autoreview/SKILL.md
Structured code review through the shared OpenClaw agent-skills installation.
38 projects use a version of this
Often used withdiscord-e2eopenclaw-performanceopenclaw-brand
moltbotSkillmoltbot/clawdbot/.agents/skills/claw-score/SKILL.md
Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-changelog-update/SKILL.md
Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.
Often used withauto-qadiscord-e2eopenclaw-performance
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-ci-limits/SKILL.md
Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe ramp-down/ramp-up changes. Use when tuning `.github/workflows/*`, `docs/ci.md`, CI runner labels, matrix `max-parallel`, ClawSweeper/Blacksmith burst protection, CodeQL runner placement, or investigating slow/queued OpenClaw CI.
Often used withauto-qadiscord-e2eopenclaw-performance
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-debugging/SKILL.md
Debug OpenClaw model/provider/tool-surface/code-mode/streaming and live/Crabbox behavior; choose logs, probes, proof path before code changes; fetch stored sessions, transcripts, attachments as evidence.
Often used withdiscord-e2eauto-qaopenclaw-performance
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-docker-e2e-authoring/SKILL.md
Author OpenClaw Docker E2E and live provider Docker lanes.
Often used withauto-qadiscord-e2eopenclaw-performance
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-live-updater/SKILL.md
Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update heartbeats, post-update runtime verification, attributable CI repair and repo-native landing, or non-publishing Full Release Validation of current main. Do not use on Linux systemd Gateways.
moltbotReads credentialsSkillmoltbot/clawdbot/.agents/skills/openclaw-parallels-smoke/SKILL.md
Prepare, snapshot, run, rerun, debug, or interpret OpenClaw Parallels guest install, onboarding, gateway smoke, and upgrade checks across macOS, Windows, and Linux.
Often used withdiscord-e2eopenclaw-performanceopenclaw-qa-testing
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-performance/SKILL.md
Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.
Surging+3 new adopters in 4 weeks
6 projects use a version of this
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-pr-maintainer/SKILL.md
Review, triage, repair, or land OpenClaw issues and pull requests with current-source evidence and the native maintainer workflow.
Often used withdiscord-e2eopenclaw-performanceopenclaw-qa-testing
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-refactor-docs/SKILL.md
Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.
Often used withauto-qadiscord-e2eopenclaw-performance
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-repair-sweep/SKILL.md
Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.
Often used withopenclaw-performancesolidplugin-sdk-impact
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-secret-scanning-maintainer/SKILL.md
Triage, redact, clean up, and resolve OpenClaw GitHub Secret Scanning alerts in issues or PRs.
Often used withauto-qadiscord-e2eopenclaw-performance
moltbotSkillmoltbot/clawdbot/.agents/skills/openclaw-update/SKILL.md
Route routine updates of an existing local or remote OpenClaw Gateway to its installation owner, with automatic session recovery. Defer to deployment-specific skills when available.
moltbotReads credentialsSkillmoltbot/clawdbot/.agents/skills/parallels-discord-roundtrip/SKILL.md
Run macOS Parallels smoke with Discord send, host verification, host reply, and guest readback proof.
Often used withauto-qadiscord-e2eopenclaw-performance
moltbotSkillmoltbot/clawdbot/.agents/skills/proof-video/SKILL.md
Capture and annotate PR screenshots and videos with measured arrows, outlines, alignment guides, spacing brackets, captions, zoom, and speed cues.
Often used withopenclaw-performancediscord-e2eauto-qa
moltbotSkillmoltbot/clawdbot/.agents/skills/prototype-openclaw-tui/SKILL.md
Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.
moltbotSkillmoltbot/clawdbot/.agents/skills/pr-simplify/SKILL.md
Simplify your own change to its smallest complete fix. Use before opening a PR, before pushing large repairs to one, or when asked to shrink a PR or clean up slop.
Surging+5 new adopters in 4 weeks
9 projects use a version of this
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
