GitHubSkilllane
github/gh-aw-threat-detection/.agents/skills/lane/SKILL.md
Use lane in this repository when the user asks to create or work in an isolated worktree.
Find the best CLAUDE.md, AGENTS.md and Claude skills
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.
Your trail
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.
Worked for most · soon
GitHubSkillGitHubReads credentialsCLAUDE.mdgh-aw-threat-detection
github/gh-aw-threat-detection/CLAUDE.md
gh-aw-threat-detection is the threat detection component for GitHub Agentic Workflows (gh-aw). It is a Go CLI (threat-detect) that analyzes artifacts produced by AI agents — prompts, agent output, git patches, comment memory — and decides whether to allow or block the downstream safe-outputs job. The component runs in two main contexts: It detects three categories: prompt injection, secret leak, and malicious patch, and emits a strict JSON contract. Run these from the repo root. They are the canonical entry points…
GitHubSkillconsole-rendering
github/gh-aw-threat-detection/skills/console-rendering/SKILL.md
Instructions for using the struct tag-based console rendering system in Go
GitHubSkillerror-messages
github/gh-aw-threat-detection/skills/error-messages/SKILL.md
Error Message Style Guide for Validation Errors
GitHubSkillget-gh-aw-release-binary
github/gh-aw-threat-detection/skills/get-gh-aw-release-binary/SKILL.md
How to fetch the latest github/gh-aw release binary — either as the gh CLI extension (gh aw ...) or as a raw platform binary downloaded from GitHub Releases — including how to resolve the latest tag, pick the right asset, and verify its checksum.
GitHubReads credentialsSkillupdate-workflow-versions
github/gh-aw-threat-detection/skills/update-workflow-versions/SKILL.md
How to manually regenerate the compiled agentic workflow .lock.yml files when the gh-aw Version Check workflow reports version drift. All workflows track the newest github/gh-aw release or prerelease.
GitHubCopilot instructionshooks
github/hooks/.github/copilot-instructions.md
You are an AI assistant that specializes in software development for the Ruby programming language. Regarding scripts that manage the environment or start the app, follow the guidance given by GitHub in their Scripts to Rule Them All blog post. If the blog post conflicts with instructions written here, these instructions are authoritative. For example: Bootstrap the Ruby project by running: Ensure all unit tests pass by running the following: This project requires X% test coverage of code, not including:
GitHubCopilot instructionsempty-repos
github/empty-repos/.github/copilot-instructions.md
The Empty Repos Workflow is a GitHub Actions workflow that scans organizations for empty repositories and README-only repositories, generating monthly reports as GitHub issues. Always reference these instructions first and fallback to search or bash commands only when you encounter unexpected information that does not match the info here.
GitHubAGENTS.mdplugin-marketplace-starter
github/plugin-marketplace-starter/AGENTS.md
This repository is a GitHub Copilot plugin marketplace, maintained by editing its files directly. README.md shows the steps. - Keep documentation README-first. Every page under docs/ must have a direct, descriptive README link and only expand a topic already introduced there. - Each local plugin lives in plugins/<name>/ with plugin.json, README.md, and CHANGELOG.md. It's listed in marketplace.json with the same name, version, and description. Keep each plugin self-contained and installable on its own. Don't add repository settings that install or…
GitHubSkillreview-notes
github/plugin-marketplace-starter/evals/marketplace-maintainer/agents/plugin-reviewer/fixtures/common/plugins/review-notes/skills/review-notes/SKILL.md
Summarize notes supplied by the user when they ask for a short note summary. Not for file editing or remote content.
GitHubAGENTS.mdplugin-marketplace-starter / sample-marketplace
github/plugin-marketplace-starter/evals/_shared/fixtures/sample-marketplace/AGENTS.md
This is a synthetic GitHub Copilot plugin marketplace for evals. - Each local plugin lives in plugins/<name>/ with plugin.json, README.md, and CHANGELOG.md, and it's listed in marketplace.json. - Changes since a known released base need a semver bump in plugin.json and marketplace.json, and a matching changelog heading. An explicitly unreleased first version keeps its current version and heading. Never lower versions, bump twice, or rewrite history. Ask if the released base or first-release status is unknown; a PR base isn't…
GitHubSkillsample-notes
github/plugin-marketplace-starter/evals/_shared/fixtures/sample-marketplace/plugins/sample-notes/skills/sample-notes/SKILL.md
Summarize synthetic release notes when asked for a summary.
GitHubSkillrelease-plugins
github/plugin-marketplace-starter/plugins/marketplace-maintainer/skills/release-plugins/SKILL.md
Prepare a marketplace release, fix catalog inconsistencies, or retire a stale plugin. Use whenever asked to get a catalog ready to release, check changed plugin versions and changelogs, draft marketplace release notes including confirmed first releases with no file changes, or retire or remove a plugin from the marketplace. Don't use for a single contribution's PR draft, remote pin updates alone, or publishing without approval.
GitHubSkillupdate-remote-pins
github/plugin-marketplace-starter/plugins/marketplace-maintainer/skills/update-remote-pins/SKILL.md
Add an outside plugin to this marketplace or deliberately update its pinned upstream release. Use whenever asked to pin, re-pin, or update an outside plugin's release, ref, or commit SHA in the catalog, including from a supplied offline snapshot. Don't use to edit a local plugin, install upstream code, or update npm dependencies.
GitHubSkilladd-plugin
github/plugin-marketplace-starter/plugins/plugin-authoring/skills/add-plugin/SKILL.md
Add a new plugin to this marketplace: its folder, plugin.json, README, CHANGELOG, catalog entry, and root README listing. Use whenever asked to add, create, scaffold, or register a new plugin in a marketplace checkout. Don't use for writing a plugin's skills or agents, editing an existing plugin, or Copilot pricing questions.
GitHubSkillsubmit-plugin
github/plugin-marketplace-starter/plugins/plugin-authoring/skills/submit-plugin/SKILL.md
Prepare a marketplace plugin contribution or update for a pull request. Use whenever asked to get a plugin ready for a pull request, bump its version or changelog, flag compatibility changes, and write the pull request description. Don't use for a catalog-wide release, generic PRs, or publishing without approval.
GitHubSkilltry-plugin-locally
github/plugin-marketplace-starter/plugins/plugin-authoring/skills/try-plugin-locally/SKILL.md
Try a new or edited marketplace plugin from your current local checkout in a fresh host session before opening a pull request. Use for local development, Copilot CLI or VS Code discovery checks, and optional explicit installation checks. Don't use to publish a plugin or test a remote catalog pin.
GitHubSkillpr-description
github/plugin-marketplace-starter/plugins/pr-description/skills/pr-description/SKILL.md
Draft a structured pull request description in chat from supplied change notes, commit summaries, or a diff. Use when asked to write or format a general PR description or summary. Don't use for marketplace plugin submission or version/changelog bumps (use submit-plugin), scaffolding plugins, reviewing code for defects, or unrelated questions.
GitHubReads credentialsCLAUDE.mdgh-aw-harness
github/gh-aw-harness/CLAUDE.md
gh-aw-threat-detection is the threat detection component for GitHub Agentic Workflows (gh-aw). It is a Go CLI (threat-detect) that analyzes artifacts produced by AI agents — prompts, agent output, git patches, comment memory — and decides whether to allow or block the downstream safe-outputs job. The component runs in two main contexts: It detects three categories: prompt injection, secret leak, and malicious patch, and emits a strict JSON contract. Run these from the repo root. They are the canonical entry points…
GitHubAGENTS.mdevals-action
github/evals-action/AGENTS.md
- Keep this a thin GitHub adapter over the acquired Vally CLI. Translate supported commands and consume native JSONL; never duplicate selection, configuration parsing, grading or execution. - Use Node 24, the pinned pnpm version, and one lockfile. Install with scripts disabled. Run focused tests during development and pnpm check before review. - Rebuild and commit dist after source changes. Never manually edit bundles. - Do not run models, add credentials, publish, merge or change repository visibility without separate authorization.…
Agent instruction files
What are agent instruction files?
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 or AGENTS.md?
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.
What is a skill?
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.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.