Find the best CLAUDE.md, AGENTS.md and Claude skills

GitHubSkill

hello-world

github/copilot-cli-for-beginners/.github/skills/hello-world/SKILL.md

A minimal skill example - use when learning the skill format

GitHubSkill

pytest-gen

github/copilot-cli-for-beginners/.github/skills/pytest-gen/SKILL.md

Generate comprehensive pytest tests - use when generating tests, creating test suites, or testing Python code

No other project uses it yet

GitHubAGENTS.md

gh-stack

github/gh-stack/AGENTS.md

A GitHub CLI (gh) extension for managing stacked branches and pull requests. Written in Go, it automates creating branches, keeping them rebased, setting PR base branches, and navigating between stack layers. Repository operations require Git 2.36 or later. Always run go vet before tests. See CONTRIBUTING.md for the alternative canonical go test command, targeted tests, and timing artifacts. CI runs the full platform-applicable suite with race detection on Linux, macOS, and Windows, with a cross-shard completion gate. There is no…

No other project uses it yet

GitHubCopilot instructions

gh-stack

github/gh-stack/.github/copilot-instructions.md

A Go CLI extension (gh stack) for managing stacked branches and pull requests. Uses Cobra for commands, bubbletea/lipgloss for TUI, and stretchr/testify for tests. Repository operations require Git 2.36+. Run vet before tests. See CONTRIBUTING.md for canonical/targeted commands and runner details. Do not add t.Parallel to tests that change Git mocks, cwd, or environment variables. No Makefile, no code generation, no external linter config. Standard Go toolchain only.

No other project uses it yet

GitHubSkill

gh-stack

github/gh-stack/skills/gh-stack/SKILL.md

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.

GitHubCopilot instructions

codeql-action

github/codeql-action/.github/copilot-instructions.md

The CodeQL Action is used in GitHub Actions workflows to run CodeQL scans using the CodeQL CLI. The main codebase of the CodeQL Action is written in TypeScript and compiled to JavaScript. Both the TypeScript sources and the generated JavaScript code are contained in this repository. The TypeScript sources are contained in the src directory and the JavaScript code is contained in the lib directory. A GitHub Actions workflow checks that the JavaScript code in lib is up-to-date. Therefore, you…

No other project uses it yet

GitHubCopilot instructions

gh-skyline

github/gh-skyline/.github/copilot-instructions.md

No summary in the file. Open it to read it.

GitHubAGENTS.md

branch-deploy

github/branch-deploy/AGENTS.md

This file applies to the entire repository. It is the repository-specific instruction source for coding agents and automated contributors. Keep this file durable, small, and focused on rules that should apply every time work happens in this repository. Do not add one-off task plans, temporary investigation notes, local machine details, or long procedure transcripts here. Move detailed operating procedures to docs/, reusable workflows to skills, and directory-specific rules to a closer nested AGENTS.md if that scope ever appears. Codex loads…

GitHubCopilot instructions

gh-gei

github/gh-gei/.github/copilot-instructions.md

This is a C# based repository that produces several CLIs that are used by customers to interact with the GitHub migration APIs. Please follow these guidelines when contributing:

GitHubCopilot instructions

local-action

github/local-action/.github/copilot-instructions.md

Install dependencies by running: Ensure all unit tests pass by running: Unit tests should exist in the __tests__ directory. They are powered by jest. Fixtures should be placed in the __fixtures__ directory. - Follow standard TypeScript and JavaScript coding conventions and best practices - Changes should maintain consistency with existing patterns and style - Document changes clearly and thoroughly, including updates to existing comments when appropriate - Do not include basic, unnecessary comments that simply restate what the code is…

GitHubSkill

build-performance-analysis

github/copilot-plugins/plugins/build-perf-cpp/skills/build-performance-analysis/SKILL.md

Analyze C++ build performance using vcperf.exe and ETL traces. Use this skill when the user wants to profile a build, understand compile bottlenecks, identify expensive headers or templates, generate JSON analysis reports, or interpret vcperf output. Covers tracing workflows, the /jsonAnalysis flag, reading the resulting JSON schema, and actionable remediation strategies for each bottleneck category.

GitHubSkill

spark-app-template

github/copilot-plugins/plugins/spark/skills/spark-app-template/SKILL.md

Comprehensive guidance for building web apps with opinionated defaults for tech stack, design system, and code standards. Use when user wants to create a new web application, dashboard, or interactive interface. Provides tech choices, styling guidance, project structure, and design philosophy to get users up and running quickly with a fully functional, beautiful web app.

GitHubAGENTS.md

gh-actions-lock

github/gh-actions-lock/AGENTS.md

Write Go that follows the Google Go Style Guide and lines up with cli/cli conventions. Keep it readable and simple. Doc comments earn their keep by saying something the code doesn't. Skip: When in doubt, fewer words. If a comment reads like marketing or a victory lap, delete it. There are two test layers with different guarantees. Put a test in the cheapest layer that can actually prove the thing, and don't restate the same claim in both. - Go…

GitHubReads credentialsSkill

gh-actions-lock

github/gh-actions-lock/skills/gh-actions-lock/SKILL.md

Locks and verifies GitHub Actions workflow dependencies with gh-actions-lock. Use when onboarding a repository to .github/workflows/actions.lock, fixing or relocking the lockfile, verifying it in CI, reading its findings, or whenever a user mentions actions.lock, gh actions-lock, or pinning workflow dependencies.

GitHubSkill

automate-it

github/lever/skills/automate-it/SKILL.md

Turns a task you keep doing by hand into a paused GitHub Copilot Automation with an event trigger, a least-privilege tool list, a PARAMETERS + CONTRACT prompt, a quiet exit and a propose-only improver sibling. It creates automations, so it runs only on `/lever automate` or an explicit ask ("automate this", "run this on every PR/issue", "do this nightly", "make this run in the cloud"). When the same task has been done 3 or more times by hand, or a local self-wake has fired 5 or more times for the same job, suggest it in one line instead of running it.

GitHubSkill

autonomous-delivery

github/lever/skills/autonomous-delivery/SKILL.md

Runs long-lived delivery as a coordinator with parallel lanes. Sets authority and pacing dials up front, keeps lanes alive and fed, lands work through a single-writer release train, and reports status only when something changed. Runs only on `/lever deliver`, "/autonomous-delivery" or an explicit request to run multi-hour, overnight or multi-lane delivery ("run this overnight", "keep N streams going", "don't stop until it ships"), or to re-arm an existing run after a restart.

GitHubSkill

autonomy-dial

github/lever/skills/autonomy-dial/SKILL.md

Resolves how far an agent may take a change, from L0 propose to L5 release. It reads the repo's real GitHub rules (rulesets, branch protection, CODEOWNERS, merge queue) and `.github/lever.yml`, applies per-path and per-class limits, records every grant verbatim with its source and expiry, and exposes a `may_merge` check that delivery skills call before landing anything. Use when a delivery skill or automation starts, when creating an automation, before any merge or enqueue, or when the user says "merge", "ship it", "land it", "then merge", "hand off", "do not merge", "freeze" or "you can merge X".

GitHubSkill

brief

github/lever/skills/brief/SKILL.md

Turns a short intent, often around 20 words, into a brief that can run unattended. The brief has the user's words verbatim, an outcome owner, an observable done-when, a feedback loop, constraints and neighbors, a budget, an autonomy level, an absence window, stop conditions and a report contract. Runs only on `/lever brief`, when another lever skill delegates, or on an explicit request to write a brief or hand work off ("kick off", "spin up", "hand this to", "while I'm asleep", "I'll be away"). It files issues, so it never runs just because work is happening in parallel.

Often used withcapture·decide·ingest

GitHubSkill

cross-model-review

github/lever/skills/cross-model-review/SKILL.md

Reviews a PR, diff, plan or skill with 2–3 models from different providers working blind and independently, and surfaces only the findings they agree on or that survive a contradiction-first proof; a precision mode runs one automated reviewer that posts at most two proven findings and stays silent otherwise. Use when asked to "review this with opus, codex and gemini", "rubber duck this plan", "second opinion", "only show me issues the models agree on", when a plan is about to drive a day or more of work, when work has been stuck for hours, or when setting up review-on-ready automation.

GitHubSkill

experiment-arms

github/lever/skills/experiment-arms/SKILL.md

Runs many single-hypothesis "arms" as do-not-merge PRs, measures each with paired, interleaved runs against a cost-matched control, keeps only the arms that clear a keep bar set in advance, records every negative, and composes the winners into a stack that is re-measured on real traffic after merge. It opens PRs and burns CI, so it runs only on `/lever arms` or an explicit ask to measure ideas ("which of these ideas actually helps?", "is this change worth it?", "try that tip I saw", "run arms on this") for a CI, perf, eval, benchmark or cost hill-climb where the system can be run on demand.