agentleFS

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.

Best matches · from page 7Worked for most · soon
alibabaSkill

open-code-review-delegate

alibaba/open-code-review/skills/open-code-review-delegate/SKILL.md

Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.

Surging6 mentions in 2 weeks

5 projects use a version of this

52k3mo agoReviewMountCreate a free account to mount
rustfsSkill

pr-review

rustfs/rustfs/.agents/skills/pr-review/SKILL.md

Review a GitHub PR using its exact base/head and repository risk policy. Use for requested PR reviews; publish or fix only within conversation authorization.

195 projects use a version of this

36k17d agoReviewMountCreate a free account to mount
remix-runSkill

review-pr

remix-run/remix/.agents/skills/review-pr/SKILL.md

Review Remix pull requests from a local development checkout. Use when asked to review a PR, inspect a pull request diff, or produce a thorough reviewer-style assessment.

33k5d agoReviewMountCreate a free account to mount
tirth8205Skill

review-pr

tirth8205/code-review-graph/skills/review-pr/SKILL.md

Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.

Steady6 mentions in 2 weeks

185 projects use a version of this

33k5d agoReviewMountCreate a free account to mount
alpinejsSkill

review-pr

alpinejs/alpine/.claude/skills/review-pr/SKILL.md

Review an open PR like a maintainer — checkout, fix issues, push changes, post a structured verdict comment. You just merge or close.

Steady7 mentions in 2 weeks

185 projects use a version of this

32k9mo agoReviewMountCreate a free account to mount
wanshuiyinSkill

comm-lit-review

wanshuiyin/Auto-claude-code-research-in-sleep/skills/comm-lit-review/SKILL.md

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.

Steady5 mentions in 2 weeks

2 projects use a version of this

19k4mo agoReviewMountCreate a free account to mount
wanshuiyinSkill

comm-lit-review

wanshuiyin/Auto-claude-code-research-in-sleep/skills/skills-codex/comm-lit-review/SKILL.md

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.

Steady5 mentions in 2 weeks

2 projects use a version of this

19k4mo agoReviewMountCreate a free account to mount
nrwlSkill

review-pr

nrwl/nx/.agents/skills/review-pr/SKILL.md

Deep, findings-first review of one nrwl/nx pull request from a PR reference or associated Linear task, including drafts. Uses four fixed Sol/xhigh lanes, exact merge-base scope, inert snapshots, optional sandboxed checks, and produces one private record holding a postable review draft, without posting it.

29k13d agoReviewMountCreate a free account to mount
nrwlSkill

review-pr

nrwl/nx/.claude/skills/review-pr/SKILL.md

Deep code review of a single open PR in nrwl/nx. Checks the PR out only inside an isolated sandbox, then runs four fixed reviewers: implementation (correctness, errors, types, performance), verification (tests, ticket grounding, comments, and docs), approach, and security. A reproduce-verifier executes a runnable repro only when verification identifies one. The skill saves a GitHub-flavored draft to ~/.nx-pr-reviews/<NUMBER>.md and never posts it. Claude reads/executes PR code only through the sandbox CLI; credentials never enter the sandbox.

29k13d agoReviewMountCreate a free account to mount
PrefectHQSkill

review-pr

PrefectHQ/fastmcp/.agents/skills/review-pr/SKILL.md

Assess a FastMCP pull request for justified behavior, compatibility, and correctness, then follow CI and review feedback to a revision-specific verdict. Use for draft or ready PRs and self-review before publication.

29k4d agoReviewMountCreate a free account to mount
PaddlePaddleSkill

ai-review

PaddlePaddle/Paddle/.agents/skills/ai-review/SKILL.md

使用 PaddlePaddle 仓库规则评审 Pull Request 和全仓库代码变更,覆盖正确性、兼容性、算子、分布式、数值、性能、安全、测试、构建和 PR 信息。当需要审查 Paddle 的代码、测试、算子 YAML、C++/CUDA/XPU kernel、Python API、分布式逻辑或 CI 配置时使用。

24k3mo agoReviewMountCreate a free account to mount
livewireSkill

review-pr

livewire/livewire/.claude/skills/review-pr/SKILL.md

Review an open PR like a maintainer — checkout, fix issues, push changes, post a structured verdict comment. You just merge or close.

24k9mo agoReviewMountCreate a free account to mount
dotnetDeletes or force-pushesSkill

pr-review

dotnet/maui/.github/skills/pr-review/SKILL.md

End-to-end PR reviewer for dotnet/maui. Orchestrates 3 phases — Pre-Flight, Try-Fix, Report. Gate runs separately before this skill. Use when asked to 'review PR #XXXXX', 'work on PR #XXXXX', or 'fix issue #XXXXX'.

23k17d agoReviewMountCreate a free account to mount
MicrosoftSkill

review-pr

microsoft/fluentui/.agents/skills/review-pr/SKILL.md

Review a PR for correctness, pattern compliance, testing, accessibility, and safety. Produces a confidence score for merge readiness.

20k42d agoReviewMountCreate a free account to mount
MicrosoftSkill

review-pr

microsoft/fluentui/.claude/skills/review-pr/SKILL.md

@../../../.agents/skills/review-pr/SKILL.md

20k42d agoReviewMountCreate a free account to mount
NVIDIASkill

pr-review

NVIDIA/Megatron-LM/skills/pr-review/SKILL.md

Review rubric for the `/review` pull-request command. The formal reviewer reads it as a file and it is not an interactive skill — do not load it to answer questions or to review code outside that command.

18k3d agoReviewMountCreate a free account to mount
verdaccioSkill

review-pr

verdaccio/verdaccio/.agents/skills/review-pr/SKILL.md

Review an existing verdaccio/verdaccio pull request end to end — description, diff, review threads, CI, labels, changeset, release-line coverage — verify the findings, and report them; optionally fix them on the PR branch when asked. Use when given a PR number or URL to review, re-review, or "review and fix".

18k8d agoReviewMountCreate a free account to mount
questdbSkill

review-pr

questdb/questdb/.claude/skills/review-pr/SKILL.md

Review a GitHub pull request or local Git range against QuestDB coding standards

18k11d agoReviewMountCreate a free account to mount
tisfengSkill

review-pr

tisfeng/Easydict/.agents/skills/review-pr/SKILL.md

审查 GitHub PR 的准确 head/base diff、关联 issue、CI 和 review threads;明确调用时回复并关闭已解决线程,交付前刷新。创建 PR 使用 submit-pr;本地审查使用 review。

185 projects use a version of this

15k5d agoReviewMountCreate a free account to mount
MicrosoftReads credentialsSkill

api-review

microsoft/playwright/.claude/skills/api-review/SKILL.md

Produce the "Playwright 1.xx API Review" artifact for a range of commits - the public API additions and the breaking or behavior changes that affect existing users since the last API review or since the last release, ordered by impact, each with links, before/after snippets and a documentation check. Covers microsoft/playwright (Node.js) and the Python, Java and .NET ports. Use when asked for an API review, to review API changes, or to check what changed in the public API since a release or since the last review.

8 projects use a version of this

100k6d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

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.