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 9Worked for most · soon
secdevSkill

scapy-code-review

secdev/scapy/.github/skills/scapy-code-review/SKILL.md

Review or re-review Scapy pull requests, branches, patches, and protocol implementations for correctness, simplicity, Scapy-likeness, backwards compatibility, robustness, performance, and tests. Compare old and new code, trace prior human review comments to their subsequent fixes, and return concise, evidence-backed, actionable findings rather than speculative suggestions.

Steady10 mentions in 2 weeks

No other project uses it yet

13k5y agoReviewMountCreate a free account to mount
MilkdownSkill

review-code-style

Milkdown/milkdown/.claude/skills/review-code-style/SKILL.md

Review all changed or newly added code in this repository for code style and quality issues. Check both staged and unstaged changes.

Steady15 mentions in 2 weeks

No other project uses it yet

12k3mo agoReviewMountCreate a free account to mount
OpenAISkill

receiving-code-review

openai/plugins/plugins/superpowers/skills/receiving-code-review/SKILL.md

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Steady5 mentions in 2 weeks

187 projects use a version of this

Often used withchinese-code-reviewdiagnosing-superpowerschinese-commit-conventions

7.8k6mo agoReviewMountCreate a free account to mount
phw198Skill

ogcs-code-review

phw198/OutlookGoogleCalendarSync/.github/skills/ogcs-code-review/SKILL.md

Review committed code changes on a branch for correctness, regressions, and code quality.

2.1k6y agoReviewMountCreate a free account to mount
polarsourceSkill

polar-code-review

polarsource/polar/.agents/skills/polar-code-review/SKILL.md

Review a Polar branch diff against conventions, Accepted ADRs, reuse, slop, and path-triggered API, ship-safety, and billing lenses. Use before opening a PR, when the user asks for a Polar code review, /polar-code-review, or $polar-code-review. Not a bug hunt or security review.

Steady4 mentions in 2 weeks

No other project uses it yet

10k5d agoReviewMountCreate a free account to mount
RabbyHubSkill

rabby-code-review

RabbyHub/Rabby/skills/rabby-code-review/SKILL.md

Review Rabby browser-extension pull requests for actionable correctness, wallet-safety, security, privacy, build, and supply-chain issues, and publish validated inline GitHub findings. Use when Codex is asked to review a Rabby PR or its changed code; do not use it to implement fixes unless separately requested.

1.9k3mo agoReviewMountCreate a free account to mount
vudovnSkill

code-review-graph

vudovn/ag-kit/.agents/skills/code-review-graph/SKILL.md

Token-efficient code review using Tree-sitter AST graphs and MCP. Cuts AI token usage on large codebases by computing the blast radius of changes instead of reading entire codebases. Uses a SQLite graph database for structural analysis.

8.2k4mo agoReviewMountCreate a free account to mount
AzureADSkill

msal-code-review

AzureAD/microsoft-authentication-library-for-dotnet/.github/skills/msal-code-review/SKILL.md

Repository-wide MSAL.NET pull request review for correctness, behavioral compatibility, public API contracts, protocol behavior, caching, concurrency, transports, platforms, packaging, performance, security, privacy, and test adequacy. Use before reviewing any pull request in this repository.

Steady6 mentions in 2 weeks

No other project uses it yet

1.5k3y agoReviewMountCreate a free account to mount
uswdsSkill

uswds-code-review

uswds/uswds/.agents/skills/uswds-code-review/SKILL.md

Review USWDS PRs or branches using the core team's calibrated judgment. Enforces 16 specific gates (size, dependencies, DRY, sanitization, test regression, etc.), distinguishes personal preference from what all consumers inherit, and routes specialist decisions (accessibility, breaking changes, new API surface). Use when the user says "review this", "code review", "review the PR", asks for feedback on changes, or explicitly invokes /uswds-code-review.

7.2k59d agoReviewMountCreate a free account to mount
langgeniusSkill

backend-code-review

langgenius/dify/.agents/skills/backend-code-review/SKILL.md

Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, frontend code, or backend code outside `api/`.

6 projects use a version of this

161k17d agoReviewMountCreate a free account to mount
langflow-aiReads credentialsSkill

backend-code-review

langflow-ai/langflow/.agents/skills/backend-code-review/SKILL.md

Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `src/backend/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.

6 projects use a version of this

157k21d agoReviewMountCreate a free account to mount
asterinasSkill

aster-code-review

asterinas/asterinas/.agents/skills/aster-code-review/SKILL.md

Review code against Asterinas's persona-keyed coding guidelines and write a Markdown review file. Use when asked to review a Git change (diff mode) or a set of target files (files mode) for defects, or inside a write-test-review loop.

5.1k14d agoReviewMountCreate a free account to mount
nyldnSkill

skill-code-review

nyldn/claude-octopus/.claude/skills/skill-code-review/SKILL.md

Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis

Steady19 mentions in 2 weeks

3 projects use a version of this

4.4k3mo agoReviewMountCreate a free account to mount
nyldnSkill

skill-code-review

nyldn/claude-octopus/skills/skill-code-review/SKILL.md

Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis

Steady19 mentions in 2 weeks

3 projects use a version of this

4.4k3mo agoReviewMountCreate a free account to mount
gradleSkill

gradle-code-review

gradle/gradle/.claude/skills/gradle-code-review/SKILL.md

The code review workflow for this Gradle repository. Use whenever the user asks to review code, perform/do a code review, review a change, diff, branch, or PR, or check changes before they reach the target branch. Prefer this over any generic code-review skill when working in this repo.

19k19d agoReviewMountCreate a free account to mount
BytePioneer-AISkill

codexhost-code-review

BytePioneer-AI/codex-host/.agents/skills/codexhost-code-review/SKILL.md

审查 codexhost 的 Pull Request 或本地 diff 的正确性与边界。检查包与 Rust 所有权边界、官方 Thread 与外部 Harness Thread 的区分、Renderer 私有绑定、生命周期与测试强度。用于“review 这个 PR / diff”;一批 PR 的总览与推荐分请先用 codexhost-pr-overview,再对其中需深审的 PR 使用本 skill。

3.2k1d agoReviewMountCreate a free account to mount
penpotSkill

code-review-criteria

penpot/penpot/.agents/skills/code-review-criteria/SKILL.md

Code review criteria — the five review axes, core principles, severity format, and verdict for reviewing code changes. Loaded by the reviewer subagent of the review-code flow. Not a user-facing flow — to review code, use the review-code flow.

Steady6 mentions in 2 weeks

No other project uses it yet

62k2mo 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.