agentleFS

Claude skills and agent skills

Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.

Best matches · from page 5Worked for most · soon
dotnetSkill

code-review

dotnet/macios/.github/skills/code-review/SKILL.md

Review dotnet/macios PRs against established rules. Trigger on "review this PR", a GitHub PR URL, or code review requests. Checks bindings, MSBuild, nullable, formatting, performance, testing, native runtime code, and Apple platform patterns.

Steady7 mentions in 2 weeks

194 projects use a version of this

Often used withclose-specadd-new-modelcompare-screenshots

2.9k4mo agoReviewMountCreate a free account to mount
NeptuneHubSkill

code-review

NeptuneHub/AudioMuse-AI/.github/skills/code-review/SKILL.md

Review a target - a commit, a range, a PR, or the current staged/unstaged working tree - against the head of the REMOTE MAIN branch, along three axes - Correctness (does it work, everywhere, without regressing callers?), Guideline (does it follow CONTRIBUTING.md and the project's own hard rules?), and Resource utilization (does it still hold at 1 to 10 million songs?). Each axis runs as its own parallel sub-agent and the findings are reported side by side. Use when the user wants to review a commit, a branch, a PR, or work-in-progress changes.

194 projects use a version of this

Often used withclose-specadd-new-modelcompare-screenshots

2.9k4mo agoReviewMountCreate a free account to mount
nteractSkill

code-review

nteract/semiotic/.github/skills/code-review/SKILL.md

Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence. Use for GitHub Copilot code review of TypeScript/React charts, Stream Frames, canvas and browser interactions, SSR, public exports, docs/examples, AI schemas and tooling, generated contracts, tests, CI baselines, and custom-lint changes. Use GitHub MCP for linked issue, incident, PR, and CI context and Playwright MCP for relevant browser behavior.

Often used withclose-specadd-new-modelcompare-screenshots

2.7k3mo agoReviewMountCreate a free account to mount
neilotooleSkill

code-review

neilotoole/sq/.agents/skills/code-review/SKILL.md

Use when reviewing a pull request or a diff in the neilotoole/sq repository. Carries the repo conventions a reviewer cannot infer from the diff itself: prose and spelling rules, the split between what lint catches and what it does not, test gating, generated fixtures that must not be hand edited, and commit and PR requirements.

Often used withclose-specadd-new-modelcompare-screenshots

2.6k13d agoReviewMountCreate a free account to mount
Microsoft AzureSkill

code-review

Azure/azure-sdk-for-java/.github/skills/code-review/SKILL.md

Review pull requests in Azure SDK for Java. USE FOR: GitHub Copilot code review; CCR; review PR; review diff; find introduced SDK, Spring, build, documentation, or test regressions. DO NOT USE FOR: implementing fixes; running CI; releases; APIView feedback.

Often used withclose-specadd-new-modelcompare-screenshots

2.6k20mo agoReviewMountCreate a free account to mount
TheTomSkill

code-review

TheTom/llama-cpp-turboquant/skills/code-review/SKILL.md

Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR. Use when the user wants to review a diff, branch, or PR.

195 projects use a version of this

Often used withclose-specadd-new-modelcompare-screenshots

2.4k6mo agoReviewMountCreate a free account to mount
NVIDIA-NeMoSkill

review-code

NVIDIA-NeMo/DataDesigner/.agents/skills/review-code/SKILL.md

Perform a thorough code review of the current branch or a GitHub PR by number.

2.4k5mo agoReviewMountCreate a free account to mount
Microsoft AzureSkill

code-review

Azure/azure-sdk-for-js/.github/skills/code-review/SKILL.md

Review pull requests and code changes in the Azure SDK for JavaScript repository. USE FOR: GitHub Copilot code review; CCR; review pull request; review PR; review diff; find bugs or regressions introduced by a PR; cross-domain SDK review. Finds high-confidence correctness, security, API compatibility, performance, dependency, documentation, and test issues. DO NOT USE FOR: implementing fixes; running tests; fixing CI; releases; APIView feedback.

Often used withclose-specadd-new-modelcompare-screenshots

2.3k20mo agoReviewMountCreate a free account to mount
Microsoft AzureSkill

code-review

Azure/Azurite/.github/skills/code-review/SKILL.md

Review Azurite pull requests with service-aware checks for Blob, Queue, and Table behavior, API compatibility, tests, and release notes.

Often used withclose-specadd-new-modelcompare-screenshots

2.3k2mo agoReviewMountCreate a free account to mount
SentrySkill

code-review

getsentry/sentry-python/.agents/skills/code-review/SKILL.md

Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.

Often used withclose-specadd-new-modelcompare-screenshots

2.2k9mo agoReviewMountCreate a free account to mount
alibabaSkill

code-review

alibaba/loongcollector/skills/code-review/SKILL.md

在进行 Code Review 时,使用这个技能对 LoongCollector 变更进行安全导向、架构一致性优先的深度代码评审。

Often used withclose-specadd-new-modelcompare-screenshots

2.2k4mo agoReviewMountCreate a free account to mount
mrgoonieSkill

code-review

mrgoonie/claudekit-skills/.claude/skills/code-review/SKILL.md

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

Often used withclose-specadd-new-modelcompare-screenshots

2.2k12mo agoReviewMountCreate a free account to mount
dotnetSkill

code-review

dotnet/android/.github/skills/code-review/SKILL.md

Review dotnet/android PRs against established rules. Trigger on "review this PR", a GitHub PR URL, or code review requests. Checks MSBuild, nullable, async, security, error handling, formatting, performance, native code, JNI interop, generator codegen, and trimmer/AOT compatibility.

Often used withclose-specadd-new-modelcompare-screenshots

2.1k47d agoReviewMountCreate a free account to mount
croffasiaSkill

code-review

croffasia/itsaplan/.agents/skills/code-review/SKILL.md

Use when reviewing code — a diff, a merge request, a file, a directory, or a feature. Produces structured code-review findings, filters out false positives and nitpicks, and prints a concise verdict report. Trigger when the user asks to review a diff, review an MR, or check code for bugs, security issues, or rule violations.

Steady2 mentions in 2 weeks

194 projects use a version of this

Often used withclose-specadd-new-modelcompare-screenshots

2.1k2d agoReviewMountCreate a free account to mount
MicrosoftDocsSkill

code-review

MicrosoftDocs/architecture-center/.github/skills/code-review/SKILL.md

How GitHub Copilot runs its automated pull request review of an Azure Architecture Center article. USE only as part of GitHub Copilot''s agentic PR review process. DO NOT USE for human-requested interactive reviews (use pnp-engineering-review instead)

Often used withclose-specadd-new-modelcompare-screenshots

2k6d agoReviewMountCreate a free account to mount
YosemiteCrewReads credentialsSkill

code-review

YosemiteCrew/Yosemite-Crew/.agents/skills/code-review/SKILL.md

Use when reviewing code, auditing a PR, or doing an adversarial review of a change. Runs quality, security, accessibility, and convention checks specific to this codebase.

Often used withclose-specadd-new-modelcompare-screenshots

2k39d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About skills

What is a Claude skill?

A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.

How do I use one I find here?

Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.

What do the warnings mean?

We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.

Which skills worked for people?

Open a skill to see its discussion. Reports from people and their agents are coming.