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 9Worked for most · soon
victorgarciaesgiSkill

code-review

victorgarciaesgi/regle/.github/skills/code-review/SKILL.md

Mandatory pre-commit validation for every Copilot code review on pull requests in the regle monorepo. Always verify commitlint compliance on commit titles and descriptions, pnpm workspace install, lint (vp lint), and format (vp fmt --check). Loaded on every code review — do not skip.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

5089mo agoReviewMountCreate a free account to mount
canonicalSkill

code-review

canonical/lxd-ui/.github/skills/code-review/SKILL.md

Review a GitHub PR for the LXD-UI codebase. Checks code quality, security, and adherence to LXD-UI conventions including TypeScript, React, React Query, side panel patterns, notifications, and OWASP Top 10. For GitHub Copilot code review and VS Code Copilot Chat. Triggers on: code review, review, PR review, code quality, security review.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

50034d agoReviewMountCreate a free account to mount
ankitvguptaReads credentialsSkill

review-code

ankitvgupta/exo/.claude/skills/review-code/SKILL.md

Pre-commit code review for production-critical issues. Use when reviewing staged changes, before committing, or when asked to review code for bugs and consistency issues.

4946mo agoReviewMountCreate a free account to mount
MicrosoftSkill

code-review

microsoft/mssql-python/.github/skills/code-review/SKILL.md

General repository code review for microsoft/mssql-python, based solely on .github/copilot-instructions.md. Use when reviewing pull requests or diffs across the Python API, native bindings, packaging, tests, CI, or documentation. Apply the repository's existing architecture, correctness, compatibility, testing, and credential-handling expectations without replacing normal Copilot review.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

48343d agoReviewMountCreate a free account to mount
esphomeSkill

code-review

esphome/esphome-docs/.agents/skills/code-review/SKILL.md

Review esphome.io documentation changes (the local diff, a branch, or a PR number) against CONTRIBUTING.md, the CI lint gates, and the ESPHome source. Use when asked to review docs changes, a docs PR, or "check my changes before I open a PR".

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

46734d agoReviewMountCreate a free account to mount
SentrySkill

code-review

getsentry/warden/packages/warden/src/builtin-skills/code-review/SKILL.md

Finds real correctness bugs in code changes. Use for adversarial code review, bug hunts, regression review, PR correctness review, logic errors, data loss, race conditions, state bugs, interface contract breaks, error handling bugs, edge cases, broken builds, or broken workflows. Excludes style, readability, architecture, AppSec, and best-practice-only feedback unless the issue causes a demonstrable bug.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

4249mo agoReviewMountCreate a free account to mount
liza-masSkill

code-review

liza-mas/liza/skills/code-review/SKILL.md

Two-sided review protocol — reviewers raise findings, authors answer them. Use when reviewing a change to code or to another artifact (spec, plan, doc, contract, proposal), pending or in a PR, or when responding to review feedback, review comments, or a rejected verdict. For a consistency-and-gap audit of a specification, use spec-review.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

41812d agoReviewMountCreate a free account to mount
hyperledger-cactiSkill

code-review

hyperledger-cacti/cacti/.github/skills/code-review/SKILL.md

Apply when reviewing a pull request in Hyperledger Cacti. Covers PR scope, Conventional Commits, TypeScript conventions, public API surface, testing, security (OWASP Top 10), AI slop detection, and CI status.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

4124mo agoReviewMountCreate a free account to mount
MicrosoftSkill

code-review

microsoft/mssql-django/.github/skills/code-review/SKILL.md

Review methodology for pull requests to the mssql-django SQL Server backend. Use when reviewing a PR that changes the Django database backend under mssql/ or its tests under testapp/. Adds whole-PR, cross-file, and cross-version review procedure on top of the path-scoped instructions in .github/instructions/.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

3992mo agoReviewMountCreate a free account to mount
hcloud-talosSkill

code-review

hcloud-talos/terraform-hcloud-talos/.agents/skills/code-review/SKILL.md

Review a branch, PR, commit range, or working tree with separate Standards and Spec tasks through review_run. Use when the user asks for a code review or asks to review changes since a fixed point.

Often used withclose-specadd-new-modelazsdk-common-apiview-feedback-resolution

36453d 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.