Skills pour agents
Skills pour Claude Code, Codex, Cursor et d'autres agents, issues de l'annuaire skills.sh : installations, statut de l'audit de sécurité et commande pour ajouter une skill.
Un skill n’est lié à aucun agent : npx skills add l’installe dans n’importe quel agent pris en charge. Sans -a, la CLI détecte les agents de votre ordinateur et demande où l’ajouter.
Mis à jour · Sources: skills.sh
Affichées : 31 · trouvés : 31 · sur 10 000 dans l'annuaire
-
code-review mattpocock/skills
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
669 376 Échoué -
security-review getsentry/skills
Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.
18 924 Échoué -
azure-devops-cli github/awesome-copilot
Manage Azure DevOps resources via CLI including projects, repos, pipelines, builds, pull requests, work items, artifacts, and service endpoints. Use when working with Azure DevOps, az commands, devops automation, CI/CD, or when user mentions Azure DevOps CLI.
14 068 Échoué -
marimo-pair marimo-team/marimo-pair
Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.
11 435 Échoué -
github-actions callstackincubator/agent-skills
GitHub Actions workflow patterns for React Native iOS simulator and Android emulator cloud builds with downloadable artifacts. Use when setting up CI build pipelines or downloading GitHub Actions artifacts via gh CLI and GitHub API.
9 689 Échoué -
copilot-instructions-blueprint-generator github/awesome-copilot
Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions.
8 928 Échoué -
suggest-awesome-github-copilot-instructions github/awesome-copilot
Suggest relevant GitHub Copilot instruction files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing instructions in this repository, and identifying outdated instructions that need updates.
8 752 Échoué -
ci-cd-security superagent-ai/skills
Scan GitHub Actions workflow files for security vulnerabilities by reading the YAML and reporting findings directly — no external tools, no installation, no shell execution. Use this skill whenever the user shares a `.github/workflows/` file, pastes workflow YAML, asks for a CI/CD security review, mentions `pull_request_target`, `workflow_run`, action pinning, `GITHUB_TOKEN` permissions, pwn requests, template injection, cache poisoning, secret exfiltration, supply chain risk, or any GitHub Actions hardening topic. Also trigger when the user is hardening an OSS repo, doing a CI/CD red team assessment, evaluating a target for supply-chain scanning, or writing publicly about CI/CD security. Bias toward triggering this skill rather than answering from memory — CI/CD security defaults are wrong almost everywhere and the rules are unintuitive.
7 270 Échoué -
news-aggregator-skill cclank/news-aggregator-skill
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub, arXiv, Hugging Face Papers, AIHOT, TLDR AI, Import AI, BBC, The Guardian, Al Jazeera, France 24, Reuters fallback, AI Newsletters, WallStreetCN, Weibo, 少数派, InfoQ 中文, Podcasts, and user-defined OPML feeds. Use when user requests 'daily scans', 'tech news', 'finance updates', 'AI briefings', 'international news', 'deep analysis', or says '如意如意' to open the interactive menu.
5 924 Échoué -
worktrunk max-sixty/worktrunk
Guidance for Worktrunk (the `wt` CLI) — git worktree management, hooks, and config. Load when working out which worktree a `wt` command will act on, or reaching for the global `-C <path>` to target one; editing .config/wt.toml or ~/.config/worktrunk/config.toml; adding, modifying, or debugging hooks (post-merge, post-start, pre-commit, pre-merge, post-switch, etc.); configuring commit message generation or command aliases; or troubleshooting wt behavior. Also answers general worktrunk/wt questions.
5 031 Échoué -
gha-security-review getsentry/skills
GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks. Exploitation-focused with concrete PoC scenarios.
4 544 Échoué -
composio starchild-ai-agent/official-skills
Composio gateway: act on 1000+ connected apps like Gmail, Slack, GitHub, Calendar. Use when the user wants to act in a connected SaaS app (e.g. send Gmail, create Notion page, add Calendar event, open a GitHub issue).
4 319 Échoué -
gemini softaworks/agent-toolkit
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
3 928 Échoué -
security-ownership-map openai/skills
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.
3 553 Échoué -
git-fork-clone zc277584121/mygitplugin
Fork a GitHub repo and clone it locally with proper remote setup
3 211 Échoué -
nuget-trusted-publishing dotnet/skills
Set up NuGet trusted publishing (OIDC) on a GitHub Actions repo — replaces long-lived API keys with short-lived tokens. USE FOR: trusted publishing, NuGet OIDC, keyless NuGet publish, migrate from NuGet API key, NuGet/login, secure NuGet publishing. DO NOT USE FOR: publishing to private feeds or Azure Artifacts (OIDC is nuget.org only). INVOKES: shell (powershell or bash), edit, create, ask_user for guided repo setup.
2 480 Échoué -
fusion-github-review-resolution equinor/fusion-skills
Resolves unresolved GitHub PR review threads end-to-end: evaluates whether each review comment is correct, applies a targeted fix when valid, replies with rationale when not, commits, and resolves the thread. USE FOR: unresolved review threads, PR review feedback, changes requested PRs, PR review URLs (#pullrequestreview-...), fix the review comments, close the open threads, address PR feedback. DO NOT USE FOR: summarizing feedback without code changes, creating new PRs, or read-only branches.
2 363 Échoué -
sentry-pr-code-review getsentry/sentry-for-ai
2 263 Échoué -
difit yoshiko-pg/difit
Ask the user for a code review by opening the changes in difit, a local diff viewer. Explicit opt-in only — use when the user names difit, asks to open or show the diff in the viewer, or has a standing instruction to request reviews through difit after changes. Do not use it for ordinary requests to review code, diffs, commits, branches, or pull requests.
2 109 Échoué -
code-review paulrberg/agent-skills
2 013 Échoué -
issue-fields-migration github/awesome-copilot
Bulk-migrate metadata to GitHub issue fields from two sources: repo labels (e.g. priority labels to a Priority field) and Project V2 fields. Use when users say "migrate my labels to issue fields", "migrate project fields to issue fields", "convert labels to issue fields", "copy project field values to issue fields", or ask about adopting issue fields. Issue fields are org-level typed metadata (single select, text, number, date) that replace label-based workarounds with structured, searchable, cross-repo fields.
1 882 Échoué -
publish-to-pages github/awesome-copilot
Publish presentations and web content to GitHub Pages. Converts PPTX, PDF, HTML, or Google Slides to a live GitHub Pages URL. Handles repo creation, file conversion, Pages enablement, and returns the live URL. Use when the user wants to publish, deploy, or share a presentation or HTML file via GitHub Pages.
1 833 Échoué -
nodejs-core mcollina/skills
Contributes to and debugs Node.js core, including nodejs/node commit and PR tone, contribution workflows, native crashes, V8 performance, node-gyp builds, N-API bindings, and libuv issues. Use when drafting or reviewing a Node.js core commit or pull request, working in nodejs/node, or diagnosing C++ addons, binding.gyp failures, segfaults, native leaks, V8 deoptimizations, and event-loop internals.
1 812 Échoué -
gitlab-cli-skills vince-winkintel/gitlab-cli-skills
Comprehensive GitLab CLI (glab) command reference and workflows for all GitLab operations via terminal. Use when user mentions GitLab CLI, glab commands, GitLab automation, MR/issue management via CLI, CI/CD pipeline commands, Artifact Registry token exchange, repo operations, authentication setup, or any GitLab terminal operations. Routes to specialized sub-skills for auth, CI, MRs, issues, releases, repos, and 30+ other glab commands. Triggers on glab, GitLab CLI, GitLab commands, GitLab terminal, GitLab automation.
1 780 Échoué -
gstack-workflow-assistant reason-machines/trending-skills
Team of specialist AI workflows for Claude Code with CEO review, engineering planning, code review, shipping, QA testing, and browser automation
1 639 Échoué -
ctx-upgrade mksglu/context-mode
Update context-mode from GitHub and fix hooks/settings. Pulls latest, builds, installs, updates npm global, configures hooks. Trigger: /context-mode:ctx-upgrade
1 432 Échoué -
speckit-taskstoissues dceoy/speckit-agent-skills
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
1 431 Échoué -
code-review alinaqi/maggy
Mandatory code reviews via /code-review before commits and deploys
1 386 Échoué -
adversarial-review poteto/noodle
Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesized verdict with findings and lead judgment. Triggers: "adversarial review".
1 368 Échoué -
github-project-management ruvnet/ruflo
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
1 361 Échoué -
github-release jezweb/claude-skills
Prepare and publish GitHub releases. Sanitizes code for public release (secrets scan, personal artifacts, LICENSE/README validation), creates version tags, and publishes via gh CLI. Trigger with 'release', 'publish', 'open source', 'prepare for release', 'create release', or 'github release'.
1 286 Échoué
Les descriptions sont celles des auteurs, en anglais. Lisez le code d'une skill dans son dépôt avant de l'installer.
Qu'est-ce qu'un skill d'agent ?
Un skill est un dossier contenant un fichier SKILL.md, et parfois des scripts, que l'agent charge quand la tâche en cours correspond à sa description. On apprend ainsi à Claude Code, Codex, Cursor ou à d'autres agents une procédure précise : rédiger dans un certain style, manipuler un format de fichier, suivre les conventions d'un projet. Cette page reprend l'annuaire skills.sh.
Que trouve-t-on dans l'annuaire ?
Les 10 000 skills qui comptent le plus d'installations sur skills.sh, synchronisés chaque jour. Pour chacun : le nom, l'auteur et le dépôt, le nombre d'installations, le statut d'audit de sécurité et la commande pour l'ajouter, avec un bouton pour la copier. L'onglet « Tendances » montre les installations gagnées sur les 7 derniers jours. Des filtres par thème et par agent, ainsi qu'une recherche, affinent la liste, avec au plus 100 skills par affichage. Les descriptions sont celles des auteurs, en anglais, et ne sont pas traduites.
Que signifient les statuts d'audit ?
- « Réussi » : l'audit publié par skills.sh n'a rien relevé ;
- « Avertissements » : des points méritent votre attention ;
- « Échoué » : l'audit a détecté un problème ;
- « Non audité » : aucun audit n'est disponible.
Un audit réussi suffit-il ?
Non. Un audit réussi n'est pas une garantie. Un skill peut contenir des scripts que l'agent exécutera sur votre machine : lisez le code dans le dépôt GitHub avant de l'installer, surtout s'il demande un accès au réseau ou à des fichiers sensibles.
Comment installer un skill ?
- Trouvez-le par la recherche ou les filtres.
- Ouvrez le dépôt pour lire le fichier SKILL.md et les scripts.
- Copiez la commande affichée et exécutez-la dans votre projet.
D'où viennent les chiffres ?
Les installations et les audits sont comptés par skills.sh ; le code de chaque skill est sur GitHub. Pour choisir l'agent qui utilisera ces skills, voyez la page des agents de code.