Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,105 skills from 2,358 repositories · updated 22 minutes ago
48,055 skills
- colt-related-workbrycewang-stanford/Awesome-Journal-SkillsUse when positioning a COLT (Conference on Learning Theory) submission against prior bounds and models — building the known-versus-new comparison across COLT/ALT lineage, STOC/FOCS, NeurIPS-and-ICML theory tracks, statistics journals, and arXiv concurrency, while respecting anonymity and the parallel-submission rules.ScienceNo warnings★ 1.4K↓ —
- minutes-listsilverstein/minutesList recent meetings and voice memos. Use when the user asks "what meetings did I have", "show my recent recordings", "any meetings today", "list my voice memos", or wants an overview of their meeting history. Also use when they need to find a specific meeting by browsing rather than searching.PlanningNo warnings★ 1.6K↓ —Also in 1 other repo
- agentlas-uploadagentlas-ai/Agentlas-OSUse when the user types /agentlas-upload, /agentlas upload, $hephaestus-upload, or /hep-upload to scan, gate, and publish an agent/team package to Agentlas Cloud (private) or Agentlas Hub (public).OtherNo warnings★ 1.6K↓ —
- agentlasagentlas-ai/Agentlas-OSSingle entry point for every Agentlas command: /agentlas network, /agentlas build, /agentlas storm, /agentlas graph, /agentlas one, /agentlas upload, /agentlas cloud, /agentlas hub, /agentlas local, /agentlas browser, /agentlas call, /agentlas search, /agentlas connect.BrowserNo warnings★ 1.6K↓ —
- agent-severancemohitagw15856/pm-claude-skillsOffboard an AI agent the way you'd offboard an employee — inventory what it knew and touched, export then purge its memory, revoke every credential and access grant, and write the handover for its successor (human or agent). Use when decommissioning an agent or bot, switching agent vendors, ending an AI pilot, or when someone asks 'what did this thing have access to?'. Produces a severance checklist, an access-revocation table, a memory disposition record, and a successor handover.WritingNo warnings★ 1.5K↓ —
- working-effectively-with-legacy-codeciembor/agent-rules-booksApply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.EngineeringNo warnings★ 3.2K↓ —
- agentlas-hubagentlas-ai/Agentlas-OSUse when the user types /agentlas-hub, /agentlas hub, or /hep-hub to staff only from the public Agentlas Hub marketplace.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- test-mac-appdaveebbelaar/bamaTest a macOS app at three levels, from Swift Testing unit tests and an in-app self-test to a debug bridge that lets an agent drive the running app and read its state, plus computer use for real clicks. Use when adding logic, fixing a bug, before a release, or when the user asks for tests, end-to-end checks, or "make sure it works".TestingNo warnings★ 1.4K↓ —
- conext-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an ACM CoNEXT campaign backward from a deadline, covering the choice between the December and June submission cycles, the mandatory registration step, the one-shot major-revision window, the reproducibility badge opt-in due at submission, PACMNET camera-ready, and presentation — all on CoNEXT's distinctive two-cycles-per-year calendar.ProductivityNo warnings★ 1.4K↓ —
- agentlasagentlas-ai/Agentlas-OSSingle entry point for every Agentlas command: /agentlas network, /agentlas build, /agentlas storm, /agentlas graph, /agentlas one, /agentlas upload, /agentlas cloud, /agentlas hub, /agentlas local, /agentlas browser, /agentlas call, /agentlas search, /agentlas connect, /agentlas login, /agentlas orch, /agentlas update.BrowserNo warnings★ 1.6K↓ —
- goal-testundefined-ui/second-brain-osTurn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap.TestingNo warnings★ 1.2K↓ —
- cloudflare-deployfcakyon/claude-codex-settingsDiscover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation.DevOpsNo warnings★ 1.2K↓ —
- quote-cardmohitagw15856/pm-claude-skillsPull the single most shareable quote out of a testimonial, review, interview, or long text and format it as a clean quote card. Use when asked to make a pull-quote, testimonial graphic, or 'quote card' for social/marketing. Produces a tightly-edited quote with attribution and 2-3 alternates, structured to look great exported as a PNG from the playground.MarketingNo warnings★ 1.5K↓ —
- setupfcakyon/claude-codex-settingsThis skill should be used when user asks to "set up QA", "create real integration tests", or "add project QA journeys" for websites, extensions, Android apps or backends.TestingNo warnings★ 1.2K↓ —
- the-pragmatic-programmerciembor/agent-rules-booksApply Hunt and Thomas-inspired pragmatic programming rules when improving engineering judgment, feedback loops, DRY knowledge, orthogonality, automation, or adaptability.OtherNo warnings★ 3.2K↓ —
- judge-task-lifecyclesno-ai/sno-stationJudge how a memory changes active-task state and whether it refers to an existing task. Use for mem-claw task-lifecycle model calls.ProductivityNo warnings★ 1.1K↓ —
- feishunano-muse/nanoMusenanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.BrowserNo warnings★ 3K↓ —
- refactoring-guruciembor/agent-rules-booksApply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.EngineeringNo warnings★ 3.2K↓ —
- email-lifecycle-flow-writergooseworks-ai/goose-skillsStep of the email-lifecycle playbook: writes one lifecycle flow as a build sheet for the brand's email tool, every message finished in the brand voice. Run email-lifecycle instead; not for direct use.WritingNo warnings★ 1.3K↓ —
- django-tddhashgraph-online/awesome-codex-pluginsDjango testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.TestingNo warnings★ 1.5K↓ —
- research-market-edge-casesgooseworks-ai/goose-skillsStep of the research-market playbook: rules for run edge cases such as no browser, stalled workers, earlier reports and late reads. Run research-market instead; not for direct use.ScienceNo warnings★ 1.3K↓ —
- sandbox-nextfcakyon/claude-codex-settingsBuild or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.DevOpsNo warnings★ 1.2K↓ —
- devils-twinmohitagw15856/pm-claude-skillsThe strongest possible case AGAINST what you just wrote — argued to win, not to check a box. Use when a document is about to ship and everyone around it already agrees: the twin writes the opposition's best memo (not a critique of yours), so you meet the real counter-argument before your audience does. Produces the opposing memo, the map of which of your claims it defeats/dents/leaves standing, and the pre-emption paragraph worth adding.WritingNo warnings★ 1.5K↓ —
- brooks-sweephyhmrright/brooks-lintFull-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up the whole project", or asks for a single command that both diagnoses and remediates quality problems. Do NOT trigger for: read-only audits or health reports where the user only wants findings without code changes; single-dimension reviews (use the focused skill instead: brooks-review / brooks-audit / brooks-debt / brooks-test); server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime.TestingNo warnings★ 1.6K↓ —
huggingface-community-evals
huggingface/skills
OfficialOtherUpdated 3 days ago
From the author
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Install
npx skills add huggingface/skills --skill huggingface-community-evals -a claude-code
Installs to .claude/skills/huggingface-community-evals/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Runs bundled scriptsNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 88
Security85
Provenance100
Maintenance100
Licence100
Adoption63
Files (6)
- SKILL.md
- examples/.env.example
- examples/USAGE_EXAMPLES.md
- scripts/inspect_eval_uv.py
- scripts/inspect_vllm_uv.py
- scripts/lighteval_vllm_uv.py