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.
46,100 skills from 2,198 repositories · updated 40 minutes ago
9,541 skills
- history-healthOutlineDriven/outline-driven-developmentUse when a user asks to audit what recall fed agents. Not for source or remote-system changes.OtherNo warnings★ 55↓ —
- voice-aicoco-research/cocoPointer to the upstream skill for building voice agents with speech-to-speech and STT-LLM-TTS pipelines, installed from upstream.OtherNo warnings★ 795↓ —
- Blumira FindingsWYRE-AI/msp-claude-pluginsThe Blumira finding lifecycle: status and severity codes, resolution types, list filtering, enriched detail retrieval, assignment, and comment threads.OtherNo warnings★ 52↓ —
- HubSpot ContactsWYRE-AI/msp-claude-pluginsHubSpot contact records: core and MSP-relevant custom fields, lifecycle stages, lead status values, contact ownership, CRM search filter patterns, and associations to companies and deals.OtherNo warnings★ 52↓ —
- zhihu-transcribechubbyguan/chubbyskills知乎视频 → 下载 → 转录 → 存为 Markdown。 支持知乎视频链接、问答内嵌视频和专栏文章，无需登录。OtherNo warnings★ 1.3K↓ —
- coco-loopcoco-research/cocoStart a safe, governed autonomous loop from a plain-language goal. Use when the user says /coco-loop, "run an autonomous loop", "keep my build green for N hours", "work on X autonomously for a while", or wants a bounded self-improving loop that proposes fixes and never commits on its own. Turns a vague goal into a readable charter the user confirms, then arms and runs the loop propose-only under the coco-loops governance framework.OtherNo warnings★ 795↓ —
- pmstudio-nfrcoco-research/cocoDetailed completeness audit of all project documents. Use when someone asks "are we ready for production", "audit our docs", "readiness check", "nfr tracker", or "what's missing". Do NOT use for a quick command listing — use /pmstudio instead. Scans every document for section-level completeness, reports staleness, and gives prioritized gap-closure recommendations.OtherNo warnings★ 795↓ —
- agent-lightningcoco-research/cocoTrain and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore, implementing reward functions, or optimizing prompts with RL/APO algorithms.OtherNo warnings★ 795↓ —
- eu-ai-act-high-risk-classifier-oliver-schmidt-prietzlawve-ai/awesome-legal-skillsDepth assessment of whether an AI system is high-risk under Art. 6 of the EU AI Act, grounded in the Commission's draft Art. 6(5) classification guidelines (general principles + Annex I + Annex III). Covers the Annex I product-safety route, all eight Annex III areas with worked examples, the Art. 6(3) exception and its profiling re-exception, and the Art. 25 quasi-provider trap. Outputs a structured decision block, a practitioner memo, and a JSON interchange artefact.OtherNo warnings★ 911↓ —
- Huntress AgentsWYRE-AI/msp-claude-pluginsHuntress endpoint agents: the agent lifecycle, organization and platform filters, health signals such as `last_seen_at` and version, fleet-audit workflows, and the errors returned for missing or empty agent results.OtherNo warnings★ 52↓ —
- file-operationsmhattingpete/claude-skills-marketplaceAnalyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.OtherNo warnings★ 689↓ —
- post-merge-cleanuparbiterForge/codeArbiterClean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.OtherNo warnings★ 149↓ —
- validatehashgraph-online/awesome-codex-pluginsFreshly judge whether a finished change and its claims meet original acceptance: PASS, FAIL or NOT_PROVEN. Use when: asked for a go/no-go, sign-off or independent verdict.OtherNo warnings★ 1.4K↓ —Also in 2 other repos
- Datto RMM DevicesWYRE-AI/msp-claude-pluginsDatto RMM device management: identifiers (UID, hostname, MAC), device types and statuses, user-defined fields (UDF1-30), warranty data, and device lookup/update/delete operations.OtherNo warnings★ 52↓ —
- rustc-basicsOutlineDriven/outline-driven-developmentUse when selecting RUSTFLAGS, configuring Cargo profiles, tuning release builds, reading assembly or MIR output, understanding monomorphization, or diagnosing compilation errors.OtherNo warnings★ 55↓ —
- cpp-templatesOutlineDriven/outline-driven-developmentUse when a C++ template error needs decoding, a template needs a concept or requires-clause instead of SFINAE, or template instantiation is slowing compilation. Not for C++20 modules: use cpp-modules.OtherNo warnings★ 55↓ —
- zig-compilerOutlineDriven/outline-driven-developmentUse when invoking zig directly: build-exe, build-lib, optimize modes, zig cc as a C compiler, emit flags, ast-check, fmt, or a Zig compile error. Not for build.zig projects: use zig-build-system.OtherNo warnings★ 55↓ —
- lov-fact-checklovstudio/skills用真人尽调思路校验用户提出的事实命题：拆解可验证问题、检索一手资料、 交叉验证证据链，并给出带置信度和不确定边界的结论。 Trigger when the user asks to fact-check, verify a claim, confirm whether something is true, source-check an answer, or mentions "事实校验", "帮我确认", "这是真的吗", "verify this", "fact check", "source check", "due diligence".OtherNo warnings★ 73↓ —
- handoffAvdLee/RocketSimAppCompact the current conversation into a handoff document for another agent to pick up.OtherNo warnings★ 811↓ —Also in 1 other repo
- minutes-tagsilverstein/minutesLightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meetings get tagged, the smarter mirror gets at telling the user what behavior patterns lead to wins. Surface this skill any time the user mentions a meeting result, win, loss, or wasted time.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- giurisprudenza-lampolawve-ai/awesome-legal-skillsRicerca giurisprudenziale rapida per ottenere un quadro di orientamento iniziale su un tema giuridico. Si attiva con "giurisprudenza-lampo [tema]", "cerca giurisprudenza su [tema]", "sentenze su [tema]", "pronunce su [tema]", "orientamento giurisprudenziale su [tema]", o qualsiasi variante che chieda di cercare sentenze, pronunce, massime, orientamenti giurisprudenziali o precedenti su un argomento giuridico. Usa questa skill anche quando l'utente dice "cosa dice la giurisprudenza su", "ci sono sentenze su", "precedenti su", "come si è espressa la Cassazione/il TAR/il Consiglio di Stato su".OtherNo warnings★ 911↓ —
- decision-lifecyclearbiterForge/codeArbiterRecord user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.OtherNo warnings★ 149↓ —
- lov-fill-web-formlovstudio/skillsFill web forms by fetching form fields from a URL, deep-searching the user's local knowledge base for relevant info, and generating a markdown document with all answers pre-filled. Use when the user provides a URL to a web form (conference application, speaker submission, event registration, profile form) and wants help filling it out from their existing materials. Also trigger when the user mentions "填网页表", "fill web form", "网页填表", "表单填写", "申请表填写", "conference application", "speaker submission", "讲师申请", "报名表", or provides a URL with "form", "feedback", "apply", "register", "submit" in the path.OtherNo warnings★ 73↓ —
- post-merge-cleanuparbiterForge/codeArbiterClean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.OtherNo warnings★ 149↓ —
voice-ai
coco-research/coco
OtherUpdated 14 hours ago
From the author
Pointer to the upstream skill for building voice agents with speech-to-speech and STT-LLM-TTS pipelines, installed from upstream.
Install
npx skills add coco-research/coco --skill voice-ai -a claude-code
Installs to .claude/skills/voice-ai/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (Custom or unclear) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyUses the networkLicence: Custom or unclear
Safety checks on SKILL.md
No warnings.
Why 82
Security100
Provenance75
Maintenance100
Licence45
Adoption47
Files (1)
- SKILL.md