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.
46,700 skills from 2,243 repositories · updated 14 hours ago
10,031 skills
- grace-askosovv/grace-marketplaceAnswer questions about a GRACE 4 project by navigating .grace current-state artifacts and file-local semantic markup.OtherNo warnings★ 254↓ —Also in 1 other repo
- accessibility-audit-websitesTheGoat395/Codex-SkillsAudit semantic and keyboard accessibility.OtherNo warnings★ 133↓ —
- tourparcadei/Continuous-Claude-v3Friendly onboarding when users ask about capabilitiesOtherNo warnings★ 3.9K↓ —
- fixing-promptGulajavaMinistudio/awesome-copilot-idPrompt: Prompt Refinement and OptimizationOtherNo warnings★ 90↓ —
- clean-outputThomasMoreAI/legal-skills-openFür Clean-Output: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- domainrecht-borgheiThomasMoreAI/legal-skills-openBewertung von Domainstreitigkeiten und Ansprüchen aus Namensrecht (§ 12 BGB), Kennzeichenrecht und geschäftlicher Bezeichnung (§§ 5, 15 MarkenG) sowie Markenrecht (§ 14 MarkenG), inklusive DENIC-Dispute-Eintrag und Domain-Grabbing. Use when ein Streit über eine Internet-Domain (Registrierung, Nutzung, Übertragung, Löschung) zu beurteilen ist.OtherNo warnings★ 95↓ —
- blender-iterative-refinementifBars/blender-agent-studioRun an opt-in evidence-backed second pass on a complete Blender deliverable. Use when the user explicitly asks to critique, improve, repair, iterate, or apply a practice-makes-perfect loop; when a benchmark fixture explicitly requires retained before-and-after evidence; or when a completed candidate must be improved without regressing its existing technical or visible qualities.OtherNo warnings★ 94↓ —
- aligndevpaleo/alignfirstAct as the AlignFirst assistant: delegate the work on this project to agent sessions through aligndev.OtherNo warnings★ 86↓ —
- bmad-epsilon-v2alvin-reyes/better-agentic-ideA fixture skill with frontmatter and body problems.OtherNo warnings★ 85↓ —
- pm-business-modelkonglong87/superPMUse when: 需要设计商业模式画布、规划盈利模式、制定定价策略、设计收入模型 Do NOT use when: 商业模式已确定且已验证、仅需简单定价调整而非全面设计OtherNo warnings★ 84↓ —
- template-usageharness/harness-skillsTrack Harness template dependencies, usage, and adoption via MCP v2 tools. Find which pipelines or other templates reference a given template, analyze update impact, identify unused templates, and compare version adoption. Use when asked about template usage, template references, template dependencies, impact analysis before updating a template, finding unused templates, or tracking template adoption across projects. Trigger phrases: template usage, who uses template, template references, template dependencies, template impact, unused templates, template adoption. Do NOT use for creating or updating templates (use create-template instead).OtherNo warnings★ 125↓ —
- wechat-coauthorYiShu5/claude-skills协助意疏写「意疏的AI口袋」公众号文章。Claude 是协作者不是写手——voice 必须从意疏嘴里出来，AI 负责结构化、扩写、降 AI 味。触发：写公众号文章 / 帮我整理口述 / 有素材但想不清 / 这段 AI 味太重 / 看看有没有意疏味道 / 帮我把骨架写成文章。输出 Markdown，排版找 wechat-formatter，发布找 wechat-publisher。OtherNo warnings★ 131↓ —
- ressort-bmasThomasMoreAI/legal-skills-openFür Ressort-Heranführung BMAS: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- fangpian-brand-kitYiShu5/claude-skills方片新媒体（FANG PIAN / 方片，含方片母婴、方片时尚、方片家居等子品牌）官方品牌视觉规范与素材库。当需要为方片制作或修改任何视觉物料时使用——海报、小红书封面、PPT/幻灯片、公众号头图、数字人/短视频包装、头像、Banner、易拉宝、灯箱、水印、邀请函、培训课件等；也用于判断该用哪个 logo、配色、字体、IP 老虎姿势和部门海报模板，或需要统一品牌视觉、检查成品是否符合品牌规范时。目标是让所有 AI 产出的物料开箱即符合方片品牌识别，不再每次重做。OtherNo warnings★ 131↓ —
- mahnbescheidThomasMoreAI/legal-skills-openFür Mahnverfahren – Paragrafen 688 ff. ZPO: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- tweetclawXquik-dev/tweetclawTwitter bot guide for OpenClaw. Post, reply, search tweets, export followers & monitor accounts through Xquik. Not affiliated with X Corp.OtherNo warnings★ 95↓ —
- latchkeyimbue-ai/latchkeyInteract with third-party or self-hosted services (Slack, Google Workspace, Dropbox, GitHub, Linear, Coolify...) using their HTTP APIs on the user's behalf.OtherNo warnings★ 131↓ —
- preisangabenThomasMoreAI/legal-skills-openFür Preisangaben (PAngV 2022): ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- subskriptionspreis-eThomasMoreAI/legal-skills-openFür Verl-012 · Subskriptionspreis, Einführungspreis und Aktionspreis: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- monte-carlo-asset-healthmonte-carlo-data/mc-agent-toolkitCheck the health of a data table/asset using Monte Carlo. Activates on "how is table X", "check health of X", "is X healthy", "status of X", "check on X table", or any health/status question about a data asset.OtherNo warnings★ 93↓ —
- update-flag-targetingharness/harness-skillsChange how a Harness FME feature flag serves traffic in environments. Covers percentage rollout, individual targets, targeting rules (attribute/segment/flag-dependency), defaultTreatment, trafficAllocation, treatments, kill/restore, and copying or initializing a definition in an environment. Use when asked to ramp a flag, add rules/users, change allocation, kill/restore, or promote config. Not for creating flags (create-feature-flag), metadata like tags/owners/archive (manage-flag-lifecycle), segment keys (manage-segments), pipeline rollouts (fme-pipeline), or flag analysis (explain-flag). Trigger phrases: update targeting, ramp flag, percentage rollout, add rule, add users, kill flag, restore, copy config.OtherNo warnings★ 125↓ —
- monte-carlo-storage-cost-analysismonte-carlo-data/mc-agent-toolkitAnalyze a warehouse for stale, unused, or redundant tables via the analyze_storage_costs MCP tool. Classifies waste patterns and table categories, computes safety tiers, and handles category drill-downs and lineage follow-ups.OtherNo warnings★ 93↓ —
- ressort-bmjvThomasMoreAI/legal-skills-openFür Ressort-Heranführung BMJV: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- skill-verwalterThomasMoreAI/legal-skills-openFür Skill-Manager: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
voice-ai-realtime-agent
roedyrustam/vibes-plug
OtherUpdated yesterday
From the author
Ultra-low latency conversational voice AI (<300ms) with WebRTC / AI suara percakapan latensi ultra-rendah (<300ms) dengan WebRTC.
Install
npx skills add roedyrustam/vibes-plug --skill voice-ai-realtime-agent -a claude-code
Installs to .claude/skills/voice-ai-realtime-agent/ · 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
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance65
Maintenance100
Licence100
Adoption36
Files (1)
- SKILL.md