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.
47,307 skills from 2,272 repositories · updated 4 hours ago
10,066 skills
- firebase-app-platformBagelHole/DevOps-Security-Agent-SkillsBuild and operate apps on Firebase using Auth, Firestore, Cloud Functions, and Hosting. Use when building mobile/web backends with managed services, real-time data sync, or serverless APIs.OtherNo warnings★ 1.2K↓ —
- meeting-request-parsingcxcscmu/SkillLearnBenchParse meeting request emails from JSON format and extract duration and time constraintsOtherNo warnings★ 91↓ —
- ressort-aaThomasMoreAI/legal-skills-openFür Ressort-Heranführung AA: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- web-fetchrunxhq/runxFetch and extract one public web source, optionally restrict its hosts, and return the content by digest with full provenance.OtherNo warnings★ 104↓ —
- explain-flagharness/harness-skillsExplain a single FME feature flag in plain language: purpose, default rule, and per-environment targeting state, flagging inconsistencies across environments inline. A quick-lookup/explain capability, not a search across many flags - disambiguates when the name/key given is ambiguous. Doesn't create, kill, or modify anything - see update-flag-targeting for targeting changes, manage-flag-lifecycle for metadata/archive, discover-feature-flags for multi-flag questions, manage-experiments for experiments. Trigger phrases: what does this flag do, explain this flag, how is X configured, is X on in prod, what's targeted for X.OtherNo warnings★ 125↓ —
- schreibcanvasThomasMoreAI/legal-skills-openFür Schreib-Canvas: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- chinese-rhyme-moderncxcscmu/SkillLearnBenchModern Mandarin rhyme groups for classical Chinese poetry composition, mapping finals to rhyme categories.OtherNo warnings★ 91↓ —
- word-stil-tonThomasMoreAI/legal-skills-openFür Word: Erstprüfung, Rollenklärung und Mandatsziel: 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↓ —
- piaochuang-chuanghu-zhuangxiu-zhinanzx029w/zhuangxiu-skills飘窗窗户装修指南专用 Skill。覆盖飘窗窗帘、窗套与窗台、落地窗与封窗、安全与护栏、飘窗利用与改造等全流程，倒序整合西安装修课堂会员版知识库精华，帮用户装出更省心、不踩坑的飘窗窗户装修。OtherNo warnings★ 86↓ —
- menchuang-fengchuang-bikeng-zhinanzx029w/zhuangxiu-skills门窗封窗避坑指南专用 Skill。覆盖窗户选型、入户门与室内门、封窗与落地窗、窗帘与遮挡、安装密封与五金、门窗选型综合等全流程，倒序整合西安装修课堂会员版知识库精华，帮用户装出更省心、不踩坑的门窗封窗避坑。OtherNo warnings★ 86↓ —
- kaltstart-3ThomasMoreAI/legal-skills-openFür Deal-Kaltstart: routet Rolle, Frist, Unterlagen und Fachschritt; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Mittelstands-Corporate/M&A.OtherNo warnings★ 95↓ —
- 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↓ —
- incident-managementBagelHole/DevOps-Security-Agent-SkillsImplement incident management processes and escalation procedures. Configure on-call schedules and post-incident reviews. Use when managing production incidents.OtherNo warnings★ 1.2K↓ —
- 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↓ —
- kubesphere-openkruisekubesphere/kubesphereKubeSphere OpenKruise management Skill. Use when user asks to install or enable OpenKruise, check OpenKruise status, view kruise pods/logs/CRDs, create or update SidecarSet, manage sidecar injection, create or update CloneSet, perform in-place update or batch rollout, uninstall or remove OpenKruise, or troubleshoot Kruise Pod, CRD, and webhook issues in KubeSphere.OtherNo warnings★ 17.1K↓ —
- d3-color-legendcxcscmu/SkillLearnBenchAdd a categorical color legend to a D3 chart using colored rectangles or circles with text labels, supporting both SVG-inline and HTML overlay styles.OtherNo warnings★ 91↓ —
- vendor-dueThomasMoreAI/legal-skills-openFür Vendor Due Diligence VDD: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- ecom-pricingkangise/ecommerce-ai-skillsSet competitive prices and model profitability. Use for Buy Box pricing analysis, profit margin calculation, breakeven analysis, or multi-marketplace pricing strategy.OtherNo warnings★ 108↓ —
- ecom-listingkangise/ecommerce-ai-skillsGenerate and optimize Amazon/Shopify/TikTok Shop product listings. Use when creating titles, bullet points, descriptions, A+ Content, Search Terms, or multi-language listings.OtherNo warnings★ 108↓ —
- typed-routesJoviDeCroock/prachtAdd or maintain pracht typed routes: run typegen, adopt route-id based links and navigation, and replace hard-coded hrefs with generated helpers. Use for "add typed routes", "fix typed links", "replace hard-coded hrefs", "run typegen".OtherNo warnings★ 105↓ —
- sign-receiptrunxhq/runxBind an off-runtime action claim to opaque evidence locators in a signed Runx receipt without pretending Runx verified the external action.OtherNo warnings★ 104↓ —
- d3-fundamentalscxcscmu/SkillLearnBenchEssential D3.js v6 concepts including selections, scales, SVG basics, and data binding for building interactive visualizationsOtherNo warnings★ 91↓ —
- netcdf-processingcxcscmu/SkillLearnBenchReading, processing, and analyzing NetCDF output from lake simulation modelsOtherNo warnings★ 91↓ —
explain-flag
harness/harness-skills
OtherUpdated 16 hours ago
From the author
Explain a single FME feature flag in plain language: purpose, default rule, and per-environment targeting state, flagging inconsistencies across environments inline. A quick-lookup/explain capability, not a search across many flags - disambiguates when the name/key given is ambiguous. Doesn't create, kill, or modify anything - see update-flag-targeting for targeting changes, manage-flag-lifecycle for metadata/archive, discover-feature-flags for multi-flag questions, manage-experiments for experiments. Trigger phrases: what does this flag do, explain this flag, how is X configured, is X on in prod, what's targeted for X.
Install
npx skills add harness/harness-skills --skill explain-flag -a claude-code
Installs to .claude/skills/explain-flag/ · 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: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance65
Maintenance100
Licence100
Adoption36
Files (1)
- SKILL.md