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.
48,622 skills from 2,355 repositories · updated 16 hours ago
10,262 skills
- philips-hueAnil-matcha/awesome-muse-connectorsControl Philips Hue lights locally: list lights and rooms, set brightness/color, activate scenes, read sensors. Trigger phrases: philips hue, hue lights, my lights.OtherNo warnings★ 1.4K↓ —
- fact-checkernaveedharri/benai-skillsSystematic fact verification and misinformation identification using evidence-based analysis. Use when: verifying claims, checking facts, identifying misinformation, evaluating source credibility, or when user asks to "fact check", "verify", "is this true", or mentions claims that need validation.OtherNo warnings★ 78↓ —Also in 2 other repos
- Autotask QuotesWYRE-AI/msp-claude-pluginsAutotask quote structure and line items - quote item types (product, service, service bundle, labor, expense, shipping), the mutually-exclusive catalog reference rules, and the three discount mechanisms (unit, line, percentage) used to build customer proposals.OtherNo warnings★ 52↓ —
- ca-checkpointarbiterForge/codeArbiterPeriodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.OtherNo warnings★ 149↓ —
- msvc-clOutlineDriven/outline-driven-developmentUse when building C or C++ on Windows with cl.exe or clang-cl: GCC-to-MSVC flag translation, /MT versus /MD, PDB output, or an LNK error. Not for MinGW cross builds from Linux: use cross-gcc.OtherNo warnings★ 56↓ —
- history-recallOutlineDriven/outline-driven-developmentUse when a user requests the reasoning behind one matched session by query or handle. Not for peer transfer: use history-sync. Not for store registration: use history-source-registry.OtherNo warnings★ 56↓ —
- matlab-register-point-cloudsmatlab/matlab-agentic-toolkitRegister 3-D point clouds using ICP, NDT, LOAM, FGR, phase correlation, and CPD algorithms. Use when registering or aligning 3-D point clouds, choosing a registration algorithm, tuning registration parameters, preprocessing point clouds for registration or combining point clouds after registration.OtherNo warnings★ 1.2K↓ —
- decision-lifecyclearbiterForge/codeArbiterRecord user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.OtherNo warnings★ 149↓ —
- openrouterAnil-matcha/awesome-muse-connectorsBrowse OpenRouter's model catalog and check your key usage. Trigger phrases: openrouter, model prices, openrouter key.OtherNo warnings★ 1.4K↓ —
- dailygaliprandi/job-seekerPeriodic routine that runs news, cleans up inbox and applies if there's no recent activity. Designed to run 1-2 times per day.OtherNo warnings★ 64↓ —
- typeformAnil-matcha/awesome-muse-connectorsWork with Typeform: list forms and responses, create forms, and (with confirmation) manage response webhooks. Trigger phrases: typeform, form responses, typeform webhook, typeform forms, create form.OtherNo warnings★ 1.4K↓ —
- binutilsOutlineDriven/outline-driven-developmentUse when building static archives with ar, stripping or converting binaries, mapping crash addresses with addr2line, or demangling C++ symbols. Not for ELF analysis: use elf-inspection.OtherNo warnings★ 56↓ —
- telegramAnil-matcha/awesome-muse-connectorsSend and read Telegram messages through your bot: bot info, send messages, read updates. Trigger phrases: telegram, telegram bot, send a telegram message.OtherNo warnings★ 1.4K↓ —
- 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
- ca-tribunalarbiterForge/codeArbiterRun an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.OtherNo warnings★ 149↓ —
- using-syncJanYork/llm-wiki-cliUse when an Agent needs to synchronize LWC Wiki stores across SSH hosts, resume or abort an interrupted Sync session, or resolve semantic Sync conflicts safely.OtherNo warnings★ 70↓ —Also in 3 other repos
- principlesOutlineDriven/outline-driven-developmentUse when a request names a working principle (subtract before you add, idempotent operations, never block on the human) or asks which principle applies. Not for running a repair: use strike-the-root.OtherNo warnings★ 56↓ —
- feedback-sweepOutlineDriven/outline-driven-developmentUse when asked to /feedback-sweep [setup|reconfigure] [mode:non-interactive]. Not for pattern discovery: use feedback-pattern-sweep.OtherNo warnings★ 56↓ —
- backlink-guardzhuyansen/backlink-guardCheck a link source before submitting a site to it, verify a listing after it goes live, and audit a site's own backlink profile for patterns that read as link spam. Use when the user wants to submit a site, tool or repository to directories, awesome lists or guest-post sites, asks whether a directory or link source is safe or worth it, wants to check whether a backlink is followed, asks for a backlink audit or spam check after a Google spam update, asks which sites link to their competitors and not to them, which sites Google's AI Overviews cite for their keywords, or what ChatGPT, Perplexity, Claude and Gemini answer, search for and cite when asked for what they make. Runs the backlink-guard command line; a GOANYAPI_API_KEY and a GLASSER_API_KEY (or an AISA_API_KEY) add the paid signals.OtherNo warnings★ 62↓ —
- lov-media-verificationlovstudio/skills使用 ffprobe 验证已下载视频的可读性、时长、分辨率、编码、音轨、字幕和剧集完整性；适用于“检查下载是否完整”、"verify the downloaded media"，输出结构化验收报告。OtherNo warnings★ 72↓ —
- HubSpot TicketsWYRE-AI/msp-claude-pluginsHubSpot support tickets: core fields, default pipeline stages, priority levels, MSP ticket categories, SLA timestamp properties, and associating tickets with contacts, companies, and deals.OtherNo warnings★ 52↓ —
- using-bookJanYork/llm-wiki-cliUse to import, prepare, read, or synthesize a complete supported book in verified source order. Skip ordinary document lookup.OtherNo warnings★ 70↓ —Also in 3 other repos
- cordova-to-capacitorCap-go/capgo-skillsMigrates an Apache Cordova, PhoneGap, or Ionic-Cordova app to Capacitor. Use when the project has config.xml, a platforms/ or plugins/ folder, cordova-* or phonegap-* dependencies, @awesome-cordova-plugins or @ionic-native wrappers, deviceready listeners, or cordova.plugins.* calls, and the user wants Capacitor native projects, Capacitor/Capgo plugin replacements, config.xml preference migration, and preserved localStorage/IndexedDB data (iosScheme/androidScheme). Covers keeping Cordova plugins temporarily, Capacitor 9 making the Cordova runtime optional (CapacitorCordova only bundled when a Cordova plugin is installed), skipped incompatible plugins, and removing Cordova afterwards. Do not use for porting a single Cordova plugin's native source into a Capacitor plugin, Capacitor major upgrades (capacitor-app-upgrades), Appflow/cordova-plugin-ionic live updates (ionic-appflow-migration), or non-Cordova web apps (webapp-to-capacitor, framework-to-capacitor).OtherNo warnings★ 75↓ —Also in 1 other repo
- printfulAnil-matcha/awesome-muse-connectorsRead Printful products and orders, create orders and mockups. Trigger phrases: printful, print on demand, mockup, fulfillment, store orders.OtherNo warnings★ 1.4K↓ —