The catalog
611,178 rows, by stacks then stars
JinPLu/Teamwork/plugins/teamwork-skill/skills/grill-me Skill
12★ repoEvidence-first skills for Codex, Cursor, and Claude Code: research, debugging, planning, execution, review, and goal loops.
keithbinkly/dbt-meta-context/skills/authoring-meta-context Skill
12★ repoAuthors and extracts dbt MetricFlow meta context — structured YAML `meta:` blocks that encode business knowledge (thresholds, investigation paths, SLAs, relationships) alongside metric definitions so AI agents answer analytical questions accurately. Use when user asks about context cards, meta context blocks, dbt metric meta blocks, semantic layer context, distilling runbooks into YAML, authoring meta context, validating meta context, or improving AI agent analytical accuracy on dbt metrics.
aiatelie/ai-atelie/.claude/skills/canvas-sync Skill
12★ repoKeep the canvas surface coherent across its three places — the canonical starter at `mcp/starters/DesignCanvas.jsx`, the byte-identical demo copy at `web/projects/demo/design-canvas.jsx`, and the host-side wiring in `web/src/lib/tweakBridge.ts` plus `mcp/CANVAS_PROTOCOL.md`. Use whenever the diff touches any of those files, or when the user says "fix the canvas", "update DesignCanvas", "tweak the design canvas", "the canvas isn't working in new projects", or anything similar. Without this rule, fixes land in one place and silently miss the other — the demo project tests stale code, or new projects get content that doesn't match what's been verified.
TencentCloudBase/mp-skills/skills/wxa-ai-mode-dev Skill
no license12★ repo微信小程序 AI 开发模式(beta)完整开发指南。当开发者需要将小程序改造为 AI 开发模式、封装 SKILL、编写原子接口/原子组件、编写 SKILL.md 或 mcp.json 时触发。覆盖接入流程、项目结构、Schema 设计、content 文本写法、组件约束、最佳实践、常见反例的全部规范。
ketthub/zotero-skill Skill
no license12★Query your local Zotero library. Supports keyword, fulltext, author, collection, tag, DOI, and recent-additions search. Trigger: /zotero, "my papers", "Zotero", "find paper", "references", "citations". After installation, verify DEFAULT_DB path in scripts/zotero-search.py points to your zotero.sqlite.
takaakit/superpowers-uml/plugins/superpowers-uml/skills/brainstorming Skill
no license12★ repoSuperpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling.
S3YED/appie-kit/packages/cognify/integrations/hermes Skill
12★ repoUse when you need durable memory over documents — ingest files/notes into a typed knowledge graph and recall facts with their relationships. Build a knowledge base from PDFs, markdown, or pasted text, then ask grounded questions.
fastrevmd-lab/fwskillsshare/skills/cis-controls-ngfw-compliance Skill
12★ repoMap firewall controls, evidence, and gaps to CIS Controls v8/v8.1 safeguards. Use when assessing IG1/IG2/IG3, inventory, secure configuration, access, logging, threat prevention, or safeguard IDs such as 4.2 and 13.3. Excludes product-specific CIS Benchmarks.
pekral/cursor-rules/skills/analyze-problem Skill
12★ repoUse when structured problem analysis for debugging, root cause identification, and breaking down complex issues before proposing solutions
Short video analysis tool skills
shuhaolin63-hash/short_video_analysis_tool-skills Skill
12★抖音/TikTok/B站短视频全链路解析工具
TashanGKD/cognitive-os/.cursor/skills/cognitive-ask Skill
12★ repo基于用户自己的认知文档回答问题,严格引用来源,标注置信度,暴露矛盾,识别知识空白。触发词:「基于我的文档」「根据我的想法」「我之前怎么想的」「我说过什么关于X」「我对X的看法是什么」「帮我回忆」「我的认知里怎么说」「我的框架里有没有」「从我的角度」「我如何看待」。
KoukkuAi/call-matt/antigravity/.agents/skills/call-matt Skill
12★ repoOrchestrator and router for Matt Pocock's open-source agent skills (github.com/mattpocock/skills). Use whenever the user invokes /call-matt, asks "which skill should I use", feels stuck about what to do next in a coding project, or describes a situation that maps to one of the toolkit's skills (vague plan, messy backlog, buggy code, bloated context, ball-of-mud architecture) without naming a specific skill. Analyzes the project's current state, recommends the right skill from the toolkit, explains why, and triggers it.
zvec-ai/zvec-agent-skills/skills/zvec Skill
12★ repoZvec vector database development assistant. Use this skill when users need to develop vector search applications based on zvec, build RAG systems, implement semantic search, or handle vector data storage and querying. Suitable for Python and Node.js development environments, providing complete technical guidance from basic concepts to advanced usage. Proactively use this skill when users mention vector databases, similarity search, embedding storage, HNSW/IVF indexes, hybrid search, multi-vector queries, or zvec API usage.
kissgyorgy/coding-agents/skills/ai-sdk Skill
no license12★ repoAnswer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".
The same file is in 5 other repositories
eugenepyvovarov/mcpbundler-agent-skills-marketplace/ab-test-setup Skill
12★ repoWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
Galius5136/databricks-spark-3.5-cert-prep/skills/apache-spark Skill
12★ repoKnowledge base from "Learning Spark, 2nd Edition" by Damji, Wenig, Das & Lee. Use when working with Apache Spark / PySpark, preparing for the Databricks Certified Associate Developer for Apache Spark exam, or applying the authors' frameworks for Spark architecture, DataFrame API, Spark SQL, Structured Streaming, tuning, and Datasets.
EmblemCompany/Agent-skills/skills/emblem-ai-agent-wallet Skill
12★ repoConnect to EmblemVault and manage wallet-aware workflows via EmblemAI with review-first, operator-controlled actions. Supports Solana, Ethereum, Base, BSC, Polygon, Hedera, and Bitcoin. Also use when the user needs Emblem's auth model explained: one browser auth flow can log a user in with wallets, email/password, or social sign-in, while agent mode can auto-provision a profile-scoped wallet with no manual setup.
The same file is in 1 other repository
JuneYaooo/launchfit-ai Skill
no license12★Use when reviewing cross-border product launch readiness, target-market benchmarks, marketplace/category admission, packaging or claims, documents, brand authorization, certificates, logistics, or remediation for products moving from an origin country to one or more destination markets.
Orkas-AI/Orkas-Awesome-AgentSkills/creation/skills/content-writer Skill
12★ repoCurated Orkas agents and skills for education, product development, content creation, data analysis, office automation, and e-commerce workflows.
The same file is in 1 other repository
gandli/weread-skills/skills/weread Skill
no license12★ repo微信读书助手 — 搜索书籍、管理书架、查看笔记划线、浏览书评、阅读统计、发现推荐好书
The same file is in 6 other repositories
yike-gunshi/forge-skills Skill
12★Forge 工作流总入口。只读检测项目状态,推荐下一步该用哪个 skill,自己不干活。触发方式:用户说"forge"、"下一步"、"接下来做什么"。
rudrankriyam/App-Intents-Agent-Skill/app-intents-expert-skill Skill
12★ repoExpert App Intents guidance for building Siri, Shortcuts, Spotlight, Apple Intelligence, and interactive snippet integrations on iOS 26+. Use when implementing AppIntent, AppEntity, AppEnum, EntityQuery, AppShortcutsProvider, SnippetIntent, SiriTipView, IndexedEntity, or when making an app work with Siri, Shortcuts, Spotlight, Apple Intelligence, Visual Intelligence, Action Button, or Apple Pencil. Also use when asked about App Intents architecture, intent-driven development, or migrating from SiriKit.
runkids/my-skills/agent-browser/agent-browser Skill
no license12★ repoBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
The same file is in 1 other repository
southleft/skills-for-figma/skills/analyze-component-set-figma Skill
12★ repoAnalyze a Figma COMPONENT_SET as a state machine for code generation — extract variant axes (state/size/etc.), map state variants to CSS pseudo-classes (hover→:hover, focus→:focus-visible, disabled→:disabled, error→[aria-invalid]), and compute per-variant visual diffs (only what changes per state). Use when generating an interactive component from a Figma variant set — triggers: 'analyze this component set', 'turn these variants into CSS states', 'generate a button/input/checkbox from Figma variants', 'what changes between the hover and default state', 'map Figma variants to component props', 'extract the state machine for this component'. Resolves bound variables to token names. NOT covered by the native MCP's get_design_context/get_metadata, which don't give you a variant-axis→CSS-state machine.
MSiccDev/ai-context-kit/skills/create-agents-md Skill
12★ repoCreate concise, repository-specific AGENTS.md files with operational contract, precedence rules, and drift-control guidance.
instantX-research/skills/skills/brand-quill Skill
12★ repoBrand Quill — Rewrites everyday text into the aesthetic voice of iconic brands. 13 built-in styles: MUJI (restraint), Apple (minimal confidence), Aesop (literary sensory), Patagonia (honest activism), Diptyque (Parisian narrative), Snow Peak (nature craft), IKEA (everyday warmth), Nike (action empowerment), Suntory (liquid philosophy), Hobonichi (gentle everyday), Hermès (poetic craft), Rolls-Royce (facts as poetry), Guinness (patience and substance). Supports mood control (positive/negative/neutral) to shape emotional direction. Supports ZH/EN/JA multilingual output. Specify scene: social media, Vlog, product, bio, slogan. Use when asked to "rewrite copy", "write in X style", "文案改写", "风格文案", "帮我写个无印风的文案", "make this sound like Apple", or any copywriting style request.
pattern-ai-labs/built-with-agentcall/meeting-presenter Skill
12★ repoJoin a Google Meet, Zoom, or Teams meeting as an AI presenter and DELIVER a presentation — slides on the bot's camera, narrated aloud, auto-advancing. Hand it a DOCUMENT (PDF, PowerPoint, or Word) or a TOPIC. A PowerPoint (already a deck) is shown as-is; a Word/PDF document is turned into a meaningful deck the agent authors from the source's text AND figures. Cross-platform and self-contained. Use when the user wants their agent to present something in a live meeting.
oubakiou/mdxg-redline/skills/md-review Skill
12★ repoRun the standard markdown review loop end-to-end with the mdxg-redline CLI: send a markdown document to a human reviewer, wait (via Bash polling) for the feedback.json they export, then apply their location-aware inline comments back into the markdown and revise it. Always use this skill when the user wants human-in-the-loop review of markdown with structured JSON feedback — e.g. "send this spec out for review", "get a human to review this before we move on", "have someone redline this doc", "leave inline comments on this draft". Even without an explicit file name or tool name, actively consider this skill for any request involving a human review round, human-in-the-loop checking, redlining, or structured reviewer feedback on a document. The same workflow applies when the user launches it as a slash command like `/md-review <path>`.
di37/EvalSurfer/skills/eval-surfer Skill
12★ repoDrive AI application evaluations using the EvalSurfer skill-first workflow. Use when creating AI eval rubrics, reviewing RAG outputs, checking agent tool use, assessing safety, or calculating operational metrics like latency, TTFT, inter-token latency, throughput (tokens per second), P99 tail latency, cost, cost per million tokens, token efficiency, failure rate, and latency under load.
luka2chat/geo-skills Skill
12★Best practices for Generative Engine Optimization (GEO) - optimizing content for AI search engines and LLM-based answer engines
jamarpl21/prawo-pl-eli/plugins/prawo-eu-eurlex/skills/prawo-eu-eurlex Skill
12★ repoPrawo polskie i UE z oficjalnych źródeł (API ELI Sejmu + CELLAR/EUR-Lex) — agent skills dla Claude Code i OpenAI Codex. Teksty jednolite, pojedyncze artykuły, nowelizacje, CELEX.
nonlooped/roblox-suite/.opencode/skills/release Skill
12★ repoPublish a Roblox Suite release end-to-end: clean the tree, polish files, choose a semver bump, split work into conventional commits, update CHANGELOG, tag, create a GitHub Release in the project format, and push. Invoke when ready to ship accumulated changes (e.g. "release", "ship it", "publish vX.Y.Z", "cut a release").
AstravueOrg/astravue-mcp-server/com.astravue/astravue-mcp MCP server
12★ repoManage projects, tasks, time tracking, and team collaboration through natural language.
Deltologic/datadoe-mcp/com.datadoe/amazon-seller-mcp MCP server
12★ repoHosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
knitli/codeweaver/com.knitli/codeweaver MCP server
12★ repoSemantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.
covariance-network/productclank-mcp-server/com.productclank/productclank MCP server
12★ repoBoost posts and launch community growth campaigns from your AI assistant. OAuth, credit-billed.
mericcintosun/AvaKit/dev.avakit/avalanche MCP server
12★ repoAct on Avalanche from your agent: scaffold a dapp, deploy a contract, mint, and read chain state.
mazamaka/llm-latency-tracker/dev.llmlatency/llm-latency-tracker MCP server
12★ repoMeasured latency & uptime for AI inference APIs, by region. Exposes a get_ai_api_latency tool.
MCPfinder - MCP Server Discovery
mcpfinder/mcpfinder/dev.mcpfinder/server MCP server
12★ repoYour AI discovers and installs MCP servers across Official Registry, Glama, and Smithery.
joshsymonds/savecraft.gg/gg.savecraft/savecraft MCP server
12★ repoSavecraft serves real save game data and expert game knowledge to AI assistants.
balldontlie-api/mcp/io.balldontlie/mcp MCP server
12★ repoProvides access to live sports data and analytics from BALLDONTLIE: The Sports API
formio/uag/io.form/uag MCP server
12★ repoThe Universal Agent Gateway (UAG) enables in-process agentic automation using Form.io.
Cavinooo/claude-find/io.github.Cavinooo/claude-find MCP server
12★ repoPull Deep Memory from across your Claude Code Sessions — when you need it.
IngTian/witness/io.github.IngTian/witness MCP server
12★ repoSecond brain for Claude Code & OpenCode: distills how your patterns and knowledge evolve over time.
IvanBBaev/servicenow-mcp-ai/io.github.IvanBBaev/servicenow-mcp-ai MCP server
12★ repoServiceNow MCP server — 67 tools over the full REST surface, every auth method, flows, diagrams.
Izyuusya/japan-data-mcp/io.github.Izyuusya/japan-data-mcp MCP server
12★ repo日本の公的データ(統計・法人・不動産)にAIからアクセスするMCPサーバー。e-Stat統計API・法人番号Web-API・不動産情報ライブラリAPIの3API統合。全国約1,700市区町村対応。
L337-org/docker-mcp/io.github.L337-org/docker-mcp-server MCP server
12★ repoManage Docker (containers, images, Compose, Swarm, registries) via the Docker SDK and CLI.
LaZZy0v0/tijori-finance-mcp/io.github.LaZZy0v0/tijori-finance MCP server
12★ repoIndian equity research MCP — 5,000+ NSE/BSE stocks, financials, KPIs, and concall transcripts.
LeassTaTT/servicenow-mcp-ai/io.github.LeassTaTT/servicenow-mcp-ai MCP server
12★ repoServiceNow MCP server — 67 tools over the full REST surface, every auth method, flows, diagrams.
Oortonaut/mcacp/io.github.Oortonaut/mcacp MCP server
12★ repoMCP-to-ACP bridge — let any MCP client drive ACP coding agents
OrygnsCode/Omnicord/io.github.OrygnsCode/omnicord MCP server
12★ repoYour AI runs your Discord server: chat, moderation, admin, even building it all from one brief.
PrinceGabriel-lgtm/freshcontext-mcp/io.github.PrinceGabriel-lgtm/freshcontext MCP server
12★ repoFreshness-aware AI retrieval with 21 MCP tools for timestamped, decay-ranked live signals.
RonieNeubauer/cli2mcp/io.github.RonieNeubauer/cli2mcp MCP server
12★ repoWrap any CLI as a Model Context Protocol server - schema auto-inferred from --help.
SPerekrestova/interactive-leetcode-mcp/io.github.SPerekrestova/interactive-leetcode-mcp MCP server
12★ repoInteractive LeetCode MCP server with authorization and solution submission capabilities
STiFLeR7/memex/io.github.STiFLeR7/memex MCP server
12★ repoTemporal knowledge graph of your codebase (Graphiti + Neo4j), served to AI agents via MCP.
VictoriaMetrics-Community/mcp-victoriatraces/io.github.VictoriaMetrics-Community/mcp-victoriatraces MCP server
12★ repoMCP Server for VictoriaTraces. Provides integration with VictoriaTraces API and documentation
aibtcdev/aibtc-mcp-server/io.github.aibtcdev/mcp-server MCP server
no license12★ repoBitcoin-native MCP server for AI agents: BTC/STX wallets, DeFi yield, sBTC peg, NFTs, x402 payments.
aidongise-cell/prism-scanner/io.github.aidongise-cell/prism-scanner MCP server
12★ repoSecurity scanner for AI Agent skills, plugins, and MCP servers with A-F grading.
akutishevsky/monobank-mcp-server/io.github.akutishevsky/monobank-mcp-server MCP server
12★ repoMCP server for Monobank API — currency rates, client info, and account statements
alex-jordan547/renforge-mcp/io.github.alex-jordan547/renforge MCP server
12★ repoInspect, drive and debug a running Ren'Py game: state, screenshots, guarded clicks, saves, builds.