Skill catalog
1,895ai & agents agent skills synced from skills.sh, with their install counts. Read them here, or let your agent fetch the right one through the Graph-of-Skills MCP server.
Want your agent to use these? Set up Graph-of-Skills
or get a free key.
How these skills are sourced and what we check.
Cannot find one? Your agent can write a skill for your own library.
Have skills of your own? Install one on another machine.
A skill that comes from GitHub shows its npx skills add command on its page.
- parallel-mcp-setup parallel-web/parallel-agent-skills
Use when installing, configuring, or troubleshooting an authenticated Parallel Search MCP connection in Bifrost, including gateway-level search settings and downstream tool access.
1,044 installs - phoenix-evals github/awesome-copilot
Build and run evaluators for AI/LLM applications using Phoenix.
1,043 installs - agents-best-practices denissergeevitch/agents-best-practices
Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic,…
1,041 installs - bailian-model-recommend modelstudioai/skills
阿里云百炼模型选型与推荐。当用户需要"选择、推荐、对比"模型，或描述一个 AI 场景/功能需求（隐含需要帮其决策用哪个模型）时激活。核心意图是帮用户做决策， 不是单纯查资料。触发词：推荐模型、选哪个、哪个适合、对比、做一个XX、实现XX 功能、用什么模型好、XX场景方案。当用户同时涉及模型查询和模型选择时，优先 使用本 skill（本 skill 内部会读取模型数据完成推荐）。
1,041 installs - code-reviewer-to-walle walle.17usoft.com
No description provided.
1,041 installs - marketingskills-ai-agent-collection reason-machines/marketing-skills
Marketing skills collection for AI agents - CRO, copywriting, SEO, analytics, and growth engineering
1,041 installs - phoenix-tracing github/awesome-copilot
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.
1,041 installs - my-brain-is-full-crew reason-machines/trending-skills
A team of 10 AI agents that manage your Obsidian vault for knowledge, nutrition, and mental wellness using Claude Code
1,039 installs - postplus-shared postplusai/postplus-skills
Shared rules, routing preferences, execution boundaries, and workflow references for released PostPlus skills. Use this before any PostPlus skill that mentions shared public skill rules, research preferences, product-se…
1,039 installs - catalyst-basics catalystbyzoho/agent-skills
Core Catalyst project setup — directory structure, environments, CLI commands, and all Catalyst IDs (Project ID, ZAID, Table ID, Segment ID, Org ID). Trigger on 'start a Catalyst project', 'what is .catalystrc', 'where…
1,036 installs - gh-pr-description vercel/eve
No description provided.
1,036 installs - configuring-dbt-mcp-server dbt-labs/dbt-agent-skills
Generates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop…
1,034 installs - deepinit yeachan-heo/oh-my-claudecode
Deep codebase initialization with hierarchical AGENTS.md documentation
1,033 installs - btca-local davis7dotsh/better-context
Invoke this skill when the user says "use btca"
1,032 installs - omni-settings cheaper-inference/omniroute
Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.
1,032 installs - qiaomu-smart-search joeseesun/qiaomu-opencli-skills
基于 opencli 命令的智能搜索路由器。当用户想要搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill
1,032 installs - claude-peers-mcp reason-machines/trending-skills
Enable multiple Claude Code instances to discover each other and exchange messages in real-time via a local broker daemon and MCP server.
1,031 installs - omni-compression cheaper-inference/omniroute
Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60–90%.
1,031 installs - rag-engineer sickn33/agentic-awesome-skills
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.
1,030 installs - agentic-gateway alchemyplatform/skills
Wire Alchemy into application code without an API key, using the x402 or MPP gateway with wallet-based auth (SIWE/SIWS) and per-request payments (USDC via x402, or USDC/credit-card via MPP). Specialized app-integration…
1,029 installs - ce-pov everyinc/compound-engineering-plugin
Judge a supplied subject against the project's evidence and constraints. Use when assessing an external-adoption question, a holistic take on a document, or a supplied approach set. Use for an oracle panel to consult ot…
1,029 installs - pr-improver trailofbits/skills
Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branch touched. Reviews are performed by an installed P…
1,029 installs - onboard-context-matic github/awesome-copilot
Interactive onboarding tour for the context-matic MCP server. Walks the user through what the server does, shows all available APIs, lets them pick one to explore, explains it in their project language, demonstrates mod…
1,028 installs - jina-reader sundial-org/awesome-openclaw-skills
Web content extraction via Jina AI Reader API. Three modes: read (URL to markdown), search (web search + full content), ground (fact-checking). Extracts clean content without exposing server IP.
1,027 installs - subagent-driven-development jnmetacode/superpowers-zh
当在当前会话中执行包含独立任务的实现计划时使用
1,026 installs - catalyst-sdk catalystbyzoho/agent-skills
Catalyst SDKs — initialization patterns, service access, and method reference for Node.js, Web (browser), Python, Java, Android, iOS, and Flutter. Trigger on 'SDK', 'zcatalyst-sdk-node', 'Node.js SDK', 'Web SDK', 'Pytho…
1,025 installs - copilotkit copilotkit/skills
Use when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.
1,025 installs - fit-scorer aaron-he-zhu/aaron-marketing-skills
Use when the user asks to "score this influencer", "rank these creators for our campaign", or "tell me which influencer is the best fit"; produces the typed STAR Suitability (S) read plus a separately labeled campaign-f…
1,025 installs - shopify-app-recommendations nexscope-ai/ecommerce-skills
App stack advisor — essential apps by business stage, cost optimization, performance impact analysis
1,025 installs - executing-plans jnmetacode/superpowers-zh
当你要在当前会话里亲自担任实现者执行一份实现计划时使用——你的人类伙伴选择了内联执行，或者没有可用的子智能体工具
1,021 installs - catalyst-zoho-mcp catalystbyzoho/agent-skills
Catalyst Zoho MCP — manage Catalyst infrastructure (tables, buckets, cache) via CatalystbyZoho_* MCP tools using natural language. Trigger on 'Zoho MCP', 'MCP tools', 'catalyst MCP', 'CatalystbyZoho', 'create table with…
1,020 installs - cs-decide codestable/codestable
No description provided.
1,020 installs - yaml vercel-labs/json-render
YAML wire format for json-render with streaming parser, prompt generation, and AI SDK transform. Use when working with @json-render/yaml, YAML-based spec streaming, yaml-spec/yaml-edit fences, or YAML prompt generation.
1,020 installs - claude-code-history-files-finder daymade/claude-code-skills
Searches and recovers Claude Code JSONL history across all active config homes and archives registered in ~/.claude/history-sources.json. Use --all-projects when the project is unknown, --codex to include Codex rollout…
1,019 installs - speakturbo-tts emzod/speak-turbo
Give your agent the ability to speak to you real-time. Talk to your Claude! Ultra-fast TTS, text-to-speech, voice synthesis, audio output with ~90ms latency. 8 built-in voices for instant voice responses. For voice clon…
1,019 installs - creator-registry aaron-he-zhu/aaron-marketing-skills
Use when the user asks "what did we pay this creator last time" or to "update the creator roster"; curates creator identity, rate, rights, exclusivity, compliance-event, and performance facts through the append-only cre…
1,016 installs - social-quality-auditor aaron-he-zhu/aaron-marketing-skills
Use when the user asks to "audit our social presence" or "is this batch safe to publish"; runs either the typed ECHO asset gate or a separate program-maturity profile, with channel-truth, claim, disclosure, manipulation…
1,016 installs - spritecook-workflow-essentials spritecook/skills
Shared workflow rules for SpriteCook. Use together with SpriteCook generation, UI-kit building, animation, import, background-removal, and asset-organization workflows for credits, downloads, asset manifests, safe auth…
1,016 installs - use-arc circlefin/skills
Provide instructions on how to build with Arc, Circle's blockchain where USDC is the native gas token. Arc offers key advantages: USDC as gas (no other native token needed), stable and predictable transaction fees, and…
1,015 installs - cmux-cua manaflow-ai/cmux
Use only after the user explicitly asks for cmux Computer Use through the cmux-cua skill: drive real macOS apps from a cmux agent session via the bundled engine (accessibility tree + screenshots, click/type/scroll/drag,…
1,014 installs - ralph-loop cursor/plugins
Start a Ralph Loop for iterative self-referential development. Use when the user asks to run a ralph loop, start an iterative loop, or wants repeated autonomous iteration on a task until completion.
1,014 installs - channel-registry aaron-he-zhu/aaron-marketing-skills
Use when the user asks to register/query a social channel, record channel state, cadence, governance, voice adaptation, UGC permission, or advocacy facts; curates them through the append-only channels event stream and d…
1,012 installs - phoenix-cli github/awesome-copilot
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL A…
1,012 installs - autopilot yeachan-heo/oh-my-claudecode
Full autonomous execution from idea to working code
1,011 installs - memory-ci-capture basicmachines-co/basic-memory
Synthesize GitHub delivery context into a concise Basic Memory project update. Use in CI after `bm ci collect` prepares a ProjectUpdateContext; return only structured AgentSynthesis JSON for `bm ci publish`.
1,011 installs - config-codex-cli cheaper-inference/omniroute
Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use OmniRoute as an OpenAI-compatible backend. Detects OS and shell, writes config.toml and 7 named profiles, sets…
1,010 installs - prompt-caching-strategy affaan-m/ecc
Optimize LLM prompt caching hit rate to reduce API costs and improve latency. Analyzes prompt structure, identifies cacheable vs non-cacheable content, and recommends restructuring to maximize cache reuse. TRIGGER when:…
1,010 installs - senior-prompt-engineer davila7/claude-code-templates
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI…
1,010 installs - cli-mcp cheaper-inference/omniroute
Inspect the MCP server status, list registered tools and scopes, run tool invocations, and manage MCP audit logs from the CLI.
1,009 installs - deep-interview yeachan-heo/oh-my-claudecode
Socratic deep interview with mathematical ambiguity gating before explicit execution approval
1,009 installs