Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Create and configure hookify rules — markdown files with YAML frontmatter that match bash, file, prompt, or stop events by regex or conditions and show warn/block messages to the agent. Use when creating a hookify rule, writing hook rule syntax, configuring hookify, or adding pattern guardrails such as blocking dangerous commands, .env edits, or debug code.
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, Hermes Agent, OpenCode, or OpenClaw, apply an author's frameworks while working, or build a reusable knowledge base from a file.
Design a SaaS product's MCP server as a product surface AI agents operate - sizing the build investment, curating a 5-15 workflow-tool agent surface instead of mirroring API endpoints, MCP Apps interactive UI, named write-tool safety patterns (scoped credentials, read-only lockdown, human-in-the-loop approval, risk-tiered server-side gates, dry-run preflight, idempotency and spend caps), remote hosting with OAuth 2.1, versioning the tool surface, MCP registry discoverability, and measuring agent adoption. Use whenever the user mentions MCP, Model Context Protocol, an agent-facing tool surface, exposing a product to AI agents or coding assistants, or MCP write-tool safety - even if they never say "MCP server". Design layer only - code-generation MCP builder skills scaffold what this specifies.
Develop a Base44 app remotely from your own coding agent (Claude Code, claude.ai, or any MCP client) by connecting it to the Base44 sandbox. Cloud agents connect over MCP; local agents can connect over MCP or drive the same sandbox with the `base44 sandbox` CLI subcommands (the CLI uses shorter names — e.g. read_file is `sandbox read`, list_directory is `sandbox ls`, run_command is `sandbox run`). Covers connecting/ authenticating, the available sandbox tools (run_command, read_file, write_file, edit_file, grep, list_directory, create_checkpoint, list_user_apps, and the connector tools list_connectors / initiate_connector_connection), the edit→preview→verify loop, how changes persist, builder/external-agent concurrency, the in-editor "Send to Coding Agent" button + onboarding README URLs, and tips like reading the Vite dev-server logs. Triggers on "develop my Base44 app remotely", "connect Claude Code to Base44", "bring my own agent", "edit a Base44 app over MCP", "Base44 sandbox MCP", or "Send to Coding Agent".
Grades agent skills by scoring agent conversations for efficiency, code quality, procedure compliance, and verbosity, then drafts concrete skill edits and a shareable report. Use when the user wants their agent setup graded from real conversation history, or asks which of their installed skills are actually working.
Build generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Applies when invoking models, setting up Knowledge Bases, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing Bedrock models (Claude, Llama, Nova, Titan). Also for KB migration to Managed, prompt caching, quota and throttling diagnosis, cost tracking, migrating between Claude model generations, chunking strategies, and Bedrock model selection. Covers AgentCore Payments (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, paid endpoints, agent payments). NOT for custom model training, Rekognition, or Comprehend. For SageMaker model discovery, customization, or endpoints, use aws-ai-ml.
Install a single skill or a skill collection into general agents such as Agents, Claude Code, Codex, WorkBuddy, Grok, Hermes Agent, Kiro, Qwen Code, Cline. Use when the user asks to install, sync, view, deduplicate, or uninstall skills across agents.
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when generating synthetic user scenarios, evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For general production deployment, use agent-platform-deploy.
Generates comprehensive, workable unit tests for any programming language using a multi-agent pipeline. Use when asked to generate tests, write unit tests, improve test coverage, add test coverage, create test files, or test a codebase. Supports C#, TypeScript, JavaScript, Python, Go, Rust, Java, and more. Orchestrates research, planning, and implementation phases to produce tests that compile, pass, and follow project conventions.
CrewAI architecture decisions and project scaffolding. Use when starting a new crewAI project, choosing between LLM.call() vs Agent.kickoff() vs Crew.kickoff() vs Flow, scaffolding with 'crewai create flow', setting up YAML config (agents.yaml, tasks.yaml), wiring @CrewBase crew.py, writing Flow main.py with @start/@listen, building experimental conversational Flows with handle_turn()/chat(), or using {variable} interpolation.
PreToolUse fact-forcing gate that denies the first Edit/Write/Bash (including MultiEdit and NotebookEdit) attempt until the agent presents concrete facts (importers, data schemas, verbatim user instruction), then allows retry; A/B-tested at +2.25 quality points. Use when enabling or configuring the GateGuard hook, exempting paths via env vars, or handling first-touch denials.
CrewAI agent design and configuration. Use when creating, configuring, or debugging crewAI agents — choosing role/goal/backstory, selecting LLMs, assigning tools, tuning max_iter/max_rpm/max_execution_time, enabling planning/delegation, setting up knowledge sources, using guardrails, or configuring agents in YAML vs code.
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, organizing workflows into folders, managing credentials, auditing instance security, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns. IMPORTANT — Always consult this skill before calling any n8n-mcp tool — it prevents common mistakes like wrong nodeType formats, incorrect parameter structures, and inefficient tool usage. If the user mentions n8n, workflows, nodes, or automation and you have n8n MCP tools available, use this skill first.
Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help diagnosing a connection or tool call.
Query the official CrewAI documentation for answers. Use when the user has a CrewAI question that isn't fully covered by the getting-started, design-agent, design-task skills — e.g., specific API details, configuration options, advanced features, troubleshooting errors, enterprise features, tool references, or anything where the latest docs are the best source of truth.
CrewAI task design and configuration. Use when creating, configuring, or debugging crewAI tasks — writing descriptions and expected_output, setting up task dependencies with context, configuring output formats (output_pydantic, output_json, output_file), using guardrails for validation, enabling human_input, async execution, markdown formatting, or debugging task execution issues.
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and which skill to load next.
Use this skill when the user asks to: 'find a trading skill', 'search for skills', 'install a skill', 'add a skill', 'download a skill', 'browse skill marketplace', 'what skills are available', 'update a skill', 'check for skill updates', 'remove a skill', 'uninstall a skill', 'list installed skills', 'show my skills', 'skill categories', 'verify skill signature', 'verify installed skill', 're-verify a skill', 'check skill integrity', or any request to discover, install, update, verify, or manage AI trading skills from the OKX Skills Marketplace. This skill covers searching, browsing categories, installing via CLI, downloading zip packages, checking for updates, removing installed skills, and verifying Ed25519 signatures of installed skills. Requires API credentials for marketplace API access. Do NOT use for placing orders (use okx-cex-trade), market data (use okx-cex-market), or bot management (use okx-cex-bot).
Know Your Agent (KYA). Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentication proofs. Based on iden3 self-sovereign identity protocol.
Common pre-checks, bot acquisition and real-person identity authorization for wecom-cli business skills, plus shared output constraints. Before any wecomcli-* skill first prepares to run wecom-cli commands, it must also read this skill to check whether the CLI is installed, whether the version is 1.2.1 or higher, and whether the WeCom credentials are authorized; install or initialize only when missing, outdated or unauthorized. This skill also defines the shared rule that ID-type fields must never be exposed. This skill does not handle specific business requests.
Audit an AI agent skill for security risks before installing or trusting it. Runs a deterministic scanner (regex patterns, Python AST analysis, source-to-sink taint tracking, and YARA signatures) and then reasons about intent — catching prompt injection, credential exfiltration, persistence, memory poisoning, malicious code, supply-chain risks, and description-vs-behavior mismatch. Make sure to use this skill whenever the user wants to scan, audit, vet, review, or check the safety of a skill, plugin, SKILL.md, or agent tool — whether it is a local folder, a zip/.skill file, or a cloned repo — and whenever someone asks "is this skill safe to install?".
Create a new Skill or improve an existing one. First propose a plan based on the scope of the changes and wait for confirmation, then generate or modify files and compare performance before and after using real tasks. Use when the user asks to create a Skill, turn recurring issues into a Skill, modify or fix a Skill, improve a Skill based on failure cases, or inspect or test a Skill. Prepare a GitHub repository and verify `npx skills add` only when the user explicitly asks to share or publish.
Find, connect, and use MCP tools and skills via the Smithery CLI. Use when the user searches for new tools or skills, wants to discover integrations, connect to an MCP, install a skill, or wants to interact with an external service (email, Slack, Discord, GitHub, Jira, Notion, databases, cloud APIs, monitoring, etc.).
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" — or to run a queue of coding tasks through Codex while staying the reviewer. Prefer it over a one-shot Codex forwarder (such as the codex-rescue agent) when the user will review the diff and commit it themselves. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite, apply Simplified Technical English, plain-language rewrite, controlled-language rewrite, rewrite so an agent cannot misread this. Not for creative or marketing copy.
Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
Persistent file-based planning for multi-step AI agent work. Keeps task_plan.md, findings.md and progress.md on disk, with lifecycle hooks injecting selected project planning content. Auto-resume only reads the project planning files; running session-catchup.py --metadata explicitly is required to inspect local agent session metadata for the same project, and --replay outputs bounded, nonce-framed excerpts. The optional gate mode only prompts for continuation when the host supports it, and never executes commands declared in Markdown. This skill has no network upload path. Suited to research or work needing more than 5 tool calls. Triggers: task planning, project plan, make a plan, break down tasks, multi-step planning, progress tracking, file planning, plan for me, break down a project
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.
Use this skill when the user asks to “create an agent,” “add an agent,” “write a subagent,” “agent frontmatter,” “when to use description,” “agent examples,” “agent tools,” “agent colors,” or “autonomous agent,” or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
Parallel divergent ideation for coding agents. Spawns N isolated branches under different cognitive frames (regulator, biology, speedrunner, 10-year-old, $0 budget), scores, clusters, prunes traps, and deepens top survivors. Use on /adhd, "ADHD mode", brainstorm/ideate intents, or open-ended design, architecture, naming, API/SDK surface, and fuzzy-debugging decisions. Skip for syntax, lookups, bugs with known root cause, or closed phrasing ("quick", "standard", "canonical", "textbook"). Full pre-flight gate is in the skill body.
Use this skill when the user wants to “create a skill,” “add a skill to a plugin,” “write a new skill,” “improve a skill description,” or “organize skill content,” or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Routes any game-development request to the right specialized skill(s): it detects the engine (Godot, Unity, Unreal, Bevy, Phaser, PixiJS, three.js, LÖVE, pygame, Roblox) and the task, then reads the chosen skill before acting. Use to make a game or to decide which skill applies — for players, levels, enemies, shaders, art direction, sprites, tiles, textures, 3D assets, UI/UX, cameras, game feel, physics, input, audio, saving, multiplayer, AI, dialogue, procedural generation, or performance, for genres (platformer, roguelike, RPG, FPS, tower-defense, card game, visual novel, survival-crafting, puzzle), and for shipping (game jam, Steam, itch). Start here when unsure which gamedev skill to use
PluginEval quality methodology, covering dimensions, rubrics, and scoring formulas. Use this skill when understanding how plugin quality is measured, when interpreting a low score on a specific dimension, when deciding how to improve a skill's triggering accuracy or orchestration fitness, when setting score thresholds for your marketplace, or when explaining quality badges to external partners like Neon.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.