Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Develop independent competing solutions to a defined brief, compare them, and synthesize a winning approach. Use when choosing well requires developing alternatives beyond their current form. Use ce-pov to judge developed material and ce-ideate to discover opportunities.
Take a spec, issue, branch, or pull request to a reviewed pull request: implement and publish it, then run review-and-resolve rounds, each step in a fresh subagent, resuming wherever the pull request stands. Use only when the user says the explicit phrase "Finish it".
Use when the user asks to “create a hook,” “add a PreToolUse/PostToolUse/Stop hook,” “validate tool use,” “implement prompt-based hooks,” “use ${CLAUDE_PLUGIN_ROOT},” “set up event-driven automation,” “block dangerous commands,” or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks, focusing on the advanced prompt-based hooks API
Use this skill when the user asks to “add MCP server”, “integrate MCP”, “configure MCP in plugin”, “use .mcp.json”, “set up Model Context Protocol”, “connect external service”, mentions “${CLAUDE_PLUGIN_ROOT} with MCP”, or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Build or refresh a browser-viewable topic graph over Claude session history using local clustering. Use for mapping or clustering sessions, recent or stale topic analysis, or rebuilding/showing the session graph. Unlike wiki-history-ingest, it indexes raw sessions and never writes to the vault.
Mechanics library for running AI coding CLIs as managed tmux workers via agent-tmux <cli> <command> (plus tmux-agent-sessions and the other bundled tools). Entry point is the using-tmux-agent-tools router skill — route through it first; read this skill for wrapper mechanics it defers to. Covers start/send-wait/status/result/stop, structured result.json completion, multi-worker watch, profiles for custom CLIs, and bounded dialogue/fanout. Not for general tmux config, theming, non-tmux headless CLI use, or human team debate.
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. Trigger when the user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. Do not trigger for Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work unrelated to Agent Script, or when the primary input is a production session or trace ID rather than an agent artifact.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.
Audit recent work in a folder and produce a forward-looking self-improvement report. Reviews files modified in the past week, git activity, file-type distribution, and recurring task patterns; writes a 5-section weekly-setup-improvements.md with concrete updates for context files, ideas for new skills, workflow gaps to close, files to clean up, and what's working well enough to leave alone. Cross-platform; safe to schedule weekly via /schedule. Use when: 'weekly review', 'weekly self audit', 'improve my setup', 'what should I clean up', 'suggest new skills', 'self improvement loop', 'weekly setup improvements', or before a planning week.
Build MCP servers on Cloudflare Workers—the only platform with official remote MCP support. TypeScript-based, with OAuth, Durable Objects, and WebSocket hibernation. Prevents 24 documented errors. Use when deploying remote MCP servers, implementing OAuth, or troubleshooting URL path mismatches, McpAgent exports, CORS issues, or IoContext timeouts.
DigitalOcean Gradient AI agentic cloud and AI platform for building, training, and deploying AI agents on GPU infrastructure with foundation models, knowledge bases, and agent routes. Use when planning or operating AI agents on DigitalOcean
Route LangSmith work into one workflow packet before touching SDK code. Use when the user needs LangSmith tracing, offline evals, annotation/review queues, prompt-registry decisions, audit/gap review, or cross-service trace propagation for an LLM app or agent workflow. Choose one packet: trace-debug, eval, review, prompt-registry, propagation, or audit. Triggers on: LangSmith, LangChain tracing, `@traceable` / `traceable`, `wrap_openai` / `wrapOpenAI`, datasets, experiments, annotation queues, feedback criteria, Prompt Hub, run trees, trace IDs, or production confidence for an AI feature. Not for generic SLO/alert design, non-LangSmith deployment orchestration, or runtime guardrails outside LangSmith.
Design and development best practices for Claude Code skills, MCP tools, and AI agent capabilities. Use when creating skills, writing SKILL.md files, designing tool descriptions, or optimizing triggers. Triggers on "create a skill", "skill template", "write skill instructions", SKILL.md, metadata.json, progressive disclosure, trigger optimization, MCP tool design, or skill testing. Does NOT cover specific frameworks or languages (use dedicated skills).
Diagnose Claude Code usage limits—find out where tokens actually went and why a 5-hour or weekly limit was hit. Use whenever the user mentions hitting a usage limit, being rate limited, burning through their quota, running out of Claude Code usage, unexpected or suspicious token consumption, "why am I hitting limits", phantom usage, or asks to audit, analyze, or track their Claude Code token usage. Also use when the user asks how full their 5-hour window is, whether it is safe to start a big task now, which tool, model, project, file, MCP server, skill or subagent is eating their quota, what their usage would cost on the API, whether a habit or update changed their consumption, whether something is using Claude Code in the background or while they were away, or wants a usage report, a week-over-week comparison, a spreadsheet export, or a shareable redacted summary. Questions about the user's OWN tokens, usage, quota or limits—"where did my tokens actually go this week?"—mean this skill and the local Claude Code logs, NOT product analytics, LLM-cost or billing tools (PostHog, Stripe, cloud dashboards), even when such tools are connected. Trigger even if they don't use the word "tare" or "audit"—a complaint about limits is enough.
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors. Use when building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, or WebSocket payload limits.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
Use this skill when implementing, consuming, or debugging an Open Responses-compliant API—the open standard for multi-provider LLM interoperability. Covers the protocol, items, state machines, streaming events, tools, the agentic loop pattern, and extensions. Triggers on: Open Responses, open-responses, /v1/responses endpoint, multi-provider LLM API, Open Responses compliance
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Use this skill when the user asks to “create a plugin,” “scaffold a plugin,” “understand plugin structure,” “organize plugin components,” “set up plugin.json,” “use ${CLAUDE_PLUGIN_ROOT},” “add commands/agents/skills/hooks,” “configure auto-discovery,” or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
Recover lost Claude Code session context by merging duplicate project directories. Finds session/memory dirs under ~/.claude/projects/ that point at the same logical project from different cwd-encoded paths (e.g. /mnt/work/foo vs ~/Projects/foo cwd produces two separate namespaces). Unifies memory into the canonical dir, archives orphaned jsonl transcripts, and captures the lesson as a feedback memory so the split doesn't repeat. Use when: 'merge sessions', 'recover lost context', 'fix duplicate session dirs', 'session memory split', 'memory dir is empty but I added things', 'two project dirs', 'recover legacy memories from before a folder move', 'stale orphan memory namespace', or any time you find a populated memory dir at the "wrong" path and an empty one at the canonical path.
Single entry point that routes any ASO, App Store, Google Play, app marketing, paid UA, monetization, retention, reviews, ratings, market-intel, or app-analytics question to the correct specialist skill in this library. Use FIRST whenever the user mentions an app, App Store, Play Store, keywords, ranking, downloads, revenue, subscriptions, screenshots, icon, reviews, competitors, charts, in-app events, launch, press, or ads — but the right specialized skill is not obvious. Triggers: "/aso-router", "/aso-skill", "/aso", "aso help", "help me with my app", "I need ASO", "which skill should I use", or any ambiguous app-marketing request. Skip this router only when the user explicitly invokes a specific skill (e.g. /aso-audit, /keyword-research)
Build with the Claude Messages API using structured outputs for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, and model deprecations. Prevents 16 documented errors. Use when building chatbots or agents, troubleshooting rate_limit_error, prompt caching issues, streaming SSE parsing errors, MCP timeout issues, or structured output hallucinations
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
Read and navigate external documentation efficiently. Invoke when the task requires checking how a specific function, endpoint, or configuration option works; when the user references an API, SDK, library, or third-party tool by name; when any docs URL or documentation site is mentioned; or when implementing something that depends on an external service or package.
For end-to-end generation and acceptance of React / HiUI pages, from refining requirements onward. Use to generate and review pages from vague product requirements, check HiUI pages before testing, conduct an experience walkthrough after page generation, or close the loop from requirements through implementation to UX acceptance. Orchestrates hiui-refine, hiui-design, and ux-walkthrough: requirementGate, generationInputGate, and uxGate control requirement confirmation, page-generation input confirmation, engineering acceptance, tiered UX acceptance, before/after screenshots, fix closure, and report output
Tavily API integration with managed API key authentication. Perform AI-powered web search, extract content from URLs, crawl websites, map site structure, and run research tasks. Use this skill when users want to search the web, extract page content, crawl websites, discover URLs, or conduct in-depth research with citations. For other third-party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and a valid Maton API key.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost reduction", "performance optimization", "latency improvement", or "efficiency".
Query and propose local knowledge cards for this repo. Always use at the start of work here — run `npx knowcards query` before acting. Also use when wrapping up after proving a durable nuance, guideline, domain learning, or do/don't (propose a card). Skip only for routine edits in code you already hold with no repo nuance at stake, or if you already queried this topic in the session.
Route Claude Code–first orchestration to the truthful OMC install topology and runtime before giving commands. Use when the user wants oh-my-claudecode / OMC in Claude Code, needs to choose between marketplace plugin, shell-side `omc` CLI, or local-checkout `--plugin-dir` usage, or needs accurate guidance on `/team`, `/autopilot`, `/ralph`, `/ultrawork`, `/ultraqa`, `omc setup`, `omc team`, `omc ask`, updates, HUD/hooks, duplicate installs, worktree/state drift, or mapping Claude workflows to Codex/OMX and Gemini/Antigravity/OMA. Triggers on: omc, oh-my-claudecode, Claude Code team mode, autopilot, /team, ralph, ultrawork, ultraqa, ccg, omc team, omc ask, omc setup, plugin-dir, OMC HUD, OMC hooks.
Bootstrap the session into a team position. Loads the position profile from `ai-workspace/team/<name>.md`, loads sibling state directory if present (PLAYBOOK + DECISIONS), runs the position's session-start sequence. Use when a teammate session needs to assume a persistent role identity.
Creates new Claude Code skills following repository conventions with proper structure, frontmatter, workflows, code examples, and reference files. Use when users request "create a skill", "new skill", "generate skill", or "add skill to collection".
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.