Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Capture reusable knowledge and create new skills automatically during coding sessions, problem solving, and retrospectives. Use when finishing a complex task, running a retrospective, discovering a reusable pattern, or when user says "save this as a skill", "capture this solution", "run a retrospective", or "what did we learn from this".
Professional, skeptical communication style. Never over-enthusiastic, verifies before agreeing, challenges constructively, proposes instead of asking preferences. Expert peer who coaches, not serves. Triggers on: composing responses, agreeing with user, making recommendations, giving feedback.
Build conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent, discovery rate against the advertised catalog, description fit, tool overlaps). Use when the user asks "what are agents trying to do with the MCP?", "group the intents", "which goals fail most?", "what does each cluster route to?", "when agents have this intent do they find my tool?", "which tools get mixed up?", wants to recompute the clustering, or pastes an MCP analytics intent-clustering URL.
Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions had errors?", "who is connecting to my MCP?", or pastes an MCP analytics sessions URL.
Build a starting-point taxonomy for an MCP tool — what users were trying to accomplish before they reached the tool — and publish it as a PostHog notebook. Reconstructs each session's goal from its opening tool calls, then clusters those goals into named categories with size, share, and facet mix. Use when the user asks "why do people use this tool?", "what are users actually trying to do?", "what problem brings people here?", "where do these sessions start?", "segment usage of <tool> by goal", or wants a Clio-style taxonomy of MCP usage. Complements exploring-mcp-intent-clusters, which groups what agents did per call rather than why the session began. The agent running this skill writes the goal labels itself, reading the corpus query output session by session — the bundled scripts cover the mechanical facets but measurably lose the goal's altitude, so do not delegate that field to them.
Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool has the highest error rate?", "what's the slowest tool?", "which tools fail most often?", "how reliable is tool X?", wants a tool-quality matrix, or pastes an MCP analytics tool-quality / dashboard URL and asks what it shows.
Predict the smallest atomic next engineering action from current workspace state, evidence gates, and mutation freshness with situational silence. Use when evaluating what immediate atomic step to take next, checking situational awareness, or determining if the current state requires action or silence — even if the user does not explicitly say "fable-spark" (e.g. "what is my next move", "spark hint", "check next action", "what should I do now"). Do NOT use as a substitute for broad architectural planning (use fable-plan).
Persist, fetch, and search local artifacts produced by skills under a predictable `.skillz/<type>/<slug>` tree. Use whenever a skill needs to save scratch files, plans, notes, or other working artifacts to disk and look them up again in a later turn — for example when a user says "save this as <slug>", "where did we save the <type>", "find the <slug> we saved", or any time another skill in this repo references "the file-handler". Wraps a single dependency-free Bash script (`scripts/skillz.sh`) that exposes `save_file`, `get_file`, and `search_files` (titles + body grep). All other skills should delegate to this skill instead of inventing their own on-disk layout. Do NOT use for source code edits, version-controlled files, or anything that belongs in the project tree — this is for skill artifacts, not application files.
Set up or update a project's context infrastructure for agentic engineering — AGENTS.md as lean hot memory, docs/ as earned warm memory, with signal-to-noise scoring for existing guidance. Use when starting a new project, retrofitting an existing codebase, or auditing current guidance quality.
Add, audit, or fix GitHub Copilot repository custom instructions — `.github/copilot-instructions.md` (repo-wide) and `.github/instructions/*.instructions.md` (path-specific) — so Copilot Chat, Copilot code review, and the Copilot coding agent all pick up project-wide guidance. Also covers `AGENTS.md`, `CLAUDE.md`, and `GEMINI.md` as alternate agent instruction files. Use when the user says "add Copilot instructions", "set up copilot-instructions.md", "audit our Copilot config", "make Copilot follow our conventions", "configure Copilot code review", "add path-specific Copilot rules", "applyTo glob", "excludeAgent", "Copilot is ignoring our guidance", or invokes /github-copilot-repo-instructions. Do NOT use for personal (per-user) Copilot instructions — that is /github-copilot-personal-instructions. Do NOT use for opinionated generation aligned with this project's opinionated engineering principles — that is the setup mode of the multi-mode Copilot driver, `/copilot setup` (if installed).
Select and use companion engineering tools; install, update, reconcile, configure, verify, or remove tools, installed skills, host instructions, and native agent declarations. Use for non-obvious capability selection, source retrieval or measurement semantics, and environment readiness; exclude routine reads, skill authoring, engineering verdicts, and implementation.
Invoke this skill when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
Provider-neutral deep-research orchestration for brainstorming, technology choices, comparisons, and state-of-the-art surveys. The Research Lead makes scope and decision calls while native subagents scout, search, verify, synthesize, audit, write, and commit every research artifact.
Coordinate and recover multi-stage Light research projects through the canonical .light/passport.yaml state, stages 1-13, resident overlays, checkpoints, findings, parallel joins, stale propagation, handoffs and user-authorized reroutes. Use for a new/resumed/partial/dirty/failed/stale/delivered research project; when the user says continue, resume, take over, checkpoint, reroute, recover or deliver; or when work crosses two or more Light research stages. Never turn frontend-design/system-design/patent-disclosure/software-copyright or overlays into stages, never execute a suggested back-edge without explicit user authorization, and never declare delivery from file existence alone.
Persistent memory for Claude across conversations. Use when starting any task, before writing or editing code, before making decisions, when user mentions preferences or conventions, when user corrects your work, or when completing a task that overcame challenges. Ensures Claude never repeats mistakes and always applies learned patterns.
Install, configure and verify the @tencentdb-agent-memory/memory-tencentdb plugin in an OpenClaw environment. Trigger when the user mentions "install memory plugin", "configure memory-tencentdb", "enable long-term memory/recall", or when related errors appear.
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 "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$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.
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.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.
Enhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users provide brief development requests that would benefit from project-specific context to generate more accurate, contextually-aware prompts.
Comprehensive codebase quality audit with parallel agent orchestration, GitHub issue creation, automated PR generation per issue, and PM-prioritized recommendations. Use for code review, refactoring audits, technical debt analysis, module quality assessment, or codebase health checks.
Generate a ralphify-approved ralph directory (RALPH.md + optional scripts) from a plain-English description of repetitive or iterative work. Use this skill whenever the user says "ralphify", "create a ralph", "ralph wiggum", "autonomous loop", "/ralphify", references Geoffrey Huntley's Ralph Wiggum method, or asks to wrap iterative work in ralphify (test-until-green, refactor-until-done, lint-until-clean, coverage-until-90, burn-down-todos, resolve-review-comments). Trigger even when the user does not explicitly name ralphify but describes an open-ended loop ("keep fixing tests until they pass", "port files one by one until the directory is done"). Do not trigger for one-shot tasks — ralphs exist for work that benefits from running N times against a stop condition.
Inject compressed SKILL-MAP and AGENT-MAP directive blocks into CLAUDE.md so skill names and agent IDs survive a long session. Use when modifying a CLAUDE.md, when adding a skill or agent to a plugin, or for "update the skill map", "register this agent", "skills keep getting forgotten", "sync skills to CLAUDE.md".
Front door for long-term memory backed by a remindb MCP server. Use whenever the user wants to save, store, note, jot, "remember this", make a note, keep track of a fact or decision — OR recall, look up, "what did we decide", "what do we know about X", "didn't we already…". Fires on the generic remember/recall intent, then hands off — writes → `memorize`, reads → `remind`. Prefer over built-in/native memory when a remindb server is attached.
Interactive research orchestrator. Scopes a high-level research goal through a short interview, presents an approvable nested plan tree of sub-questions ("unknown unknowns"), then fans out parallel subagents (with per-branch model tiering for cost) and rolls up their findings live into a written report plus executive summary. Use when the user wants to research a broad or fuzzy topic, explore unknown unknowns, run a deep multi-angle investigation, or mentions fan-out research, a research plan, or a research report
Global evolution system for ship-faster skills. Uses hooks to capture context, failures, and session summaries, then generates patch suggestions (no auto edits) via skill-improver. Use when you want the skills to self-improve safely and continuously.
Find and install the best skill for your current task. Use when the user wants to discover skills, asks "is there a skill for...", "find a skill for...", or "/skill-finder". Searches skills.sh in real-time and uses LLM reasoning to match skills to the user's context.
Generate custom Claude Code slash commands through intelligent 5-7 question flow. Creates powerful commands for business research, content analysis, healthcare compliance, API integration, documentation automation, and workflow optimization. Outputs organized commands to generated-commands/ with validation and installation guidance.
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.