Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Guide users through installing, connecting, and configuring the official Lingxing (Lingxing) MCP, and troubleshoot connection, authentication, permission, and client compatibility issues. Trigger keywords: Lingxing, Lingxing ERP, Lingxing, Lingxing MCP, Lingxing MCP, install Lingxing MCP, configure Lingxing MCP, connect Lingxing MCP, reconfigure Lingxing MCP, MCP Server URL, X-MCP-KEY, X-Mcp-Key, Lingxing MCP authentication failure, Lingxing MCP connection failure.
Deploys and operates a LiveKit agent in production: shipping a version to LiveKit Cloud and rolling it back, secrets and configuration, the worker process model and prewarming, safe async inside worker processes, provider timeouts and degradation, graceful shutdown, SDK upgrades, and observability. Use when the user says "deploy my agent", "roll back the deployment", "tail the agent logs", "the first call after a restart is slow", "attached to a different loop / event loop is closed", "prewarm the VAD", "shut down without dropping calls", "upgrade livekit-agents safely", "correlate logs by session", or is changing an agent codebase that is already live. Not for designing the agent (building-livekit-agents) or reproducing one bad conversation locally (debugging-livekit-agents).
Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.
OpenClaw Token Optimizer v3.2.0 — practical cost-control toolkit for OpenClaw agents. Lazy context loading, Sonnet/Opus-aware routing, heartbeat scheduling, local token budgets, cache-TTL guidance, and security-audit-safe command behavior for current OpenClaw 2026.6.x installs.
MindOS is the user's local knowledge assistant and a knowledge base shared across sessions and Agents. It stores decision records, meeting notes, SOPs, troubleshooting experience, architecture choices, research findings, and preferences. Tasks are limited to the mindRoot knowledge base. Do not use it to modify code repositories, project source code, or paths outside the KB. Core concepts: spaces, instructions (INSTRUCTION.md), and skills (SKILL.md); notes can contain instructions and skills. Trigger scenarios: saving or recording anything; searching historical notes or context; updating or editing files; organizing or restructuring files; executing an SOP or workflow; capturing decisions from conversations; reviewing or summarizing experience; appending table or CSV data; handing off context across Agents; distilling lessons learned; syncing related documents; checking whether something was discussed before; querying past decisions; finding templates or SOPs; preparing context for a meeting; quickly saving to the inbox; organizing the inbox; checking knowledge health; detecting knowledge conflicts or contradictions; and finding outdated content. Trigger phrases: remember this for me, search my notes, update the knowledge base, organize files, run the workflow, save to the knowledge base, make a note, organize notes, review, distill lessons, sync documents, check previous records, are there related notes, what did I write before, save this, summarize and save, hand this off to another Agent, append to the table, put it in the inbox, organize the inbox, check knowledge health, detect knowledge conflicts. Proactive behavior—don't wait for the user to mention MindOS: (1) If the user's question suggests historical records may exist (past decisions, previous discussions, meeting notes), search MindOS first, even if they don't explicitly mention the knowledge base. (2) After completing valuable work (fixing a bug, making a decision, summarizing experience, choosing an architecture, or finishing a meeting), proactively suggest saving it to MindOS for future reference. (3) After a long or multi-topic conversation, suggest preserving key decisions and context.
Use this skill when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution
Audit applications for AI prompt injection, agent security, and LLM permission boundary vulnerabilities. Use when the user mentions 'prompt injection,' 'LLM security,' 'AI security,' 'jailbreak,' 'indirect prompt injection,' 'prompt leaking,' 'AI red team,' 'LLM vulnerabilities,' 'AI input validation,' 'system prompt extraction,' 'agent security,' 'MCP security,' 'AI permissions,' 'AI privilege escalation,' or needs to secure any application with AI features, AI agents, or LLM integrations.
Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns. Use when: creating custom sub-agents, delegating bulk operations, parallel research, understanding built-in agents, or configuring agent tools/models.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Search and query past Claude Code, Codex, Kimi Code, Kiro, OMP, and Pi session history. Reactive: when the user asks "how did I fix X", "what did we do last time", "find the session where", "上次怎么修的", "之前的session", "历史记录". Proactive: when the user references past work you lack context for, when you're about to modify a file with complex edit history, when the user says "继续之前的" or "continue where we left off", or when understanding prior decisions would improve your current response. Memory: when the user says "记住这个", "remember this", "写入记忆", "save this conclusion", or when you determine a retrieval result contains a conclusion worth persisting.
Iterative, confirmation-driven workflow for building Factorial Code processes and modules end to end — plan-and-confirm, discovery scripts, incremental implementation validated with the run_code MCP tool, exposing processes as MCP tools, plus security and error-handling practices. Use when asked to build, automate, or integrate something on Factorial Code (fcode) and you need the recommended working method.
Creates and maintains the scenarios run by LiveKit agent simulations and wires the agent to consume them. Use when the user asks “what should I test,” “generate simulation scenarios,” “write scenarios for my agent,” “add a scenario for X,” “organize my scenario files,” “my simulations are flaky,” “the scenario hits my real database,” “seed state per scenario,” “it passed but booked the wrong thing,” “grade the final state,” or wants to stress-test a flow before shipping. Covers generating a baseline with the LiveKit scenario generator and refining it, writing cases generation misses, phrasing simulated-user instructions for reliable steering, splitting scenarios into sets across files, and agent-side code that seeds deterministic state from a scenario and fails a run if its final state is wrong. To run scenarios, use running-livekit-simulations.
Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.
Runs LiveKit agent simulations and acts on the results. Use when the user says “run my simulations,” “regression test my agent before deploying,” “run the scenarios,” “use lk agent simulate,” “did my agent pass,” “why did this scenario fail,” “run simulations in CI,” “test the audio pipeline,” “check turn-taking and interruptions,” or wants to check whole-conversation behavior before shipping. Covers text and audio modes and what each catches, running against a local or deployed agent, degraded-audio flags, automating a pre-release run, and triaging failures with list, view, and export. To write scenarios, use writing-livekit-scenarios. Not the default for a bare “test my agent,” which goes to debugging-livekit-agents. Use this skill when the user names simulations, scenarios, a run, CI, or shipping.
You MUST use this when deciding whether a recurring workflow needs a reusable agent skill, or when designing, creating, evaluating, improving, splitting, merging, or retiring skills. Covers trigger boundaries, architecture, behavior contracts, and effectiveness evaluation. Not for repository agent instruction maintenance (maintaining-agent-context), settled implementation planning (plan-crafting), or code behavior fixes (tdd).
Oversee the other Claude threads (sessions) working on the same project. Check what each is doing, confirm finished work is merged to main, has its changelog entry with screenshots, and is live, archive threads that are truly done, and restart or flag threads that were cut off. Use when the user says "check threads", "check new changes", "are the threads merged and pushed", "archive the done threads", or asks what the other sessions are up to. Project specifics (changelog format, live site, capture folders) go in an optional local references/<project>.md next to this skill.
Emit and maintain a dagr run file — a live, contract-valid JSON description of recursive projects, tasks, attempts, gates, evidence, policies, events, and operator-message resolutions that `dagr view` renders as a DAG. Use when orchestrating agents or tracking multi-step work that a dagr pane should display.
Investigate LLM spend in PostHog: total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.
Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for “instrument my code”, “add opik tracing”, “add observability”, “trace my agent”. Not for building a new app from scratch, or a review-only pass with no code changes.
Delegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delegate to Jules', 'send to Jules', 'ask Jules to', 'check Jules sessions', 'pull Jules results', 'jules add tests', 'jules add docs', 'jules review pr'. Handles: bug fixes, documentation, features, tests, refactoring, code reviews. Works with GitHub repos, creates PRs.
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after research-ideation), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing research-ideation cycles or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use research-ideation)
Execute sensitive browser actions (login, payments, form filling) outside the core agent loop using a dedicated CLI tool. Use when Claude needs to handle credentials, payment information, or other sensitive data in browser automation workflows. Triggers when users ask to log into websites, fill payment forms, or perform authenticated browser actions where sensitive data must be kept secure and separate from the main agent context.
Bootstrap and run a lightweight multi-agent development team. Use when starting or adopting a project, planning work, coordinating implementation and optional QA, brainstorming with distinct perspectives, or preserving context across sessions.
Use when an agent must inspect or operate an authenticated SAP web UI through an in-app Browser, Microsoft Edge CDP, or an existing Playwright client, especially when SAP SSO reuse, isolated Edge profiles, deterministic target selection, screenshots, or browser bootstrap recovery is required.
Project development lifecycle management with a complexity-tiered three-phase workflow (investigate, proposal, implement; trivial changes take a fast path, everything else waits for approval), file-based plan tracking in docs/plan/, task tracking in docs/task/, and claim-before-work multi-agent coordination. Use when handling feature development, bug fixes, refactors, planning, progress tracking, or multi-agent execution in an existing codebase. English-first for repository docs and remote-visible metadata; use Chinese docs only when the user explicitly requests a specific document in Chinese
Run a bounded cross-platform landscape scan before planning or implementation. Use when the real job is researching what exists, how people work around it, which solutions repeat, or how platform/tooling patterns map before deciding what to build. Produce reusable `.survey/{slug}/` artifacts, validate the artifact contract, and route planning or execution outward only after the survey is done.
Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.
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.