Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Automated factory for converting GitHub repositories into specialized AI skills. Use this skill when the user provides a GitHub URL and wants to "package", "wrap", or "create a skill" from it. It automatically fetches repository details, latest commit hashes, and generates a standardized skill structure with enhanced metadata suitable for lifecycle management.
Use when several agents share a repo: claim a task, see who works on it, reserve an id, sync the board, set up coordination. RU: возьми задачу, кто сейчас делает, зарезервируй id, обнови доску. Not for solo work or an unconfigured repo: 'no coordination' / «без координации».
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
Discovers and installs agent skills from the open ecosystem. Enriches search results with descriptions fetched from skills.sh. Use when a user asks "how do I do X", "find a skill for X", "is there a skill that can...", or wants to extend agent capabilities. Use for skill discovery, skill search, skill install, finding tools.
Break out of a locked problem frame by picking one disciplined move—reframe, provocation (Po), random stimulus, SCAMPER, inversion, structured analogy, constraint play, or family traversal—and committing to it before evaluating. Use when stuck, when options feel narrow or obvious, when iterations produce variations of the same idea, or when the user says "widen this", "break out of", "think differently", "I'm stuck", "feels too obvious", "stress-test the framing", "what am I missing", or holds two related examples and asks what lies between or beyond them. Complements challenging (which evaluates) and convening-experts (which synthesizes viewpoints); this skill generates distance, not judgment.
Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Generates 4 interconnected docs — SPECIFICATION.md, IMPLEMENTATION.md, TASKS.md, BRANDING.md — plus a self-contained PROMPT.md for autonomous execution by any coding agent. Includes interactive tech stack selection, design pattern recommendations, and architecture decisions with trade-off analysis. Trigger when user wants to: plan a project, create specs, architect a system, break work into tasks, choose a tech stack, get design pattern advice, generate a coding agent prompt, or do documentation-first development. Phrases: "plan my project", "spec this out", "architect", "help me plan", "what stack should I use", "generate a prompt", "break this into tasks", "project docs", "I want to build X".
ElevenLabs voice agent creation for client discovery and feedback calls. Use this skill when creating AI voice agents, setting up discovery call agents, or configuring automated phone conversations. Triggers on voice agent creation, ElevenLabs agent setup, or automated call agent requests.
Use when developer-owned execution needs inspectable branching, concurrency, joins, waits, approval, retry, runtime streams, pause/resume, recovery, or mixed sync/async orchestration. Use agently-stage instead when a provider-owned sync wrapper only bridges an async SDK
Scaffold a new subagent definition. Automates the full process, including category selection, file creation, least-privilege model/tools configuration, and quality checks. Use for requests such as "create an agent", "add a subagent", or "create-agent"
Write and improve programs that call Jev, TypeSafe's System One model. Use when designing TypeSafe questions (Choice, Score, Noul, Box), structuring state, sending images, composing answers in code, setting confidence thresholds, or diagnosing a Jev question that answers wrong or with low confidence.
Write, run, and analyze structured test suites for Agentforce agents. TRIGGER when the user writes or modifies test spec YAML (AiEvaluationDefinition); runs sf agent test create, run, run-eval, or results commands; asks about test coverage strategy, metric selection, or custom evaluations; interprets test results or diagnoses test failures; or asks about batch testing, regression suites, or CI/CD test integration. DO NOT TRIGGER when the user creates, modifies, previews, or debugs .agent files (use developing-agentforce); deploys or publishes agents; writes Agent Script code; uses sf agent preview for development iteration; analyzes production session traces (use observing-agentforce); or requests OWASP, security, or red-team testing (use securing-agentforce).
Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails. Use when reviewing CLAUDE.md files, MCP configs, agent orchestration code, or any AI agent setup
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
Build, validate, test, and update registries and catalogs that follow the Agentic Resource Discovery (ARD) specification. Use this whenever the user works with an ai-catalog.json, a capability manifest, an ARD/AIR catalog or Agent Registry, urn:air: identifiers, trustManifest/attestations, representativeQueries, or an Agent Finder / discovery service — including authoring a new manifest, scaffolding one, fixing schema or URN errors, running conformance/validation, probing a registry's /search, /explore, or /agents REST endpoints, reviewing trust and federation metadata, or preparing to publish at /.well-known/ai-catalog.json. Trigger it even when the user only says “ARD”, “agentic resource discovery”, “AI catalog manifest”, “agent registry”, or “make agents discoverable” without naming the file.
Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows. Use when creating subagents for Cursor editor specifically, following Cursor's patterns and directories (.cursor/agents/). Triggers on "cursor subagent", "cursor agent". Do NOT use for generic subagent creation outside Cursor (use subagent-creator instead).
DeepWorkPlan — turn any repo AI-first and run Deep Work Plans. Routes to create, execute, refine, resume, status, verify, upgrade, and repo-onboarding sub-skills based on intent. Use when the developer wants to plan, execute, manage, or verify structured multi-task work, or make a repository AI-agent-ready.
Structurally optimize existing SKILL.md files according to the Skills MD standard writing format, improving description quality, section organization, concision, and formatting consistency. Use when users need to optimize, improve, or standardize SKILL.md files. Triggers: optimize SKILL.md, improve skill, standardize skill format, skill format check, skill optimization.
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the Task tool for architecturally enforced context isolation. Supports Jest, Vitest, pytest, Go test, cargo test, PHPUnit, and RSpec.
Create or extend a nao project's RULES.md. Owns the RULES.md template. Use when the user wants to generate the initial RULES.md from synced metadata (called by setup-context) or improve an existing RULES.md. Do not use for first-time scope setup (use setup-context) or diagnosing existing problems (use audit-context).
Self-improvement system for agents. Invoke when the user runs /agent-brain followed by: improve (learn from this session), learn <something> (teach the agent something new), interview (proactively interview you to fill knowledge gaps), absorb <path> (adopt capabilities from another agent, skill, or full brain), dream (reflect on the full brain and surface growth opportunities), or validate (audit brain for structural issues)
Run fable-mode execution discipline on Claude Opus — the top of the escalation ladder. Trigger when the user explicitly asks for thorough, systematic, or “deep work” handling on Opus (“fable on opus”, “stage this on opus”, “deep work mode, opus”). When a task exceeds Opus's ceiling, report that to the user rather than escalating further.
Analyze production Agentforce agent behavior using session traces and Data Cloud. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries. DO NOT TRIGGER when: user creates, modifies, or debugs .agent files during development (use developing-agentforce); writes or runs test specs (use testing-agentforce); uses sf agent preview for local development iteration; deploys or publishes agents.
In Claude Code: see what this session costs and where the tokens go, plus tools to cut usage—/cco for the board, /cco audit, /cco task, /cco pack, and more. Use when the user asks about session cost, context size, savings, or wants a task tracked across /compact.
Graph engineering for parallel task execution: convert a task, PRD, SPEC, or issue set into a dependency graph (DAG), layer it into supersteps, then implement each independent node concurrently with subagents — each node runs /goal → /review-it → /ship-it in an isolated git worktree, with a fan-in barrier between waves. Triggers on: graph, graph engineering, build a graph, task graph, dependency graph, DAG, parallel implement, 并发实现, 并行实现, 任务图, 把任务变成图, fan-out fan-in, superstep, dynamic workflow
One-click deployment of the JiuwenSwarm multi-Agent collaboration platform on Huawei Cloud Flexus L instances. Use when users need to quickly deploy JiuwenSwarm/JiuwenClaw on Huawei Cloud Flexus L instances, automatically create cloud instances and deploy AI Agent platforms, or configure model APIs and message channels (Xiaoyi/Feishu/DingTalk). Automatically creates instances, deploys applications via COC, and configures models and message channels. Trigger keywords: JiuwenSwarm deployment, JiuwenClaw deployment, 九问Swarm部署, 九问Claw部署, 一键部署JiuwenSwarm, AI智能体平台部署, 部署九问Swarm, 部署九问Claw, 云服务器部署AI平台.
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
Opt-in ambient signal capture. After explicit enablement, applies on substantive inbound messages to detect original thinking and entity mentions. Use an authorized sub-agent where supported; otherwise detect inline. Aim to never block the main response
Ground the assistant in the target SAP system before any coding work by producing a local system-info.md that captures SID, release, components, detected features, RAP constraints, and ARC-1 lint preset. Use when asked to "set up system context", "bootstrap the SAP system", "create system-info.md", or when starting a session against an unfamiliar SAP system
Multi-pass PR bug review with 5 parallel passes, majority voting, independent Opus validation, and resolution rate tracking. Trigger on PR review, bug finding, code review, “review this PR,” “check for bugs,” “find issues in this PR,” or /bug-review. Also trigger on /bug-review:resolve to classify whether findings were fixed at merge time, and /bug-review:report for resolution rate stats. Even if the user just says “review this” while on a PR branch, trigger this skill.
Use when building an internal admin-facing AI agent in a Medusa project. These agents are operated by merchants and store operators — not customers. Covers data models, module service, agent runtime (tools, system prompt, streamText), streaming API routes (NDJSON), and admin UI chat extensions. Load for any internal agent type: store operations assistant, product audit, cohort analysis, customer service tooling for support staff, etc. Do NOT use for customer-facing agents (storefront chatbots, buyer-side assistants).
Build and operate multi-agent workflows with OpenAI Agents SDK (Python): define agents/tools/handoffs, add guardrails, run conversations, and debug orchestration behavior. Use when users ask for agent orchestration with OpenAI-native patterns, handoff routing, or production-ready agent loops.
Build Retrieval-Augmented Generation (RAG) applications that combine LLM capabilities with external knowledge sources. Covers vector databases, embeddings, retrieval strategies, and response generation. Use when building document Q&A systems, knowledge base applications, enterprise search, or combining LLMs with custom data.
Use this skill whenever users mention “分身” or make any related request: create, view, edit, delete, evaluate, share, and manage Avatars; chat with your own or others’ Avatars; and handle regular Second Me user operations such as sign-in and registration, managing identity and appearance (Profile), materials (Note), and key memories (Key Memory).
Scaffold a new skill as skills/<name>/SKILL.md. Automates duplicate checks for names and locations, SKILL.md creation, symlink setup, quality checks, and updates to CLAUDE.md. Use for requests such as “スキル作って”, “新しいスキルを追加”, or “create-skill”. See create-agent to add an Agent definition and update-docs to update documentation.
Primes the agent with deep codebase understanding by analyzing structure, documentation, and key files. Use when starting work on a codebase, at the beginning of a session, or when you need a fast orientation before planning or implementing. Optionally pulls external task context from Jira issues and Confluence pages first.
Disciplined task execution with planning, verification, and self-improvement loops. Use when starting non-trivial tasks (3+ steps), fixing bugs, building features, refactoring code, or when rigorous execution with quality gates is needed. Includes subagent delegation, lessons tracking, and staff-engineer-level verification.
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.