Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
Use this skill whenever the user wants to create a new Claude skill, write a SKILL.md file, turn a workflow into a reusable skill, package instructions for Claude to follow, or build a custom automation that Claude can trigger. Also use when the user says "make this a skill", "create a skill for X", "I want Claude to always do X", or asks how skills work. Covers skill anatomy, writing patterns, description optimization, progressive disclosure, testing, and packaging. Even if the user just mentions wanting to standardize a workflow or create reusable instructions, this skill applies.
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
Use when you want to expose an n8n workflow as a tool the coding agent can call. Two cases. (1) Wrap n8n API capabilities the MCP doesn''t natively expose: folder CRUD, tag rename/delete, instance metadata, credential creation. (2) Expose a general-purpose workflow as an agent tool: a workflow that calls a third-party API, runs business logic, or does any task you want the agent to invoke. Triggers on "expose as MCP tool", "build a tool for my agent", "I need to know X" where X isn''t an MCP tool, "create folder", "rename tag", or any capability gap.
Prompt optimization assistant. Use when users want to optimize prompts, improve AI instructions, design better prompts for specific tasks, or choose a suitable prompt framework. It matches frameworks to the task and, when needed, asks clarifying questions before producing a clearer, more actionable prompt.
Tracks skill usage patterns, edit frequency, and success rates to suggest improvements and optimizations. Manages skill versioning with safe rollback capability and confidence scoring for suggestions. Use when reviewing skill performance, applying auto-suggested changes, or rolling back problematic versions.
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task execution unless explicitly invoked.
Create one or more git worktrees for parallel development, each on its own branch with gitignored config copied in, dependencies installed, and a health check, by fanning out a setup subagent per worktree. Use when starting isolated parallel work, running several PIV loops at once, or when the user says "set up worktrees", "create a worktree", "spin up parallel branches", or invokes /worktree-create.
INTERNAL sub-agent for blind 7-dim rubric scoring. **NOT a user-facing skill — do NOT invoke from main conversation.** Called via Task tool by cheat-score / cheat-predict / cheat-bump to get a context-isolated score on a script. Receives ONLY script_path + rubric_notes_path; refuses any other input. Outputs strict JSON: 9 dimensions × {score 0-5, confidence enum, one-line reason}. **Hard refuses to Read** .cheat-state.json, predictions/*, retro 段, or anything that could leak post-publish data. This is channel B in the 3-channel calibration model (A=main, B=blind sub, C=cross-model).
Black-box CLI grading harness that runs a test suite against a target CLI and reports per-rule pass/fail results from the cli-for-agents 45-rule catalog. Use when reviewing, auditing, or grading a command-line tool for agent-friendliness. Trigger even if the user doesn't explicitly say "agent-friendly"—apply whenever they ask "is my CLI good for agents?", "review this CLI", "grade my CLI against the rules", "check if this tool is safe to automate", or "audit command-line design". Companion to the cli-for-agents distillation skill.
Build, run and manage multi-step AI workflows that chain EachLabs models into one API call. Create a workflow from a JSON definition, trigger it, read its results and manage versions. Use when a task chains several models, reuses a fixed prompt, needs a fallback model, runs steps in parallel, routes on a condition, or calls an HTTP API between model steps
Use when building or editing AI inside an n8n workflow: the AI Agent node, Text Classifier, Information Extractor, Sentiment Analysis, Summarization Chain, Basic LLM Chain, embeddings, vector stores, single one-shot LLM calls, or AI media generation (image / audio / video) via the native LangChain provider nodes. Also when a first-class n8n Agent can’t do the job: trigger data mapped exactly into tool parameters, or memory shared across workflows. Triggers on any `@n8n/n8n-nodes-langchain.*` node, “AI Agent node”, “LLM with tools”, “tool calling”, “fromAi”, “system prompt”, “memory window”, “structured output”, “outputParser”, “RAG”, “vector store”, “embeddings”, “classify with AI”, “extract fields with LLM”, “sentiment analysis”, “summarize with LLM”, “single LLM call”, chat triggers with files, Slack / Discord / Teams / Telegram bot workflows, AI image / video / audio generation, or any multi-turn or one-shot LLM step in a workflow.
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.
Use when a session starts or resumes after compaction (auto via the session_start and session_compact event hooks) and the team AI directives context — constitution, CDR index, Class Boots catalog, skills registry — is not yet injected; also fires the session-end friction trigger for CDR/ADR/PDR capture with pending-decision safety nets.
Bootstrap agents for iOS, iPadOS, macOS, Swift, SwiftUI, SwiftData/Core Data, Swift Testing, Xcode build/test/debug, Simulator, App Intents, or XcodeBuildMCP work. Use before building, fixing, refactoring, QAing, or setting up Apple-platform repos, and when asked to load/install Ray's iOS skills or bootstrap iOS.
Использовать перед любой массовой правкой, миграцией, унификацией или редизайном, а также перед повторной попыткой исправить тот же симптом. Проверяет гипотезу, причину, масштаб и применимые факты до реализации; результат — один рекомендуемый ход, его граница и проверяемый признак успеха. Также использовать, когда решение опирается на непроверенную причину, внешний факт или метрику. Не использовать для выбора продуктовой задачи, поиска edge cases и мелкой согласованной правки.
Closeout pass on a finished substantive change — sequence refactor-clean (shape), code-review (diff), and write-docs (docs) so all three run, in the order where each feeds the next. Use after implementing a slice or feature and before calling it done or committing; when the user asks for a final review, a cleanup-and-document pass, or to "review everything." For a diff-only audit, reach code-review directly
Use when you need to generate a checklist document with Java system prompts from skills.xml, following the embedded section template and producing INVENTORY-SKILLS-JAVA.md. This should trigger for requests such as Create Java system prompts checklist; Generate INVENTORY-SKILLS-JAVA.md; Use @003-skills-inventory; Inventory Java cursor rule skills; List available Java system prompt skills. Part of Plinth Toolkit
Search, discover, browse, and install AI Gallery Agent skills using natural language. Triggers include: “AI Gallery”, “AI Gallery有什么skill”, “有什么skill”, “AI Gallery相关skill”, “AI Gallery agent skill 市场”, “AI Gallery skill类目”, “skill 市场”, “搜索AI Gallery skill”, “安装skill”, “订阅skill”, “有没有XX skill”, “有没有XX的能力”, “帮我找 XX skill”, “帮我找一个能XX的工具”, “我想扩展功能”, “介绍 XX Skill 内容”, “XX Skill 具体做什么”, “explore AI Gallery skills”, “show AI Gallery skill categories”, “does an AI Gallery skill exist for...”, “which AI Gallery skills exist”, “search skill”, “find skill”
CRITICAL — Do NOT write code yourself. Route ALL code generation through this Skill. This is the MANDATORY entry point. When a user asks for any code, file, project, or feature (生成代码/write code, 写函数/write a function, 创建模块/create a module, 开发项目/develop a project, 实现功能/implement a feature, 写一个XX/make an XX, 做一个XX/build an XX), or mentions CodeArts/码道, you MUST invoke this Skill first. Under NO circumstances may you skip this Skill and write code directly. Even if you think "this is faster" or "this is a simple task" — DO NOT skip.
Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real browser. Also use when the user mentions "browser", "webpage", "open URL", "screenshot", asks to read/interact with any website, or wants a reusable CLI tool or script that automates a specific website. Use even for simple-sounding browser requests — the daemon handles all complexity.
Use this skill when choosing or running NeMo Relay installation for an agent runtime, application language, framework integration, or plugin bundle, or checking a runtime's native Relay readiness. Do not use it for first-run instrumentation or export configuration.
Write a single-paragraph Deep Research prompt to hand to a human researcher (or a deep-research AI). Use when the user wants a research brief, a "deep research prompt", a one-paragraph task for a researcher, or asks "what should our researcher look for". Produces ONE tight paragraph with full context, numbered sub-questions, and per-finding output format.
Reduce Claude Code token burn with proactive compacting, task-scoped sessions, checkpoint files, tiered docs, and relevance-based context pruning. Use when a user explicitly asks to reduce context usage/cost, run token benchmarks, or optimize CLAUDE.md. Do not use to expand product scope or skip correctness checks
Practical guide to reduce token consumption and lower AI costs for both Claude Code users and developers calling the Anthropic API directly. Covers file organization, context management, strategic model selection, prompt caching, Batch API, effort tuning, and prompt architecture. Backed by real experiment data. Use when user mentions "optimize tokens", "reduce costs", "Claude is slow", "too many tokens", "token budget", "context window full", "organize codebase for AI", "reduce token consumption", "prompt caching", "cache_control", "batch API", "cache broken", "API costs", or "thinking budget". Do NOT use for general coding questions, debugging, or performance optimization unrelated to AI token usage.
Reusable pattern for presenting the user with explicit choices and gating execution until they respond. Used by other skills when a decision point requires human input before proceeding. Platform-agnostic — works on Telegram (inline buttons), Discord, CLI, or any agent with a message tool
An intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember/forget triggers, enabling sleep-time reflection, building knowledge graphs, or adding audit trails. Replaces basic flat-file memory with a cognitive architecture featuring episodic, semantic, procedural, and core memory stores. Supports multi-agent systems with shared-read, gated-write access. Includes philosophical meta-reflection that deepens understanding over time. Covers MEMORY.md, episode logging, entity graphs, decay scoring, reflection cycles, evolution tracking, and system-wide audits.
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context injection and subagent execution.
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.