Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Create or review a reusable skill (SKILL.md) that packages a workflow, and decide whether the request should be a skill instead of a prompt, instruction, agent, or hook. Use when creating a new skill, extracting a workflow from a conversation, updating an existing skill, reviewing SKILL.md quality, or fixing weak skill triggering. Triggers on "create skill", "/create-skill", "new skill", "review skill", "fix skill trigger", "SKILL.md", "スキル作成".
Meta-skill that forges, audits, and refines other skills. Three modes – forge a new skill from a brief, audit recent chat transcripts for new-skill candidates and pain points, or refine an existing skill with additive-only changes. Triggers on "skill-forge a thing that does X", "forge a skill", "skill-forge audit", "skill audit", "refine my skills", "skill-forge refine <name>", or "/skill-forge". Auto-opens a PR against mphinance/alpha-skills (never auto-merges).
Prepares a Claude Code session for compaction. Reads the session and prints ready-to-paste blocks: a /compact line with focus instructions tailored to this session, and a resume prompt for right after the compact or for a fresh session. Writes nothing to disk by default; `handoff` also saves the resume prompt to one file outside the project. Works in any language: everything the user sees comes back in the language of their messages. Use when the context is filling up or right before running /compact. Triggers: "prep me for compact", "prepare for compact", "before I compact", "ready to compact", "context is almost full", "the chat is getting long", "prompt to continue after compacting", "/smart-precompact", "תכין אותי לקומפאקט", "תכין לקומפאקט", "צריך לעשות קומפאקט", "לפני קומפאקט", "אחרי הקומפאקט", "הקונטקסט מתמלא", "השיחה ארוכה מדי". Also runs when the context hook (smart-precompact) adds a note that the context passed a threshold: answer the user first, then run with `handoff`. NOT for saving notes or memories when no compaction is in play, and NOT for shortening or compressing text, titles or files.
Guide for managing tasks within a session using bd (beads) for subtasks and local todo lists. Use this skill when breaking down plans into issues, tracking progress, managing dependencies, or coordinating work across sessions and agents. Triggers include requests to "manage tasks", "track progress", "break down this work", or questions about bd workflow.
Official update entry point for TC Skill. Use it when the user types "/tc-update", or explicitly asks to update, upgrade, reinstall, check and sync the latest version of TC Skill. It only updates TC-series skills from Leobai03/tc, does not modify other skills, and does not read or upload user chats or business materials.
Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on Google Antigravity (AGY / Antigravity IDE / Antigravity 2.0). ALWAYS consult this skill for any of those — don't answer from memory, because the exact CLI name (agy), the "agy plugin install <path>" flow, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Antigravity, says the Antigravity plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Antigravity updates it, wants to pin or remove it, or finds it running an old tool version. Not for the Codex plugin (use tooluniverse-codex-plugin) or Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.
LOOP-shaped discovery pattern: repeat rounds of parallel finders (bugs, edge cases, sites, opportunities, missing items) until K consecutive *qualifying* rounds produce nothing new. Each round is a parallel fan-out + a real dedup BARRIER against a persistent seen[]; an oracle gates the seed, every item, and final completeness. Use when the total size of the set is unknown: "find all X", "enumerate edge cases", "discover all places that do Y". Invoke via /work-exhaust.
Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about AI coding agents, agent runtimes, or similar internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
This skill should be used when the user needs to solve a complex task and wants a detailed execution plan using the best available resources. Analyzes user requirements, discovers available plugins/agents/skills/MCPs, performs intelligent matching with confidence scoring, and creates strategic execution plans with alternatives. Works across all AI CLI platforms.
Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.
Use when discovering and reconciling Alibaba Cloud product catalogs from Ticket System, Support & Service, and BSS OpenAPI; fetch OpenAPI product/version/API metadata; and summarize API coverage to plan new skills. Use when you need a complete product list, product-to-API mapping, or coverage/gap reports for skill generation.
Use when creating, migrating, or optimizing skills for this alicloud-skills repository. Use whenever users ask to add a new skill, import an external skill, refactor skill structure, improve trigger descriptions, add smoke tests under tests/**, or benchmark skill quality before merge.
Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to evaluate how well a project supports unattended agent execution, assess development practices for agent autonomy, audit infrastructure for agent reliability, or improve a codebase for autonomous agent workflows. Triggers on requests like "assess this project for agent readiness", "how autonomous-ready is this codebase", "evaluate agent infrastructure", or "improve development practices for agents".
Autonomous meta-orchestrator that continuously discovers work, dispatches agents, reviews results, and manages the full lifecycle across the user's workspace. Use when the user wants hands-off autonomous operation. Triggers on: 'autonomous', 'auto-pilot', 'run continuously', 'take over', 'autopilot'.
Set up a Python repository with the Beaker Integration contract, connect real labeled data and application execution, and validate setup. Keep evaluation tooling under .beaker and preserve production behavior. Use beaker-usage for operating an already configured integration.
This skill should be used when the user asks to "create a blueprint", "blueprint this feature", "plan this implementation", "make a plan", "create an implementation plan", "design the architecture", "design this feature", "break this down into steps", "plan this refactoring", or "help me plan".
Parallel BMAD workflow orchestration using git worktrees and tmux. USE WHEN BMAD parallel, orchestrate sprint, run stories in parallel, worktree orchestration, sprint acceleration, parallel dev stories, bmad worktree, parallelize BMAD, accelerate epic.
Explore user intent, requirements and design before implementation through structured dialogue and design proposals. Use when asked to: create features, build components, add functionality, modify behavior, plan projects, or when user says 'help me design X', 'what should we build', 'let's brainstorm', or starts describing a new feature without a design.
Turn a completed daily UI inspiration capture into exactly five original landing-page builds, one per separate Codex task, using Sites. Use when the user asks to turn the daily inspiration references, a five-item UI prompt pack, or a dated `*-ui-inspiration-capture` article into distinct HTML landing pages while changing the source brands, names, copy, people, numbers, pricing, claims, and imagery.
Drive CodeBurn, a free open-source local-first CLI/TUI/web/menubar tool that reads the session files already on disk from 40 AI coding tools (Claude Code, Codex, Cursor, Gemini CLI, Grok, OpenCode, and more) and breaks down token usage and dollar cost by task, model, tool, and project. Use when the user wants to see where their AI coding spend went, find and fix token waste in a Claude Code / agent setup, cap a session's budget before it runs away, compare which model is actually worth its price, check whether AI spend shipped or was reverted, or wire live usage/savings data into an agent over MCP. Triggers on: "codeburn", "npx codeburn", "AI token usage", "AI coding cost", "where did my Claude spend go", "codeburn optimize", "codeburn guard", "codeburn compare models", "codeburn yield", "token waste in CLAUDE.md", "AI spend dashboard".
Spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs via AGENTS.md persona injection (gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5). Triggers on 'delegate to Codex', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.
Compact, compress, or minify markdown files to use fewer tokens while preserving all information and meaning. Use this skill whenever the user wants to reduce the size of a markdown file, shrink a README, compress a SKILL.md or CLAUDE.md, minify documentation, or make any markdown more token-efficient. Trigger even if they just say "make this shorter" or "compress this" on a markdown file.
Operate external SaaS apps (Slack, GitHub, Gmail, Notion, Linear, and 1000+ more) from the terminal via the Composio CLI — discover tools, connect accounts, inspect schemas, execute actions, subscribe to triggers. Use when the user asks to send/fetch/update something in an external app, "connect my <app>", run a tool by slug, or automate a cross-app workflow.
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.