Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Creates, audits, and validates agent skills following the Agent Skills open standard. Covers YAML frontmatter, description writing, progressive disclosure, directory structure, 9-phase audits, severity classification, and manifest-implementation drift detection. Use when creating new skills, writing skill descriptions, auditing existing skills, detecting version drift, validating implementations match manifests, or debugging skill discovery issues.
Provides comprehensive guidance for Spring AI Alibaba, including Alibaba Cloud AI services integration, model APIs, and AI application development. Use when the user asks about Spring AI Alibaba, needs to use Alibaba Cloud AI services, or integrate AI capabilities in Spring applications.
Complete development guide for WeChat Mini Program AI development mode (beta). Triggers when developers need to convert a mini program to AI development mode, encapsulate a SKILL, write atomic interfaces/atomic components, or write SKILL.md or mcp.json. Covers the full specification of onboarding flow, project structure, schema design, content text conventions, component constraints, best practices, and common anti-patterns.
Add project-specific rules and conventions to the configured RULES.md artifact. Each invocation appends new rules. These rules are automatically loaded by /aif-implement before execution. Use when user says "add rule", "remember this", "convention", or "always do X".
Design, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill, rewriting SKILL.md frontmatter and workflows, fixing under-triggering or over-triggering, designing scripts/references/assets, building test cases, or preparing a skill for upload/distribution.
Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.
Use when setting up, troubleshooting, or modifying the shared hooks and agent-callable utility scripts that enforce the autonomous dev/review workflow. Triggers on phrases like "push to main is blocked", "block-commit-outside-worktree hook failing", "configure hooks after npx skills add", "what does check-pr-review.sh do", "set up workflow hook symlinks", or when editing files under `skills/autonomous-common/`. Provides the hooks the autonomous-dev / autonomous-review skills depend on, plus utility scripts (gh-as-user.sh, mark-issue-checkbox.sh, reply-to-comments.sh, resolve-threads.sh).
Meta-skill for scaffolding and validating custom PLANNING/ORCHESTRATION skills within the BMAD Planning & Orchestrator plugin. Produces the full skill directory: SKILL.md, scripts, and templates — all pre-targeted at this plugin's path conventions. Includes a scope-violation checker so newly created skills never drift into dev/lint/build/coverage territory. Use when the user says "create a skill", "scaffold a skill", "build a new planning skill", "add a skill to the orchestrator", "extend BMAD planning", "custom orchestration skill", "validate this skill", "check this skill for scope violations", "new skill for the planner", or "bmad-builder". Supports three intents: Create (new skill skeleton), Validate (check an existing SKILL.md), Scaffold (directory structure only). This skill plans and scaffolds only — it NEVER writes application code, runs tests, lints, or builds.
Creative-writing session lead and entry point. Activate this to get a creative partner that brainstorms, drafts, critiques, revises, and maintains your story's knowledge base. Built for Claude.ai, where there are no subagents: it runs every mode of the work in one conversation. Load alongside the craft skills (writing-principles, prose-writing, scene-construction, prose-critique). Use at the start of any story session.
Interview employees to identify recurring daily work, office workflows, and repetitive tasks that can be automated, co-piloted, or supported by AI. Use when the user wants to find what AI can take off their plate, map available tools such as ChatGPT/OpenAI, Claude, Microsoft Copilot, Excel or PowerPoint add-ins, Google Workspace, no-code/RPA tools, coding agents, or internal automation platforms, and write tool-aware specs with fallback paths.
Felo SuperAgent API: AI conversation with real-time SSE streaming on a persistent LiveDoc canvas. Use when users want SuperAgent chat, continuous conversation, logo/branding design, or e-commerce product images. Do NOT use for tweet/X post writing — use felo-twitter-writer instead. Explicit commands: /felo-superAgent.
Use Jev as System One to save the user reasoning-model tokens, time, and cost on bulk reading or repeated semantic decisions. Trigger when sifting large documents or tool outputs, selecting evidence or actions from many candidates, or checking many items against criteria, even if the user never mentions Jev. Also use for "Jevify this", Jev question design, and product work where frequent, inexpensive judgments could improve the experience.
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).
Creates custom subagents for Claude Code with YAML frontmatter configuration in Markdown files. Covers agent scoping (project, user, CLI, plugin), tool access control, model selection, permission modes, skill preloading, and lifecycle hooks. Use when building specialized subagents, configuring tool access, selecting models, setting permission modes, or designing delegation patterns. Use for agent creation, subagent configuration, custom agent setup.
Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. Picks a test suite with judge assertions or a dataset with metrics, sources cases from traces or synthetic data, scores heuristics-first then one-failure-mode judges, runs client-side via the SDK or server-side for prompt-only targets, and reads the scores back. Covers RAG evaluation, error analysis, writing and validating LLM judges against human labels, and auditing an existing eval pipeline. Use for "evaluate my agent", "measure quality", "build an eval", "write an LLM judge for hallucinations", "audit our evaluation pipeline", "how good is my RAG", "set up evals for this". Not for before/after on an existing suite (use compare), one regression case (use test), scoring production traffic (use online-eval), or the ship/hold decision (use verify).
Collaborative interrogation that produces an implementation plan before any code is written. Explores the codebase and relevant docs first, asks one question at a time with a concrete recommended answer, grills the rationale behind documented decisions, flags fuzzy terminology, and walks a decision tree until shared understanding is reached, then writes a plan file. First step of the shipping pipeline; it creates plans, plan-reviewer stress-tests them, pr-creator opens the PR. Use when asked to "create a plan", "help me think through this", "plan this feature", "I want to build X", "grill me", "grill with docs", "understand the docs", "unpack the decisions", "brainstorm a spec", "what should the plan be", "think this through with me", or before starting any non-trivial implementation.
Chain-of-Verification (CoVe) prompting system. Converts lazy prompts into rigorous 4-stage verified output. Use for any code generation, debugging, or implementation task. Automatically invoked by wavybaby for medium/high complexity tasks. Reduces hallucinations and catches subtle bugs.
Use at a checkpoint after real friction — a task where something was repeatedly confusing, a skill misfired or failed to fire, or a workaround was invented that should not have been needed. Concerns turning friction into a change to the skills themselves, and knowing when the right change is to cut rather than add. Trigger at session end after substantial work, or when the same problem has now happened more than once. Do NOT use reflexively after routine tasks, or mid-task.
Interviews an unshaped idea into a verdict and a design document - decisions, flows, schema, contracts - that anyone can plan from without having been in the room. Use when the user says "research this", "help me understand this problem", "should we build this", "discovery", "explore this problem", or "tlc-discover". Do NOT use to cut a finished design into tasks, or to implement.
Performs semantic code intelligence and token optimization through context engineering and automated context packing. Use when reducing token overhead for large codebases, creating repository digests with Gitingest, packaging code context with Repomix, or tracing cross-file dependencies with llm-tldr.
End-to-end GECX/CXAS/CES conversational agent lifecycle -- build agents from requirements (PRD-to-agent), create and run evals (goldens, simulations, tool tests, callback tests), debug failures, and iterate to production quality. Use this skill whenever the user mentions GECX, CXAS, CES, SCRAPI, conversational agents, voice agents, audio agents, agent evals, pushing/pulling/linting agents, or agent instructions/callbacks/tools on the Google Customer Engagement Suite platform.
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.