Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Keep iterating on code changes until the tests pass, the build succeeds, or linting is clean. Runs in a tight loop of fix → run → check → repeat. Use when you want the agent to autonomously grind through test failures or build errors.
Diagnose Zapier Workflows skill and SDK CLI compatibility. Use when a workflow skill asks for a compatibility check, when SDK commands or flags are missing, when a workflow skill may be stale, or when updating workflow skills after an SDK CLI change.
Use when Ane types /improve-system, asks to "mine recent sessions", "what is the system getting wrong", "improvement loop", "trend the rejection rate" — or asks "where are my tokens going", "token audit", "why was that session expensive" (spend-audit mode) — or when the SessionStart maintenance nudge reports improve-system due (14-day cadence). Mines the QA logs and session history for recurring correction patterns, proposes system edits, and audits where token spend goes. Not for one-off bug fixes (/system-audit finds those), not for wiki integrity (/li lint), not for quality-posture grading (/grade-system).
Run an ordered sequence of pm-skills against one input, pausing for go/no-go and stopping on a failed or empty step. Accepts a saved prioritized action plan (Mode A) or an ad-hoc named chain (Mode B; the chain command routes here). Explicit invocation only; run --dry-run first while the native path is EXPERIMENTAL. To author a durable workflow instead, use utility-pm-workflow-builder.
End-to-end functional testing framework for Huawei Cloud skills — three-tier pipeline covering single-skill unit testing, multi-skill orchestration, and end-to-end full flow testing. Each phase produces structured JSON output with chain verification. Supports skill installation validation, functional analysis, CLI→SDK→API feasibility research, test case generation, real-environment execution with resource lifecycle, resource cleanup, multi-skill scenario orchestration, trigger-conflict detection, and consolidated reporting. Triggers include: 测试技能, 执行技能测试, 跑测试流程, 技能回归测试, skill test, run skill tests, test huawei cloud skill, verify skill, 测试华为云skill, 全流程测试, 编排测试, 技能完整性检查, skill-tester, 跑测试, 回归测试, 组合测试, 多skill编排, verification, e2e.
Keep a Codex orchestrator's delegation to an installed delegate skill pending until its registered relay completes, without model-driven progress polling. Use with a selected implementer delegate skill when Codex is the orchestrator and the delegation should wait in the background; sets up its MCP server on first use.
One-time project setup for creative writing: interview the author about the project, writing samples, and voice, then create the AGENTS.md, kb/ layout, and style files every writing agent reads. User-invoked; run it once when starting a project.
You MUST use this when lasting learnings from the current session should be recorded for future agents - pitfalls hit, mistakes the user corrected, conventions found, or commands that finally worked, whatever the conversation language - including when the user asks to write down what the session taught and at the end of the awf chain after finalize. Records them without asking in the project's gitignored docs/session-learnings/AGENTS.md, linked from the root CLAUDE.md or AGENTS.md, each with its quote and intended target; on a separate request, triages the accumulated notes into AGENTS.md, CLAUDE.md, the user's global instructions, or a stronger enforcement such as a check or a test, applying only the approved edits. Not for auditing or restructuring instruction files (maintaining-agent-context). Not for general memory or improvement requests for skills.
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for static/dynamic facts, and RAG for semantic search. Perfect for chatbots, assistants, and knowledge-intensive applications.
Distill a book into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "turn a book into skills" — i.e. wants a book's frameworks, principles, and methodologies extracted into atomic, reusable Claude skills that an agent can invoke in real-world situations. NOT for simple summarization, book reviews, or role-playing as the author (that is nuwa-skill's job).
Connect voice agents to WhatsApp Calling through Kapso. Use for Calling setup, signed call webhooks, inbound answering, outbound permission and dialing, native recordings and transcripts, or debugging signaling and media with Pipecat, Pipecat Cloud, ElevenLabs Agents, or another provider.
CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.
Use when creating, testing, optimizing, or implementing Agent Skills — the open format for packaging specialized knowledge and workflows into reusable skill directories that agents load on demand. Reach for this skill when building skills for agents, evaluating skill quality, optimizing skill descriptions for triggering, or integrating skills support into an agent product.
Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a tool to one, branch or loop between nodes, run steps in parallel, pause for user approval, or test an agent. Don't use for explaining how ADK works internally or designing its core components (use `adk-architecture`), for an agent that already runs but misbehaves (use `adk-debug`), for authoring a sample under `contributing/` (use `adk-sample-creator`), or for naming, typing, and formatting conventions (use `adk-style`).
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to “open a website”, “fill out a form”, “click a button”, “take a screenshot”, “scrape data from a page”, “test this web app”, “login to a site”, “automate browser actions”, or any task requiring programmatic web interaction.
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.