Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Operate Open WebUI models, chats, knowledge bases, channels, messages, threads, and files using OPEN_WEBUI_API_KEY. Use when listing models, reading or updating chat history, working with knowledge bases, fetching channel messages, or posting Markdown to Open WebUI.
Runs a project's scheduled health checks in order — syncing the main worktree's main branch with origin, refreshing installed skills, then triaging the Linear backlog to pick and ship a next ticket. Use when the user asks to run the project health check, do the scheduled/periodic project checks, run routine project maintenance, or when this is invoked as a recurring scheduled agent. The Linear team (name or key) to triage is provided when the skill is invoked; an optional date cutoff for ignoring stale tickets may also be provided.
Load when reflecting on AI collaboration quality or tracking growth over time. Analyzes session history to surface how deeply you think with AI tools and whether your orchestration sophistication matches your cognitive depth. Provides actionable nudges to push toward more strategic work.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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
Use when you need to produce a D2 decision document (RFC/Decision Doc) for a Spec Pack, and must mandatorily consume the project knowledge base and `{FEATURE_DIR}/requirements/solution.md#impact-analysis`; applies to situations where, under time or authority pressure, it is easy to read only the index, skip the full text of affected modules/ADRs, silently ignore missing inputs or fail to write a `CONTEXT GAP`, and omit the "align with the existing system" self-check.
Use for latest/current/recent/today/yesterday/tomorrow questions, changing models, versions, prices, schedules, executives, laws, weather, scores, or other time-sensitive facts. Ground answers in clock and timezone, verify live when needed, and convert relative dates. Do NOT use for stable history.
Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.
Run an end-to-end webtoon production harness — a 27-agent / 4-phase Claude Code agent team that takes a single episode from trend research to a finished vertical-scroll viewer. Use when the user wants to produce a webtoon episode: research popular webtoon trends, write a dialogue-heavy, high-tension, twist-every-episode scenario, render character reference sheets first, render 50+ panels per episode with in-image speech-bubble (Korean dialogue) baking via codex-image, run a generation–validation loop, and assemble a vertical-scroll viewer. Triggers on: webtoon harness, make a webtoon, produce a webtoon episode, webtoon scenario to image, next episode, redraw panel, stronger twist, webtoon trend research. Web data gathering for the trend-research phase routes through the `scrapling` skill. Pure webtoon recommendation/critique is answered directly.
Guide the creation of a new AI agent skill for the foundation-skills repository. Generates the skeleton of the SKILL.md and docs file, applies repository conventions (frontmatter, versioning, structure). Use when the user asks to create a new skill, write a skill, add a skill, or generate a skill skeleton.
Companion skill for the Agent-Friendly APIs course on Vercel Academy. Use when the user mentions "agent-friendly APIs", "API documentation", "llms.txt", "the course", "teach me", or asks about agent-friendly docs, documentation patterns, or building Claude Code skills in the context of the Academy course.
Refine an existing implementation plan with a second iteration. Re-analyzes the codebase for gaps, missing tasks, and wrong dependencies. Use after /aif-plan or to improve an /aif-fix plan. Optional +check flag validates refinements via a fresh-context subagent.
Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev/review session could not safely resolve alone); you and the human disambiguate the frozen spec so the story can be re-driven. Invoked as /bmad-loop-resolve <story-key>. Unlike the automated dev/review sessions this session is interactive — a human is present and you SHOULD ask.
This skill should be used at the very start of every session and when the user asks to "check my environment", "run a pre-flight check", "validate setup requirements", "is my system ready", or before any cofounder project initialization. It verifies the working directory, dev tools, git state, and remote configuration.
Create Confluent-specific skills for external users. Use this skill when users want to create, build, or author a new skill related to Confluent Cloud, Confluent Platform, Apache Kafka, WarpStream, Flink, Connectors, Schema Registry, Tableflow, CDC pipelines, or any Confluent product. Skills can be use-case focused (like data enrichment, CDC to Tableflow, stream processing workflows) or component-specific (like a Flink skill, Schema Registry skill, or Connector skill). Do NOT use this skill when users want to directly use Confluent products (e.g., build a pipeline, write a producer, deploy Flink SQL) — use the appropriate product-specific skill instead. This skill is specifically for creating new skills, not for using existing ones.
Generates a Markdown bug report for an IBM watsonx.data integration session. User can invoke directly. The agent MUST propose it (and must wait for explicit acceptance) after 3 or more consecutive calls to the same tool or the same sequence of tools result in a failure or the same error. Skip for non-watsonx.data integration sessions.
Canonical guide to authoring Claude Code hooks, both prompt-based and command-based. PROACTIVELY activate for: (1) creating a hook, (2) adding PreToolUse or PostToolUse hooks, (3) validating tool use, (4) implementing prompt-based hooks, (5) blocking dangerous commands, (6) event-driven automation, (7) configuring hooks.json, (8) using ${CLAUDE_PLUGIN_ROOT}, (9) hook matchers and filtering, (10) debugging hooks that do not fire. Provides: hooks.json schema, event reference, security guidance, and examples.
Carga en la sesión actual el playbook de un rol de equipo ágil aumentado por IA (PM, BA, UX, ARCH, LEAD, TESTER, DEV) y adopta ese rol para el resto de la conversación, sin crear ni invocar ningún agente nuevo. Use when the user runs /init-agent, or asks to become/act as a specific team role (PM, BA, UX, Architect, Lead, Tester, Developer) in the current session.
Operate a selective workspace for complex reasoning, long tasks, repository engineering, coordinated agents, and authorized security analysis. Use when work requires durable state, evidence, cross-file consistency, or recovery; keep direct answers lightweight.
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), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK).
MemOS Cloud long-term memory integration for AI apps. Use for addMessage, searchMemory, Chat API, knowledge base, feedback, deletion, filters, Tool Memory, Skill, multimodal, and async mode. Helps with "接入 MemOS", "给应用加记忆", "add memory to my app", "MemOS API errors", and Cloud API/SDK integration code.
Build production OpenAI Realtime voice agents and low-latency spoken interactions with live audio sessions, WebRTC or WebSocket transport, voice activity detection, tool/function calling, prompt design, logging, consent, privacy, safety, latency, and cost controls. Use for speech-to-speech agents and live voice UX; do not use for separate request-based transcription, text-to-speech, or offline audio generation work.
Authoring Pi TypeScript extensions - ExtensionAPI, custom tools, commands, UI hooks, resources_discover, `registerProvider()`, and how extendResources merges skill paths after base reload. Use when the user builds or debugs pi extensions, registers tools, adds /commands, hooks events, integrates TUI components, or ships extension examples. Use for "how do I extend pi", "extension API", "registerTool", "registerProvider", even if pi-mono is not mentioned.
The capability index of the product-builder pack — which skill answers which capability, and where each one lives once installed. Load it to route a request to the right skill of the pack instead of guessing, and to see what the pack does not cover.
Provides a clickable Airtable link whenever the agent has touched user-visible Airtable content. Use after every MCP call that creates, updates, lists, searches, or returns records, schema, or interface pages — bases, tables, fields, records, or pages. Hand off the most-specific URL the agent's tool calls have proven access to — prefer single-record URLs over table URLs, table URLs over base URLs, and interface page URLs when the user's access is restricted to pages. Format as a markdown link with a descriptive label. Construct URLs only from IDs the tools actually returned — never synthesize IDs to round out a URL. Compose this skill from any workflow skill that affects Airtable content.
Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth. Implements two feedback loops: the inner loop (detect, verify, recover) runs within a session via plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing (active recovery on failure), simplify-and-harden, and self-improvement. The outer loop (inspect, encode, regress-test) runs across sessions via learning-aggregator, self-improvement, and eval-creator. pre-flight-check bridges the two by surfacing accumulated knowledge — past heals and learnings — at session start. Handles standard, orchestrated-batch, CI, and outer-loop pipeline variants. Does not replace individual skills; dispatches to them.
Audit and refine a skill repository, a single skill, a workflow framework, or an eval set. Covers design quality, context engineering, purpose fit, evidence discipline, and boundary clarity — the structural dimensions that assertion-based testing does not reach. When a target_repo is provided, continues into compatibility review, extraction, and integration planning. Complements skill-creator by providing deep design-level judgment after functional tests pass.
GitHub Spec-Kit integration for constitution-based spec-driven development. 7-phase workflow (constitution, specify, clarify, plan, tasks, analyze, implement). Use when working with spec-kit CLI, .specify/ directories, or creating specifications with constitution-driven development. Triggered by "spec-kit", "speckit", "constitution", "specify", references to .specify/ directory, or spec-kit commands.
Contextual help and onboarding for the swain skill ecosystem. Use when users ask about swain — what skills exist, how to use them, what artifacts are available, how workflows connect, or when they need a quick reference. Also invoked after swain-init to orient new users. Triggers on: 'how do I...', 'what is...', 'help', 'what can swain do', 'show me the commands', 'I'm confused', 'where do I start', any question about swain skills, artifacts, or workflows, and after project onboarding completes.
Run an autonomous QA cycling workflow: test, diagnose, fix, and repeat until the quality goal is met or a concrete blocker is proven. Use when the user explicitly invokes `$ultraqa`, `ultraqa`, asks for QA cycling, test/build/lint repair, or a parallel review burst. Also tolerate the common typo `$ultaqa` by treating it as `$ultraqa`.
Detects .NET intent for any C#, ASP.NET Core, EF Core, Blazor, MAUI, Uno Platform, WPF, WinUI, SignalR, gRPC, xUnit, NuGet, or MSBuild request from prompt keywords and repository signals (.sln, .csproj, global.json, .cs files). First skill to invoke for all .NET work — loads version-specific coding standards and routes to domain skills via `dotnet-advisor` before any planning or implementation. Do not use for clearly non-.NET tasks (Python, JavaScript, Go, Rust, Java).
Use when working with TopicLab / 他山世界 / OpenClaw world threads, world.tashan.chat, openclaw bootstrap or skill URLs, heartbeat, notifications, topic replies, skill installation through TopicLab, points progress, or any request to connect, test, or operate the user's OpenClaw instance. Prefer topiclab-cli for all supported TopicLab tasks.
Search for and install community Mini Program AI Skills. Triggered when users want to add AI capabilities to an existing Mini Program project but are unsure which community Skills are available, or do not want to build from scratch. Search, view details, and install from repositories such as TencentCloudBase/awesome-miniprogram-skills.
Use the Agent Auth CLI (auth-agent) to discover providers, connect agents, manage capabilities, and execute operations. Use when the user wants to interact with an Agent Auth provider from the terminal, authenticate an agent, execute capabilities, or manage agent connections.
Use the Agent Auth MCP tools to discover providers, connect agents, manage capabilities, and execute operations through the MCP protocol. Use when working inside an MCP-enabled environment (Cursor, Claude Code, etc.) and need to authenticate agents, execute capabilities, or interact with Agent Auth providers.
Multi-platform, multi-channel notification skill for AI code agents. Sends notifications (sound, macOS alert, Telegram, Email, Slack, Discord, DingTalk) when the agent needs user interaction or completes a task. Supports Claude Code, GitHub Copilot CLI, Cursor, Codex, Aider, and OpenCode.
One-command setup for a new AI coding agent. Installs the essential starter skills (find-skills, agent-browser, karpathy-guidelines, ui-ux-pro-max, caveman, arabic-design, design-taste-frontend, remotion-best-practices) across 70+ agents, plus the core Claude Code plugins/MCPs (frontend-design, superpowers, code-review, playwright, github, claude-md-management). Use when the user is setting up a new project or a fresh agent and asks for "the skills/MCPs I should start with", a "starter pack", or "set up my agent".
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.