Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Register a custom LLM endpoint with your own API key for chat in Starchild. Use when adding a personal Anthropic, OpenAI, Grok, Qwen, DeepSeek, Meta (Muse Spark), NEAR AI, or Venice key as a chat model (e.g. add my Claude key, register DeepSeek, use Muse Spark 1.1)
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via <CopilotKit a2ui={{ theme }}>. Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives (A2UIProvider, A2UIRenderer, createCatalog) ship from @copilotkit/a2ui-renderer. Covers theme customization, createSurface dedup, action-bridge try/finally cleanup. Load when an agent emits A2UI operations (createSurface / updateComponents / updateDataModel), when wiring a2ui on CopilotRuntime, or when styling A2UI surfaces
Set up, update, or diagnose CodeGraph and ast-grep so coding agents can use semantic repository scope and structural syntax evidence automatically. Use when a repository needs an idempotent CodeGraph/ast-grep installation, stable tool and index migrations, MCP reconnection, persisted agent guidance, or a read-only setup diagnosis.
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold).
Control the user's currently open Chrome tab through the Playwriter CLI (no new browser launch). Use when you need to inspect live UI state, run scripted browser actions, capture console output, or reproduce frontend issues directly in the user's tab.
Diagnoses and fixes skills in the dotnet/skills repository that lose to their own baseline, fail to activate, time out, or return "no credible improvement". Use when an evaluation verdict is a regression or underpowered, when a skill regressed after a change, when /evaluate reports no results, or when deciding whether a weak skill should be strengthened or retired. Do not use for scaffolding a brand-new skill (use create-skill) or a brand-new eval (use create-skill-test)
Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator of the project spec. Triggers when the user asks to write a spec, start a new spec, distill a spec from existing code, add invariants, amend sections (§G, §C, §I, §V, §T, §B), or record a bug via backprop. Common phrasings: "write the spec for...", "new spec", "bug: ...", "amend §V.3", "distill spec from code", "spec this idea". Reads and follows FORMAT.md for the caveman encoding rules and pipe-table shape of §T and §B
Delegate a coding task to Oh My Pi (`omp`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Oh My Pi / omp - phrasings like "have omp implement X", "delegate this to oh my pi", "run it through omp", "use oh-my-pi to implement/fix/refactor" - or wants to run a queue of coding tasks through omp while staying the reviewer. DO NOT USE for tasks small enough to do inline, when the user wants the code written directly without delegating, or when they mean the original Pi CLI (`pi`) — that is pi-delegate.
Recommend available skills or MCP tools using TypeSafe Jev, or explicitly choose one next skill. Use when the user requests capability advice, candidate inspection, selection evaluation, or reusable host integration. Native client selection remains the default and fallback.
Use when the user wants to update, refresh, or reinstall the CopilotKit agent skills (the SKILL.md files that teach this agent about CopilotKit). Not for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit skills", "update skills", "refresh skills", "skills are stale", "skills are outdated", "get latest skills", "my copilotkit knowledge is wrong", "copilotkit APIs changed", "skills seem old", "wrong API names", "reinstall skills", "skills not working right", "update your copilotkit knowledge".
Turn ambiguous coding requests into verified Cursor Agent implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels hand-wavy or lost in details, or before committing to any agent-written plan.
Turn ambiguous coding requests into verified Codex implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).
MUST READ before deploying any ADK agent. ADK deployment guide — Agent Engine, Cloud Run, GKE, CI/CD pipelines, secrets, observability, and production workflows. Use when deploying agents to Google Cloud or troubleshooting deployments. Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or project scaffolding (use adk-scaffold).
Diagnose what state one open PR is actually in — unfinished plan steps, missing review, unresolved conversations, red CI, base conflicts, missing QA evidence, merge-ready — then run the matching chain of om-* skills in order and publish a status report. Use for "finish PR 123", "what is left on PR 123", "drive PR 123 to the end".
MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK observability guide — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations, and troubleshooting. Use when configuring monitoring, tracing, or logging for agents, or when understanding how a deployed agent handles real traffic.
Extend Pydantic AI agents with capabilities from pydantic-ai-harness — the Coder coding agent, file and shell tools in local or sandboxed workspaces (Modal, E2B, Sprites, smolvm), Code Mode, sub-agents and planning, memory and skills, context compaction, guardrails and spend limits, web research and browsers, hosted SaaS integrations, step persistence, and background agents on Render Workflows. Use when the user mentions pydantic-ai-harness or pydantic_ai_harness, imports a harness capability such as Coder, CodeMode, FileSystem, Shell, SubAgents, Memory, or ToolGuardrail, or wants a Pydantic AI agent that edits files, runs commands or agent-written Python, delegates, remembers, manages long context, stays within limits, or runs model and tool operations as chained Render task runs.
Use for Desktop Commander MCP capabilities — persistent shells and REPLs, long-running processes, filesystem beyond the workspace, structured files (.xlsx, .docx, .pdf, images) and large local data files such as CSVs, ripgrep search at scale, SSH, or cross-turn state.
Guide for creating effective opencode skills. Use for creating or updating skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Examples: - user: "Create a skill for git workflows" → define SKILL.md with instructions and examples - user: "Add examples to my skill" → follow the user: "query" → action pattern - user: "Update skill description" → use literal block scalar and trigger contexts - user: "Structure a complex skill" → organize with scripts/ and references/ directories - user: "Validate my skill" → check structure, frontmatter, and discovery triggers
Progressive Domain Crystallization (PDC) — a skill for building and maintaining a living domain knowledge base for any custom business application. Use this skill whenever the user is developing a business application and wants the AI to accumulate understanding of internal terminology, entities, relationships, and business rules over time — especially when that knowledge is not fully defined upfront and grows across sessions. Trigger on any of: "remember how our system works", "learn our domain", "track business entities", "build domain knowledge", "understand our terminology", "grow AI context over time", "domain model", "business rules documentation", or whenever a user says the AI doesn't understand their business-specific language or data model. Also use at the start of any session where a .tasks/domain.md file exists in the project — always read it before doing any work.
Turn ambiguous coding requests into verified Claude Code implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
Explains the product capabilities, applicability boundaries and latest official docs of 火山 AI audio-video interaction; generates or modifies VoiceChat/Aibot configurations; and helps users build, run and troubleshoot a minimal InteractAI VoiceChat Web Demo stage by stage.
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch for Claude Code or Cursor, 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.
Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus for learning, Sonnet for development/debugging). Prefers bash commands over reading files.
Classify finished pipeline runs from the configured tracker — clean single pass, hard recovery, loop checkpoints, or cause not recorded — and rank what the second passes cost in wall-clock hours. Read-only; hands the top cause to om-prepare-issue. Use for "pipeline retro", "why is our pipeline slow", "what is costing us rework".
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
You MUST use this when a request needs design decisions before code - new features, product or UX behavior, architecture changes, unclear success criteria, or two materially different approaches. Explicitly specified mechanical refactors, localized fixes with known expected behavior, and single-outcome config changes go straight to implementation.
Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source capture, precision passes, authoring, registration, and validation.
Run AI agent tasks remotely on Netlify using Claude, Codex, or Gemini. Use when the user wants to run an AI agent on their site, get a second opinion from another model, or delegate development tasks to run remotely against their repo.
Keeps a long Claude Code task on-track — breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills. Use when the model is repeating steps, re-reading the same files, second-guessing in circles, stuck or spinning, or running a long multi-step task at risk of exhausting context. Also use when the user says it is "looping", "going in circles", "stuck", "repeating itself", or asks for a handoff before running out of context.
Browser automation skill for AI agents using the mb CLI. Use when the agent needs to browse the web, take screenshots, scrape text, fill forms, click elements, record screencasts, run JS in pages, or audit designs. Triggers on: "browse", "open a page", "take a screenshot", "scrape", "fill form", "click button", "web automation", "record screen", "design audit", "accessibility check".
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.