All Skills

Changeset

Document $ISSUE

Fix Lint for PR $PR

Ralph Plan - Interactive Ralph Command Builder

Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

Official skill for MobileBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

Official skill for the MobileBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

Generate a conventional commit message by analyzing staged git changes. Use when the user wants to create, write, or generate a git commit message from their current staged diff.

Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.

End-to-end debugging for CopilotKit v2 — CopilotKitCoreErrorCode catalog (17 snake_case codes including runtime_info_fetch_failed, agent_thread_locked, agent_run_failed, tool_handler_failed, etc.), TranscriptionErrorCode catalog (9 codes), AG-UI SSE event tracing, web inspector lazy-loading, onError wiring on both CopilotKitProvider and CopilotChat, server-first debug discipline, and deprecated-alias → canonical cheat sheet. v1 CopilotKitErrorCode (SCREAMING_SNAKE) is kept for migration context only. Load when diagnosing a CopilotKit runtime or client failure, when interpreting an error code, when tracing missing events, or when wiring onError handlers.

Authoritative v1 → v2 migration playbook for CopilotKit. NO official codemod ships — this skill IS the migration tool. Covers the full rename table (17+ entries), import-path rewrite to /v2 subpaths, hook rename/split (useCopilotAction → useFrontendTool + useHumanInTheLoop, useCoAgent → useAgent, useCopilotReadable → useAgentContext), CopilotKit → CopilotKitProvider, runtime endpoint port, CopilotKitErrorCode (SCREAMING_SNAKE) → CopilotKitCoreErrorCode (snake_case), imageUploadsEnabled → attachments, publicApiKey unchanged (publicLicenseKey accepted as alias), @copilotkit/react-ui chat components relocated to @copilotkit/react-core/v2. Load when the user has a v1 CopilotKit codebase and wants to upgrade, or when you encounter useCopilotAction / useCoAgent / useCopilotReadable / CopilotKit provider / @copilotkit/react-ui imports.

Use for any CopilotKit question — adding it to an app, chat UI, frontend or server tools, generative UI, shared state, human-in-the-loop, agent frameworks (LangGraph, CrewAI, Mastra, ADK, PydanticAI, and others), the runtime, Intelligence, threads, voice, or diagnosing something that is not working. Do not answer from memory: this skill exists to point you at the current documentation and source, both of which you can read.

Upgrade a single-agent CopilotKit v2 app to multi-agent with per-panel useAgent({ agentId }), agent-scoped tools / renderers / context, key-remount when swapping agents in one chat slot, and thread-switcher UIs via useThreads. No useAgents() hook exists — discover the agent list via copilotkit.subscribe({ onAgentsChanged }). Load when moving from one agent to many, when agentId filters start appearing on tools, or when building a side-by-side multi-panel chat.

@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno, AWS Strands, MS Agent Framework, AG2, A2A), enable Intelligence mode for durable threads + websocket, register server-side tools via defineTool, and wire voice transcription. Uses the fetch-based createCopilotRuntimeHandler primitive — the Express/Hono adapters are discouraged. Load the reference under references/ that matches your task.

End-to-end quickstart for CopilotKit v2 — scaffold, mount the runtime, mount the provider, render chat, add the first tool. Canonical framework order is React Router v7 framework mode → TanStack Start → Next.js App Router, plus an SPA-without-runtime branch. Every branch uses createCopilotRuntimeHandler (the fetch primitive) — avoid createCopilotExpressHandler / createCopilotHonoHandler. Factory Mode BuiltInAgent with TanStack AI is the preferred default. Load when bootstrapping a new CopilotKit v2 app, adding runtime to an existing React app, or deciding which framework branch to wire.

Keeps the CopilotKit Intelligence landing page in sync when a new Intelligence feature ships or when Intelligence docs are added, renamed, or removed. Use when adding Intelligence capabilities, writing or moving pages under docs/intelligence, editing IntelligenceFeatureCards, or changing snippets/shared/intelligence/overview.mdx. Don't use for OSS-only frontend docs, Inspector pane callouts, or marketing-site copy.

Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.

Use when contributing to the CopilotKit open-source project — forking, cloning, setting up the monorepo, creating branches, running tests, and submitting pull requests against CopilotKit/CopilotKit.

Build a pure-client CopilotKit v2 SPA with NO server runtime by pointing CopilotKitProvider at CopilotKit Cloud via publicApiKey. This is the ONLY production-safe SPA path. Both agents__unsafe_dev_only and selfManagedAgents are dev-only aliases that leak credentials in production — never ship them. Covers Vite / plain React Router SPA wiring, getting a publicApiKey from cloud.copilotkit.ai, and the SSR non-concern. publicLicenseKey is an accepted alias for publicApiKey (publicApiKey wins when both are set). Load when the user has no backend and wants chat in a pure-SPA deployment (Vite, GitHub Pages, S3, etc.).

Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't use for docs-only Callout updates (load inspector-docs), runtime or core changes with no Inspector UI, showcase cell work, or reading Inspector as a consumer inside an app.

Locks customer-facing CopilotKit Intelligence docs to one approved name per concept. Use when writing, editing, or reviewing Intelligence docs, nav labels, signup labels, or image alt text in showcase/shell-docs. Don't use for renaming code identifiers, route slugs, env vars, API fields, or component names, or for docs that do not mention Intelligence.

Keeps CopilotKit docs pointing at shipped Inspector panes so readers open the overlay. Use when adding, changing, renaming, or removing an Inspector pane, tab, or overlay action in @copilotkit/web-inspector, or when editing docs that mention Inspector. Don't use for Inspector UI polish that does not add a pane, for CLI or agent-prompt copy, or for unshipped Inspector ideas.

Pre-deploy checklist for CopilotKit v2 apps — persistent AgentRunner (not InMemory) behind horizontal scaling, CORS, showDevConsole off, debug off, credentials:'include' for cookie auth, env-sourced secrets on edge runtimes, publicApiKey / licenseToken, dev-only-prop audit (agents__unsafe_dev_only, selfManagedAgents). Pointer skill — does NOT teach auth, rate-limit, or observability (those are server- framework concerns wired via the middleware skill). Load before any first production deploy of a CopilotKit v2 app.