coact

Use this skill whenever the user wants to add, refactor, or audit the agent runtime — the loop that drives multi-step tool-using LLM conversations, optionally with durable execution for long-running, resumable agents. Triggers include "add an agent loop", "make my agent multi-step", "stop the agent from looping forever", "resume an agent after a crash", "run an agent in the background", "agent handoff to sub-agent", "add Pydantic AI / LangGraph / OpenAI Agents SDK", "wrap my agent in Temporal / DBOS / Inngest / Restate", "stream agent state to the UI", "cancel a running agent", "human-in-the-loop approval mid-run", or any task on the agent orchestration or durable execution layers. Read BEFORE writing a custom agent loop.

Use this skill whenever the user wants to add, audit, refactor, or maintain an embedded AI assistant (chat + agentic) inside their own application. Triggers include phrases like "add an AI assistant to my app", "wire up a chatbot", "embed Claude/GPT into my UI", "make my app operable by AI", "audit my AI assistant integration", "what should I add next for my AI assistant", or any task that touches multiple of {chat UI, system prompts, skills, MCP tools, agent runtime, command dispatch → MCP, multi-tenancy, observability, billing} together. This is the entry-point skill — it audits the codebase, identifies the layer in question, and routes to the focused sub-skills (ai-assistant-chat-ui, ai-assistant-prompts-skills, ai-assistant-command-mcp, ai-assistant-agent-runtime).

Use this skill whenever the user wants to add, modify, or audit the chat UI / streaming / wire-protocol layer of an embedded AI assistant. Triggers include "build a chat UI", "add streaming responses", "render tool calls in the chat", "add thread CRUD", "show markdown in the assistant", "branch conversations", "make the AI response copyable", "switch from polling to streaming", "embed Claude into my React app", "set up assistant-ui", "use Vercel AI SDK in my app", "expose chat over SSE from FastAPI", or any task on the frontend chat layer of a React + Vite + shadcn application. Read this skill BEFORE writing any new chat component, runtime hook, or SSE endpoint.

Use this skill whenever the user wants to expose application operations to an AI assistant via tools/function-calling/MCP. Triggers include "make my app operable by AI", "expose my commands to Claude/GPT", "build an MCP server for my app", "bridge command dispatch to MCP", "annotate tools for AI", "add tool approval flow", "scope tools per user", "stop the AI from calling destructive operations without confirmation", "compose multiple MCP servers", "use py2mcp", "use FastMCP", "use the MCP TypeScript SDK", or any task that wires application operations to the agent's tool surface. Look for command dispatch (any of: @command decorator, CommandSpec, acture, wrapex, py2mcp, a registry of typed handlers). If absent, prefer adding one first.

Use this skill whenever the user wants to add, refactor, manage, or audit system prompts, user-editable prompts, or "skills" (Anthropic-style) in an AI assistant. Triggers include "set up a prompt registry", "version my system prompts", "add a skill to my assistant", "make prompts editable by non-engineers", "auto-select the right skill", "write a SKILL.md", "integrate Langfuse for prompt management", "add prompt evals to CI", "manage prompt versions", "load context dynamically per request", "store prompts in git", or any task involving the SSOT for instructions an LLM consumes. Read this skill BEFORE creating any prompts/ or skills/ directory or wiring up a prompt store.

Use when inspecting or moving between the skill/agent layers with coact — auditing what extras an agent adds over its skill, estimating the token cost of fanning out a fleet before you spend it, enumerating a project's reusable AI assets, or harvesting an agent back into a skill. Triggers on "diff this skill and agent", "what does this agent add", "how much will a fleet cost", "is multi-agent worth it here", "list the skills/agents/tools in this project", "inventory", or "turn this agent back into a skill".

Use when turning an existing .claude/skills/ skill into a .claude/agents/ agent definition with coact — i.e. COMPLETE. Triggers on "complete a skill into an agent", "make an agent from this skill", "what extras would coact add", "fill in the coact frontmatter block", or wanting a dry-run/provenance preview before generating an agent. Covers complete(), plan_completion(), the additive coact frontmatter, and the no-LLM default.

Use when developing, debugging, reviewing, or extending the coact package itself (this repo) — adding emit targets or realize backends, touching COMPLETE/REALIZE, the additive coact frontmatter, the policy, or the LLM/synthesis paths. Covers the architecture, the invariants that must not be broken, the open-closed extension points, and the testing/tooling gotchas specific to this repo.

Publish a Python capability as a deployable AI-chatbot integration with coact — package tools (module:function refs, live functions, or a skill's coact: mcp block) into a Claude Desktop one-click .mcpb extension (a local stdio MCP server). Use when the user wants to create, build, package, or deploy a Claude connector / plugin / MCP server / .mcpb / Desktop Extension / "integration" from existing Python code or a skill — e.g. "make an mcpb", "package these functions for Claude", "turn this into a Claude extension/connector", "publish a local MCP server", "wrap my tools as a Claude Desktop extension". Also use to draft an integration from a natural-language description ("describe an integration", "I want a Claude connector that can…") via `coact describe`. Also covers REMOTE claude.ai connectors (a hosted Streamable-HTTP MCP server + OAuth 2.1) via the `claude-remote-connector` target — use when the user wants a cloud-reachable connector, not a local install.

Use when turning a coact agent definition (or a skill) into something that actually runs — i.e. REALIZE. Triggers on "realize this agent", "run a coact agent", "materialize an agent for Claude Code", "make an aw/Agent-SDK runnable from a skill", "run a definition through LiteLLM/LangGraph/CrewAI", "expose a skill's tools as an MCP server", or choosing between the host/sdk/litellm/langgraph/crewai/mcp backends and their cost. Covers realize(), the backends, install extras, and the fan-out cost gate.

Start here for coact — the package that turns your .claude/skills/ into .claude/agents/ definitions (COMPLETE) and those into running agents (REALIZE), plus tooling to see and move between the layers (diff/estimate/inventory/back) and scaffold a starter fleet. Use when someone asks "how do I use coact", "what can coact do", "turn my skills into agents", "reuse my AI stuff across the agent stack", or isn't sure which coact capability they need. Routes to the focused coact-complete / coact-realize / coact-analyze skills.

Analyze a captured UX evidence bundle (screenshots + DOM + a11y tree) for usability and accessibility issues.