Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Create a new CLI agent provider for CAO (CLI Agent Orchestrator). Use this skill whenever the user wants to add support for a new CLI-based AI agent (e.g., a new coding assistant CLI), integrate a new provider, or scaffold a provider implementation. Also use when the user asks about the provider architecture, what files to modify, or how providers work in CAO.
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
Supervisor-side orchestration patterns for assign, handoff, and idle inbox delivery in CAO
Worker-side callback and completion rules for assigned and handed-off tasks in CAO
Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by `cao workflow run`. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a separate, user-approved step.
Shared governance for the CCFA family: routing, trigger registry, task modes, handoff modes, source registry, privacy/evidence policy, ccfa.yaml, and artifact contracts. Use only when maintaining or auditing CCFA skills; not for ordinary research tasks.
Design, create, update, validate, and audit Codex/CCFA skills, trigger wording, resources, references, scripts, path privacy, family governance, and CCFA documentation SVG diagrams. Use for skill maintenance, new skill creation, routing conflict cleanup, Markdown/SVG docs maintenance, and release validation. Do not perform research writing or review work.
Equip the agent with the official Model Context Protocol "MCP Apps" builder Agent Skills (create-mcp-app, migrate-oai-app, add-app-to-server, convert-web-app) from github.com/modelcontextprotocol/ext-apps. Use whenever building a new MCP App from scratch, adding an interactive ui:// view to an existing MCP server (including a new ui://cao/* view in CAO), migrating an OpenAI Apps SDK app, or turning a web app into a hybrid MCP App. Pairs with cao-mcp-apps (CAO's operator/extend playbook).
Author a CAO workflow spec in-band, mid-session. Produces a YAML WorkflowSpec file on disk — the SAME artifact a human writes by hand — validated by the same `cao workflow validate` surface. Use when the user asks you to create, draft, or extend a multi-agent workflow. Authoring ends at a validated spec file; running it is separate.
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality