AI & Agents Agent Skills

Phase-agnostic orchestrator for parallel multi-agent work — brainstorm, plan, implement, review, research, or test.

Merge completed parallel agent work and trigger GitHub sync per increment.

Sync AgentOps skills.

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process.

Configures 2-Agent workflow between PM and implementation roles.

Use when detecting ambiguous user intent, hedging language, open-ended framing, personal context before requests, or when unsure whether…

Scaffold a new agent definition file inside an existing addon or framework

Scaffold a new behavior definition with BEHAVIOR.md and optional scripts inside an existing addon or framework

Scaffold a new command definition inside an existing addon or framework

Guide for creating DAAF agent definition files.

Agent spawning, lifecycle management, and coordination patterns.

Agent skill for goal-planner - invoke with $agent-goal-planner

Build applications where agents are first-class citizens.

Reviews code to ensure agent-native parity — any action a user can take, an agent can also take.

Meta-skill that orchestrates all agents of the ecosystem.

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

Audit and sync agent instruction files across all coding agent formats.

Agent skill for queen-coordinator - invoke with $agent-queen-coordinator

Tools are how AI agents interact with the world.

Set up codebase intelligence for AI agents.

Run external coding agents (Codex, Claude Code, OpenCode, native Grok Build, Gemini) as independent reviewers, stateful repository…