AI Agent Workflow Collection

Assesses team fitness and composes agent teams. Use when "set up a team", "team for this", "should I use agents", "design a team", "how many agents", "agent team".

Shape output for a human working through agents. Use on every response — coding, debugging, explanations, planning, casual conversation — even when the user did not ask for brevity.

Use when the user asks to explain or understand a code change, diff, branch, or PR — or to catch up on a change an agent built before reviewing or shipping it. Triggers on "what changed here", "walk me through what you built", "help me understand this before merging".

Use when adding or changing a skill, fragment, hook, or runtime file in this repo — including deciding which unit a new capability should be.

Use as load-bearing work lands, or when the user asks to debrief, hand off recent work, or check what they actually own versus what AI carried. Triggers on "debrief", "what do I own", "hand over", "hand it back", "over", and recently shipping a load-bearing decision the human has not reasoned through.

Use when two or more concurrent subagents are running and one finishing should immediately drive the next, or when spawned subagents go idle unnoticed, linger as stale processes the human must poll or hand-kill, or leave dependent work stalled behind them. Triggers on eager parallel dispatch, subagents that need reaping, poll-only fan-outs that never wake the orchestrator.

Define how unsupervised work will be judged before it runs. Use when execution is an autonomous loop or a long unbabysat agent run that optimizes toward a metric. Triggers on "autonomous loop", "let it run", "optimize until", "overnight run", "unsupervised", "set a goal".