chanakya-net/maestro-ai

1

save-tokens Ultra-compressed response mode. Cuts token usage by dropping articles, filler, pleasantries, and hedging. Uses symbol…

chanakya-net/maestro-ai

205

2

break-req Requirements discovery, dependency mapping, and technical constraint capture before implementation planning.

chanakya-net/maestro-ai

137

3

create-git-issue Create a PRD from resolved requirements, break it into tracer-bullet implementation issues, and publish via GitHub wh…

chanakya-net/maestro-ai

137

4

run-with-it Two-layer orchestration runtime — Main Orchestrator fetches all issues, plans execution order, maintains a rolling po…

chanakya-net/maestro-ai

136

5

tdd-implementation Test-first implementation discipline for assigned work using a strict red-green-refactor loop.

chanakya-net/maestro-ai

136

6

help-me-debug Use when a user reports a bug, failure, regression, unclear root cause, or needs evidence-backed diagnosis artifacts …

chanakya-net/maestro-ai

51

7

pair-colleague Use when a problem deserves two independent AI solution colleagues exploring alternatives together — the invoking age…

chanakya-net/maestro-ai

5