← ClaudeAtlas

agent-orchestrationlisted

Coordinate a phased, multi-specialist workflow for complex software work that spans several build stages — design, planning, implementation, testing, and deployment. Use this whenever a request bundles multiple stages together, e.g. "design this feature, plan the implementation, and scaffold the code", "take this idea to a working skeleton", "help me build X end to end", or any time the user wants structured coordination across the full build lifecycle rather than one isolated step. Trigger even when the user never says "orchestrate" or "agents" — what matters is that the task clearly has several stages that benefit from being sequenced with explicit phase boundaries and checkpoints. Do NOT trigger for single-stage asks ("fix this bug", "write this function") — those are handled directly without orchestration overhead. Do NOT trigger when the person is signalling they are stuck, paralysed, or overwhelmed by the size of the work — even on a genuinely multi-stage build, that combination calls for overwhelm-brea
scoobydrew83/skills · ★ 0 · AI & Automation · score 78
Install: claude install-skill scoobydrew83/skills
# Agent Orchestration Act as a conductor for complex builds: move through the work in named phases, adopting a different specialist lens in each, and hand the user one coherent plan rather than a pile of disconnected outputs. ## Why phases Complex builds go wrong when someone jumps from idea straight to code. The design decisions that should have surfaced early (data model, boundaries, failure modes) instead surface late, when they're expensive to change. Phasing forces those decisions into the open in the right order. The phase boundaries double as natural checkpoints — good places to pause, confirm direction, and let someone with limited focus stop cleanly without losing the thread. ## The phases Each phase is a lens you step into, produce a concrete artifact from, then step out of. Don't run phases you weren't asked for — scope to the request. 1. **Design** — architecture and approach. Components, data shapes, key patterns, the main tradeoffs and why you'd land where you land. *Output: a short design note, with a diagram or component list where it helps.* 2. **Plan** — break the design into ordered, estimated tasks. Surface dependencies and the critical path. *Output: a task list with rough sizes.* 3. **Build** — scaffold the structure: files, component stubs, the skeleton that makes the shape real. *Output: a working skeleton, not a finished feature.* 4. **Test** — what proves it works. Cases, edge cases, validation approach. *Output: a test plan or s