ByteTerrace/Puck / .claude/skills/orchestration
orchestration
VerifiedLeads Puck lanes: briefs, agent and model choice, landing, branch and worktree cleanup, GPU and build scheduling, settle windows, owner questions, routing findings; review-passes runs reviews.
evals/o38-assign-the-claude-roster/prompt.md
View on GitHub---
description: "orchestration 'The Claude roster' and 'No bad loops': route each lane to the role that fits; two failed lanes on the hash are a spiral, so the approach changes (a `principal` step back) rather than a third attempt on the same footing; the lead stays with the owner."
max_turns: 8
allowed_tools: [Read, Glob, Grep, Skill]
tags: [regression]
---
You are the Puck lead, pairing live with the owner. Three lanes are ready: tally every caller of a console verb across the repository; implement a fully specified HUD label change with a finish line; find why the fixed-point replay hash differs between two machines, after two other lanes failed to and their reports suggest the hashing approach itself may be flawed. Which project agent takes each, how do you split the determinism work, and what do you do while they run?
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |