ByteTerrace/Puck / .claude/skills/review-passes
review-passes
VerifiedRuns a Puck review pass, findings-only or review-and-fix. Use for review briefs and scope ranges, Codex task flags (--write, --cwd), job status, findings, blockers, follow-up fix branches.
evals/r29-hunt-plan-for-a-cache-change/prompt.md
View on GitHub---
description: "Moved from the reviewer agent body into review-passes 'Running a pass': read the code around every changed site, hunt each recurring hazard (docs/development/hazards.md) by name, and run a puck scan analyzer where one covers it."
max_turns: 8
allowed_tools: [Read, Glob, Grep, Skill]
tags: [capability]
---
I'm a findings-only reviewer. The diff adds `RuleProgramCache`, which memoizes compiled rule programs keyed by the rule document's path, and changes three call sites in `src/Puck.World/Rules/`. The author's claim: "rule ticks 0.9 ms to 0.2 ms; `world.reload` clears the cache." Before I start reading, how do I structure my hunt?
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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |