Skip to content

Adonis0123/adonis-skills / skills/open-code-review-loop

open-code-review-loop

Unverified

Run a bounded OCR-delegation review-fix-re-review loop on a Git workspace until current evidence validates NO_FINDINGS. Use only when the user wants verified findings fixed and independently re-reviewed until clean with codex, claude-code, grok-build, or cursor-cli. Do not use for one-shot open-code-review-delegate or read-only review. A full loop request asks at most once for an unnamed Reviewer (recommending a product other than the host), then runs host mutation checks without further confirmation. Fail closed on missing ocr, reviewer mutation, skipped files, malformed output, stale evidence, or exhausted rounds.

evals/trigger-eval.json

View on GitHub
[
  {
    "query": "用 Codex 做独立 Reviewer,修复当前 diff 的问题,再反复 review 到 validated clean。",
    "should_trigger": true
  },
  {
    "query": "运行 open-code-review-loop:OCR 选文件,当前 host 修复,直到 NO_FINDINGS。",
    "should_trigger": true
  },
  {
    "query": "让 Claude Code review workspace changes,修完每个确认问题后重新审到 clean。",
    "should_trigger": true
  },
  {
    "query": "用 cursor-cli 读审,Codex 修复,再用新证据复核,最多三轮。",
    "should_trigger": true
  },
  {
    "query": "对当前 Git 工作区做 ocr delegate,fix verified findings and re-review until clean。",
    "should_trigger": true
  },
  {
    "query": "不要 commit;请把 OCR 发现的问题修掉,并让独立 Reviewer 复审到零 findings。",
    "should_trigger": true
  },
  {
    "query": "同一个 Claude Code 分成只读 Reviewer 和 Fixer 会话,循环到 validated NO_FINDINGS。",
    "should_trigger": true
  },
  {
    "query": "Grok Build 当 Fixer,Codex 当 Reviewer,处理当前改动并反复检查到 clean。",
    "should_trigger": true
  },
  {
    "query": "$open-code-review-loop current workspace,安全默认值,修复并复核直到通过。",
    "should_trigger": true
  },
  {
    "query": "OCR preview 后逐项修复可验证 finding,每次重建证据再 review,直到 clean。",
    "should_trigger": true
  },
  {
    "query": "只跑一次 open-code-review-delegate,用 Codex 返回 findings,不要修。",
    "should_trigger": false
  },
  {
    "query": "对当前 diff 做一次只读 code review,列问题就结束。",
    "should_trigger": false
  },
  {
    "query": "把 review findings 写进 .review-handoff,交给 Grok consult。",
    "should_trigger": false
  },
  {
    "query": "扫描 packages/core 的架构,修复后 rescan 到没有架构问题。",
    "should_trigger": false
  },
  {
    "query": "修复这个已知 failing test,不需要独立 review。",
    "should_trigger": false
  },
  {
    "query": "审查 commit abc123,只报告风险,不修改历史目标。",
    "should_trigger": false
  },
  {
    "query": "生成当前分支的 commit message 并 push。",
    "should_trigger": false
  },
  { "query": "给这份非 Git 文档做文字校对。", "should_trigger": false },
  { "query": "排查生产 API 500 的根因并给诊断。", "should_trigger": false },
  {
    "query": "用 ocr delegate 选择文件和规则,输出一次 reviewer 结果,不要进入 fixer。",
    "should_trigger": false
  }
]
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: 469kUpdated Claude CodeCodexVerifiedInstall
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: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 321kUpdated Claude CodeCodexVerifiedInstall