跳到正文
cccskills
Codex 官方免费在 GitHub 公开

implementation-final-review

Prepare independent review of a complete Guardrails change before pushing or updating a PR, using the repository adversarial-review procedure.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(3)

  • SKILL.md3.2 KB
  • agents/openai.yaml131 B
  • references/reviewer-brief.md2.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Implementation Final Review

Apply the adversarial-review procedure in AGENTS.md. Use the installed $adversarial-review skill when available; otherwise follow that inline procedure. This skill supplies a reusable brief, not another gate. It applies to repository workflow changes as well as runtime changes before a push or PR update.

Prepare the complete scope

Record the exact selected linked worktree, current HEAD, intended target, and comparison base SHA. Resolve the merge base with that target; for an explicitly requested stack, the previous PR's branch is the target. Inspect both the full stack and each incremental PR when reviewing several stacked changes together. Reviewers must check that every intermediate PR stands alone and references only files or skills present at that point.

Include all branch commits from the comparison base, staged and unstaged changes, and relevant untracked deliverables. Ordinary git diff omits untracked files; provide their paths and contents explicitly. Distinguish local working notes from shipped files. Include individual commit diffs so an endpoint diff cannot conceal unrelated changes. Freeze task content while reviewers run.

Read reviewer-brief.md when preparing dispatch. Fill it with the original outcome and constraints; do not include previous reviewers' conclusions or the implementer's preferred answer.

Dispatch and converge

For each round, spawn exactly two new independent, read-only subagents with fork_turns="none", both in this same worktree. Spawn both before waiting. Give each a complete self-contained brief. Reviewer A checks correctness, compatibility, security boundaries, and evidence. Reviewer B checks ownership, architecture, maintainability, and unnecessary complexity. Both inspect the entire change. They must not edit, modify Git state, or spawn agents.

Aggregate supported findings and classify them using AGENTS.md. Fix only in-scope blockers. Require two consecutive clean rounds on unchanged content, with a fresh pair in every round and no more than ten rounds. A substantive change resets the clean-round count. Do not substitute a self-review or reused agent when fresh reviewers are unavailable; stop before pushing and report the limitation. Do not create additional tasks or worktrees for reviewers.

Close the review

Run applicable verification, including focused evidence for repairs. Review any touched security surface and check Changesets requirements. Internal-only workflow changes need no package release note. Preserve commit hooks; if committing or later edits change reviewed content, repeat the invalidated checks and review.

Report scope, reviewer rounds, resolved in-scope findings, separate follow-ups, and actual verification results. Record evidence in working notes outside the shipped diff; no review-state certificate or component-credit reuse is needed. A clean local review does not authorize a merge or replace current-head CI.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

code-change-verification

Codex 官方免费

Select and run Guardrails verification for code, dependency, test, tooling, documentation, or repository-workflow changes.

中文简介正在准备中。当前显示原文说明。

openai/openai-guardrails-js1102026年10月21日 更新

implementation-kickoff

Codex 官方免费

Start or resume a requested Guardrails implementation or PR takeover in the selected linked worktree with bounded scope and verification.

中文简介正在准备中。当前显示原文说明。

openai/openai-guardrails-js1102026年10月21日 更新

implementation-strategy

Codex 官方免费

Choose bounded implementation scope and existing owning modules before Guardrails runtime, configuration, client, resource, streaming, Agents, or SDK compatibility changes and feedback fixes.

中文简介正在准备中。当前显示原文说明。

openai/openai-guardrails-js1102026年10月21日 更新

pr-draft-summary

Codex 官方免费

Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.

中文简介正在准备中。当前显示原文说明。

openai/openai-guardrails-js1102026年10月21日 更新

查看 openai 的全部技能

报告此技能的问题