本文へ移動
cccskills
無料GitHub で公開

review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.

インストール方法を見る

含まれるファイル(4)

  • SKILL.md6.9 KB
  • checklist.md7.7 KB
  • greptile-triage.md8.1 KB
  • TODOS-format.md1.6 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Step 0: Detect base branch

Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.

  1. Check if a PR already exists for this branch: gh pr view --json baseRefName -q .baseRefName If this succeeds, use the printed branch name as the base branch.

  2. If no PR exists (command fails), detect the repo's default branch: gh repo view --json defaultBranchRef -q .defaultBranchRef.name

  3. If both commands fail, fall back to dev.

Print the detected base branch name. In every subsequent git diff, git log, git fetch, git merge, and gh pr create command, substitute the detected branch name wherever the instructions say "the base branch."


Pre-Landing PR Review

You are running the /review workflow. Analyze the current branch's diff against the base branch for structural issues that tests don't catch.


Step 1: Check branch

  1. Run git branch --show-current to get the current branch.
  2. If on the base branch, output: "Nothing to review — you're on the base branch or have no changes against it." and stop.
  3. Run git fetch origin <base> --quiet && git diff origin/<base> --stat to check if there's a diff. If no diff, output the same message and stop.

Step 2: Read the checklist

Read .Codex/skills/review/checklist.md.

If the file cannot be read, STOP and report the error. Do not proceed without the checklist.


Step 2.5: Check for Greptile review comments

Read .Codex/skills/review/greptile-triage.md and follow the fetch, filter, classify, and escalation detection steps.

If no PR exists, gh fails, API returns an error, or there are zero Greptile comments: Skip this step silently. Greptile integration is additive — the review works without it.

If Greptile comments are found: Store the classifications (VALID & ACTIONABLE, VALID BUT ALREADY FIXED, FALSE POSITIVE, SUPPRESSED) — you will need them in Step 5.


Step 3: Get the diff

Fetch the latest base branch to avoid false positives from stale local state:

git fetch origin <base> --quiet

Run git diff origin/<base> to get the full diff. This includes both committed and uncommitted changes against the latest base branch.


Step 4: Two-pass review

Apply the checklist against the diff in two passes:

  1. Pass 1 (CRITICAL): SQL & Data Safety, Race Conditions & Concurrency, LLM Output Trust Boundary, Enum & Value Completeness
  2. Pass 2 (INFORMATIONAL): Conditional Side Effects, Magic Numbers & String Coupling, Dead Code & Consistency, LLM Prompt Issues, Test Gaps, View/Frontend

Enum & Value Completeness requires reading code OUTSIDE the diff. When the diff introduces a new enum value, status, tier, or type constant, use Grep to find all files that reference sibling values, then Read those files to check if the new value is handled. This is the one category where within-diff review is insufficient.

Follow the output format specified in the checklist. Respect the suppressions — do NOT flag items listed in the "DO NOT flag" section.


Step 5: Output findings

Always output ALL findings — both critical and informational. The user must see every issue.

  • If CRITICAL issues found: output all findings, then for EACH critical issue use a separate AskUserQuestion with the problem, then RECOMMENDATION: Choose A because [one-line reason], then options (A: Fix it now, B: Acknowledge, C: False positive — skip). After all critical questions are answered, output a summary of what the user chose for each issue. If the user chose A (fix) on any issue, apply the recommended fixes. If only B/C were chosen, no action needed.
  • If only non-critical issues found: output findings. No further action needed.
  • If no issues found: output Pre-Landing Review: No issues found.

Greptile comment resolution

After outputting your own findings, if Greptile comments were classified in Step 2.5:

Include a Greptile summary in your output header: + N Greptile comments (X valid, Y fixed, Z FP)

Before replying to any comment, run the Escalation Detection algorithm from greptile-triage.md to determine whether to use Tier 1 (friendly) or Tier 2 (firm) reply templates.

  1. VALID & ACTIONABLE comments: These are already included in your CRITICAL findings — they follow the same AskUserQuestion flow (A: Fix it now, B: Acknowledge, C: False positive). If the user chooses A (fix), reply using the Fix reply template from greptile-triage.md (include inline diff + explanation). If the user chooses C (false positive), reply using the False Positive reply template (include evidence + suggested re-rank), save to both per-project and global greptile-history.

  2. FALSE POSITIVE comments: Present each one via AskUserQuestion:

    • Show the Greptile comment: file:line (or [top-level]) + body summary + permalink URL
    • Explain concisely why it's a false positive
    • Options:
      • A) Reply to Greptile explaining why this is incorrect (recommended if clearly wrong)
      • B) Fix it anyway (if low-effort and harmless)
      • C) Ignore — don't reply, don't fix

    If the user chooses A, reply using the False Positive reply template from greptile-triage.md (include evidence + suggested re-rank), save to both per-project and global greptile-history.

  3. VALID BUT ALREADY FIXED comments: Reply using the Already Fixed reply template from greptile-triage.md — no AskUserQuestion needed:

    • Include what was done and the fixing commit SHA
    • Save to both per-project and global greptile-history
  4. SUPPRESSED comments: Skip silently — these are known false positives from previous triage.


Step 5.5: TODOS cross-reference

Read TODOS.md in the repository root (if it exists). Cross-reference the PR against open TODOs:

  • Does this PR close any open TODOs? If yes, note which items in your output: "This PR addresses TODO: <title>"
  • Does this PR create work that should become a TODO? If yes, flag it as an informational finding.
  • Are there related TODOs that provide context for this review? If yes, reference them when discussing related findings.

If TODOS.md doesn't exist, skip this step silently.


Important Rules

  • Read the FULL diff before commenting. Do not flag issues already addressed in the diff.
  • Read-only by default. Only modify files if the user explicitly chooses "Fix it now" on a critical issue. Never commit, push, or create PRs.
  • Be terse. One line problem, one line fix. No preamble.
  • Only flag real problems. Skip anything that's fine.
  • Use Greptile reply templates from greptile-triage.md. Every reply includes evidence. Never post vague replies.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Delete the `-bak` backup branches that `/prepare-merge` leaves behind, local and on origin, once the work they back up has merged. Use when the user says "remove my bak branches", "clean up bak branches", "delete the backups", or "/clean-bak-branches".

日本語の概要は準備中です。原文の説明を表示しています。

Actual-Chat/actual-chat562026年10月13日 更新

create-pr

無料

Use when work on a branch is finished and the next step is a pull request — "create a PR", "open a PR", "push and PR this", "/create-pr" — when a draft PR should be marked ready for review — "mark the PR ready", "undraft it", "it's ready for review" — or right after either has happened and the team has not been told about it yet.

日本語の概要は準備中です。原文の説明を表示しています。

Actual-Chat/actual-chat562026年10月13日 更新

Search Google Cloud (GKE) server logs of the DEV environment (dev.voxt.ai). Use when troubleshooting anything that needs the server side of the story — stream stalls, RPC peer changes / reconnects, watchdog closures, mesh/node churn, pod restarts — or when the user says "check GCP logs", "check server logs on dev", or gives a dev.voxt.ai timeline from a client console log.

日本語の概要は準備中です。原文の説明を表示しています。

Actual-Chat/actual-chat562026年10月13日 更新

Search Google Cloud (GKE) server logs of the PROD environment. Use when troubleshooting a production incident that needs the server side of the story — stream stalls, RPC peer changes / reconnects, watchdog closures, mesh/node churn, pod restarts — or when the user says "check PROD logs", "check production server logs", or gives a production timeline from a client console log.

日本語の概要は準備中です。原文の説明を表示しています。

Actual-Chat/actual-chat562026年10月13日 更新

memories

無料

What this project has already learned the hard way, and where any new such fact belongs. Two jobs. (1) Routing: this project keeps NO per-project Claude memories — read this before writing anything down, and pick a durable home from the list here. (2) An index, by area, of non-obvious facts worth knowing before you guess: debugging rigs and measurements that lie, iOS/WebKit and the tethered iPhone, the Windows app, production and deployment, and general codebase traps. Use before setting up a browser- or server-driven debugging session, when a bug reproduces only on iPhone, in Safari or in the Windows app, before changing deployment configuration or reading store/crash data, when something behaves unexpectedly and you are about to guess why, and whenever you are tempted to record a fact for later.

日本語の概要は準備中です。原文の説明を表示しています。

Actual-Chat/actual-chat562026年10月13日 更新

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).

日本語の概要は準備中です。原文の説明を表示しています。

Actual-Chat/actual-chat562026年10月13日 更新

Actual-Chat のスキルをすべて見る

このスキルの問題を報告する