Run a lead code review on the current branch or a given PR. Standalone entry point for the lead-reviewer agent.
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。
Standalone code review for any PR. Runs the full lead-reviewer analysis against the spec and project standards. Posting inline comments and the summary to GitHub is your choice — you are prompted at the end.
This skill targets wp-media/wp-rocket. Specs live at .TemporaryItems/Issues/wp-rocket/issues/<N>-spec.md.
If $ARGUMENTS is provided, use it as the PR number or URL.
Otherwise resolve from the current branch:
gh pr list --head "$(git branch --show-current)" --json number,url -q '.[0] | "\(.number) \(.url)"'
If no PR is found, tell the user and stop.
Get the base branch from the PR:
gh pr view <PR_NUMBER> --json baseRefName,body -q '{base: .baseRefName, body: .body}'
Extract the linked issue number from the PR body (Fixes #N, Closes #N, or a GitHub
issue URL).
If a linked issue number was found, check for a spec at:
.TemporaryItems/Issues/wp-rocket/issues/<N>-spec.md
If it exists, pass its path to the agent. If it does not exist, inform the user: "No grooming spec found — the review will check against project standards only (spec compliance section will be skipped)."
Invoke the lead-reviewer sub-agent with:
CURRENT_MODEL: "standalone"session_learnings: read Section 13 of AGENTS.md if it exists, else pass empty stringwp-media/wp-rocketSTANDALONE MODE — two differences from the normal pipeline run:
- Skip Step 5 (inline PR comments) and Step 5b (summary PR comment). Instead, output the full review report — findings table, blockers, nice-to-haves — as formatted Markdown in your response, in a section titled
## Review Report.- Skip the StructuredOutput JSON return. Return a short human-readable verdict summary instead: overall verdict, blocker count, and any open questions.
After the agent responds, display its ## Review Report and ask:
Post this review to PR #<PR_NUMBER>? Reply
yesto post inline comments + summary,noto finish here.
If yes — the agent posts inline comments (Step 5) and the summary comment (Step 5b)
using the normal dedup flow. The <!-- ai-pipeline:lead-review --> marker ensures a
later pipeline re-run updates in place rather than duplicating.
If no — confirm the review is complete and finish.
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。
概要と使いどころ
Adversarially review a grooming spec before implementation starts. Finds hidden risks, unvalidated assumptions, and missing dependencies. Standalone entry point for the challenger agent.
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。
Check a change against WordPress.org plugin rules and PHPCS standards.
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。
Update developer-facing documentation to reflect code changes on the current branch. Runs as an inline skill inside backend-agent and frontend-agent (step 2.5 of the internal sequence) after implementation and before DOD. Receives the explicit list of changed files from the implementation agent. No-op if no public API changes occurred.
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。
Run the Definition of Done checklist for the current wp-rocket branch and report PASS/WARN/FAIL with evidence. Two modes: layer 1 (self-correction inside backend-agent / frontend-agent — resolves FAILs before handoff) and layer 2 (independent orchestrator gate — fresh perspective after handoff). Pass layer: "1" or layer: "2" when invoking.
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。
Run a basic E2E behavioral probe — one primary scenario smoke test for the grooming step.
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。
Groom a single GitHub issue — produce an implementation spec and optionally post the grooming summary as a GitHub comment. Standalone entry point for the grooming-agent.
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。