القائمة
AI screening review for PRs - preliminary check before human review. Do NOT use for deep multi-reviewer code quality audits (use /audit instead).
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
issue が build に投入できる形かを検分し、verdict (build-ready / needs-plan / needs-fix) と指摘を返す。起票には使わない (/issue)。PR のスクリーニングには使わない (/preview)。
Inspect whether an issue is in shape to hand to build, returning a verdict (build-ready / needs-plan / needs-fix) and the findings. Do NOT use to file an issue (use /issue) or to screen a PR (use /preview).
critic-design による敵対的批判を伴う設計探索。生き残った案を構造化 plan にまとめ、自己点検して呼び出し元に返す。plan の永続先は issue の Plan 節が唯一。計画意図のないコードベース調査には使わない (代わりに /research)。
Design exploration with adversarial critique by critic-design. Assembles the surviving approach into a structured plan, self-checks it, and returns it to the caller. The issue's Plan section is the plan's only persistent home. Do NOT use for codebase investigation without planning intent (use /research instead).
構造化されたタイトルと本文で GitHub Issue を生成する。単独で成立し、前段を要求しない。challenge / research の成果物が会話にあれば本文の根拠に使い、/think の plan 下書きがあれば `## Plan` 節へ移設する。issue 番号を渡すと、起票済みで Plan 節を持たない issue へ plan を転記する。
Generate GitHub Issue with structured title and body. Standalone; requires no upstream stage. When challenge / research artifacts exist in the conversation, they feed the body's evidence; when a /think plan draft exists, it is transferred into the `## Plan` section. Given an issue number, it transfers a plan into a filed issue that has no Plan section.
| name | preview |
| description | AI screening review for PRs - preliminary check before human review. Do NOT use for deep multi-reviewer code quality audits (use /audit instead). |
| when_to_use | スクリーニング, PRレビュー, プレビュー, preview PR, pre-review |
| allowed-tools | Bash(git:*) Bash(gh:*) Read AskUserQuestion Bash(ugrep:*) Bash(bfs:*) |
| model | opus |
| argument-hint | [PR URL or number] |
$ARGUMENTS is a URL, a number, or empty. If empty, detect from the current branch.
gh pr view $ARGUMENTS --json number,title,body,labels,files,url. On failure, retry without $ARGUMENTSgit status --porcelaingh pr checkout $PRNever include author in gh output fields.
# Diff
gh pr diff $PR
# Existing comments
gh pr view --comments $PR
# Inline comments
gh api repos/{owner}/{repo}/pulls/{number}/comments \
--jq '.[] | {file: .path, user: .user.login, comment: .body}'
| Label | Meaning | Severity |
|---|---|---|
[must] | Requires fix before merge | High |
[want] | Should fix, not blocking | Medium |
[imo] | Personal opinion, take or leave | Low |
[ask] | Question needing clarification | - |
[nits] | Minor style/formatting issue | Low |
[info] | Context sharing, no action | - |
| Rule | Detail |
|---|---|
| Format | [label] <observed behavior or risk>. <suggestion>. (file:line) |
| Concise | 3 lines for [imo]/[nits]/[info]; up to 5 for [must]/[want] with evidence |
| Respectful | Acknowledge effort, avoid commands |
| Suggestive | "Consider..." not "This is wrong" |
| Author-targeted | Comments may be posted verbatim - calibrate detail for the PR author |
Generate the report from the ${CLAUDE_SKILL_DIR}/templates/screening-report.md skeleton and emit it to the conversation.
| Rule | Detail |
|---|---|
| No auto-post | Never post comments to PR automatically |
| Abort on dirty | If uncommitted changes exist, warn and abort |
| Speed over depth | This is screening, not full audit |
| Verify before flag | Before [ask]/[want]+, trace the issue to a reachable runtime call site |
| Topic | File |
|---|---|
| Review Checklist | ${CLAUDE_SKILL_DIR}/references/review-checklist.md |