109 skills · sorted by relevance
Review pull requests at a specific commit using existing discussions, review plans, and executed checks. Produce a detailed Chinese review and a concise English verdict, then publish and read back the result to confirm its contents.
他の開発者のGitHub PRを下読みしてレビューコメント案を作り、人間が承認した内容だけを保留(PENDING)レビュー経由で投稿する。自作PRの修正ループには codex-pr-review-loop / claude-pr-review-loop を使う。
The English summary is being prepared. Showing the original description.
Reviews Cherry Studio code and documentation against product decisions, architecture rules, implementation checks, and conventions. It selects a review approach based on scope and available agents, then reports findings with guidance for fixes.
Review FastGPT pull requests in stages, starting with the intended change and key execution paths. Check security, performance, tests, and compatibility, then organize findings by severity into a review report and line-level comments.
Runs repeated PR reviews and fixes on the directories changed by the current branch. Uses an installed reviewer, checks editing scope after each round, and reports whether blocking findings were resolved or the loop stopped.
Decide whether a LoopX pull request is ready for approval or merge by checking review evidence for the current commit, required validation, and owner authorization. Record the decision and its supporting checks on the pull request.
PRに付いたレビューコメント(AI/人間)に対応し、返信とResolved化まで行う。Triggers on: '/pr-review-respond', 'レビュー対応して', 'レビューコメントに対応'
The English summary is being prepared. Showing the original description.
GitHub pull request review desk (Busabase App-in-Skill) using the gh CLI for real GitHub access, an AirApp review UI for human approval, and a trusted gh pr review execution step. Use when the user invokes /kelly-pr-review or $kelly-pr-review, asks to review GitHub PRs, generate a PR review batch, approve/comment/request changes through the review UI, or execute approved GitHub reviews.
The English summary is being prepared. Showing the original description.
Turn pull request changes, commits, and test evidence into a self-contained HTML guide. Explain the problem, system context, before-and-after behavior, and key code changes so reviewers know where to focus.
Review of a PR, branch, or your own uncommitted work across eight dimensions — security, correctness, test coverage, API/compatibility, usability, documentation, code quality, performance. Sizes the diff, reviews inline or fans out reviewers off a shared brief, verifies findings against code, reports a grouped list with a shape verdict, fixes on approval. Use for "review this PR", "/pr-review 3011", or a pre-flight self-review before submitting; add "thorough" for adversarial verification.
The English summary is being prepared. Showing the original description.
Drive ONE already selected open pull request in microsoft/apm to mergeable. Classifies copilot-pull-request-reviewer[bot] inline review, runs autopilot-pr-review-worker, folds (by default) every recommendation inside the PR's stated scope, pushes to the head branch or a superseding PR that preserves authorship via commit trailers, watches CI to green (`agent-merge` when that skill or `<agent_merge_state>` is present; otherwise `gh pr checks --watch`), and iterates under fixed caps until ready-to-merge, advisory-with-deferred, superseded, or blocked. Plan before any fold, push, or reviewer request. Never spawned by autopilot-pr-review-scheduler. That scheduler is advisory only. Invoke this skill by name when the caller asked to drive a PR to merge.
The English summary is being prepared. Showing the original description.
Queue microsoft/apm pull requests labelled `panel-review` (or an explicit named list) and fan them out through an isolated pool (default 2) of autopilot-pr-review-worker sessions. Advisory only. Never implements. Never composes autopilot-pr-merge-worker. Never review every open PR. Works in a local session, Copilot App automation, Cloud Agent, Remote Agent, or Agentic Workflow. Does not triage issues or open greenfield PRs.
The English summary is being prepared. Showing the original description.
Use when legacy prompts or older framework flows reference `pr-review-expert` and you need the modern runtime to resolve that capability cleanly.
The English summary is being prepared. Showing the original description.
自分の作業ブランチの PR 提出前セルフレビュー（diff の包括チェック）。「セルフレビューして」「消し忘れがないか確認して」「diff を徹底チェックして」「変更漏れ・削除漏れを見て」等の依頼時、PR 作成前の最終確認時に使用。境界: 他者 PR のレビューは pr-review、コードベース全体は codebase-review。
The English summary is being prepared. Showing the original description.
PR の特定レビューコメント（discussion）への対応（実装修正と返信）。PR URL に discussion の id を添えて「この指摘に対応して」と依頼された時、PR 番号と特定の指摘内容を示された時に使用。境界: PR 全体のレビューは pr-review、返信文の作成のみは ukwhatn-writing。
The English summary is being prepared. Showing the original description.
dependabot 設定（.github/dependabot.yml）の新規作成・整備。リポジトリから ecosystem を自動検出し、lockfile コンフリクトを避ける group 設計と security fast-track を備えた設定を生成する。dependabot 設定の作成・見直し・追加の依頼時、/setup-dependabot 実行時に使用。境界: Renovate は対象外。dependabot が作った PR の対応は pr-review 等の通常フロー。
The English summary is being prepared. Showing the original description.
タスク進行中に、続行・即出荷・方向転換のどれが妥当かを、fresh なサブエージェント1体に状況サマリだけ渡して裁定させる。/gal-check 実行時、「ずれてない？」「このまま続けていい？」「ギャルに聞いて」等の方向確認の依頼時、外部レビューループの打ち切り条件に達した時に使用。成果物の中身は読まない。境界: 成果物のレビューは pr-review、計画の穴の対話検証は grilling。
The English summary is being prepared. Showing the original description.
PR を Draft で作成する。変更をローカルで動かして確かめ、画面が変わるならスクリーンショットを gh の --attach で貼り、PR テンプレートを全セクション埋めて対象 repo の既存 PR の分量に揃え、出した後は CI・レビュー・マージを Monitor で見張る。PR 作成の依頼時、実装が一段落して PR 化する時、/create-draft-pr 実行時に使用（gh pr create を直接実行しない）。引数でベースブランチを指定できる。境界: 個別レビューコメントへの対応は pr-comment、PR 全体のレビューは pr-review、複数 PR 規模の計画は plan-feature-prs。
The English summary is being prepared. Showing the original description.
コードベース全体のレビュー・監査。perf/sec/test/arch/cq/docs の6観点を並列委譲し、優先度付き issue ファイルと観点サマリをメモリディレクトリに生成する。コードベース全体の監査・定期レビュー・リリース前品質確認の依頼時、/codebase-review 実行時に使用。境界: PR 単位は pr-review、自ブランチの提出前確認は self-review。
The English summary is being prepared. Showing the original description.
Review a GitHub pull request from multiple perspectives in parallel, output only findings, then let the user pick which to fix in the same session. Use when the user asks to review a PR by number, mentions "PRレビュー" / "PR review" with a number, or invokes `/pr-review <number>`. Fans out subagents for absolute-rules, stop-slop, security, architecture, code-quality, testing, and ai-antipattern.
The English summary is being prepared. Showing the original description.
Route a PR review request to the correct tool — code-review plugin (quick parallel scan across all dimensions) or pr-review-toolkit (deep-dive on a specific quality dimension such as type design, error handling, test quality, comments, or simplification). Use when the user asks for a code review, PR review, or mentions a specific quality concern before creating a PR.
The English summary is being prepared. Showing the original description.
Review GitHub pull requests and GitLab merge requests for security, test gaps, compatibility, and performance risks. Trace affected code and services, then produce a prioritized report with suggested fixes and a structured review checklist.
Check open GitHub pull requests for overdue reviews, inactivity, and requested changes without an author response. Send a single Slack summary identifying blockers and the people responsible for the next step, while leaving GitHub unchanged.
Review code changes on GitHub or GitLab and investigate failed CI checks, the automated checks run on code. Use logs to guide fixes, push commits, and share review comments and repair summaries.