632 skills · sorted by relevance
Write Chinese code review feedback that clearly distinguishes required fixes, suggestions, and optional advice. Use question and suggestion templates, organize review summaries, and follow guidance for mixed Chinese-English comments and commit messages.
Implement work described in a specification or tickets, checking types and running tests along the way. Review the completed changes with the code-review skill, then commit the implementation to the current branch.
Run a final pull request review using separate agents for each available review skill. Collect all reported issues into a numbered Markdown list, with a specific file path and line number for every finding.
Build or refresh a knowledge graph, a map of code relationships used for code review. Choose a full rebuild or an incremental update, then report the operation's status and summary.
Always use this skill before claiming any work is done, fixed, passing, or complete — even if it seems obvious. Also use when receiving code review feedback from any source (human or automated), when finishing a task or major feature, before committing or creating a PR, or when about to express satisfaction with work. Covers three practices: receiving feedback with technical rigor (no performative agreement), triggering code review via /code-review command or cook/fix pipelines, and verification gates (run the command, read the output, then make the claim). Never skip — the cost of false completion claims is higher than the cost of verifying. References: code-review-reception.md, requesting-code-review.md, verification-before-completion.md.
The English summary is being prepared. Showing the original description.
code-review-scanner と code-review-critic による2フェーズレビュー。 大きなPRや複雑な変更を丁寧にレビューしたいときに使う。 scanner がトリアージして重要な指摘だけ critic が深掘りする。 軽いチェックには /review（4並列専門レビュー）を使う。
The English summary is being prepared. Showing the original description.
Requests a code review from a separate agent after implementation or before merging. It provides the change summary, requirements, and commit range, then guides follow-up work according to the severity of the findings.
Review GitHub pull requests with specialized AI agents that check security, performance, architecture, and coding conventions. Generate actionable comments with suggested fixes, and connect review findings to automated approval or change requests.
Take a pull request through repeated code review and fixes, verify that automated checks pass for the latest commit, and combine its changes into one commit when merging. Conflicts with the request’s goal require confirmation.
Let the host AI agent review Git changes while ocr selects files and resolves review rules. Receive findings grouped by severity, plus coverage details showing which files were reviewed or skipped and why.
Review Git changes with the ocr command-line tool and a configured AI model. Get line-level findings grouped by severity for working changes, commits, or branch comparisons, with code fixes applied when explicitly requested.
Review a defined code change through independent code and architecture reviewers. Receive severity-rated findings with file and line references, concrete fixes, and a final recommendation on whether the change is ready to merge.
Comprehensive GitHub code review with AI-powered swarm coordination
The English summary is being prepared. Showing the original description.
PR 提出前にコードオーナー視点でフルレビューする。WHY の理解 → 設計 → AST/基盤型 → 実装（複数 Agent の順次レビュー）の順に、各フェーズでユーザーと対話しながら指摘を修正し、品質に問題がなくなるまで繰り返す。「/full-code-review」「フルレビュー」「レビューして」などの依頼時に使用。rsvelte（公式 Svelte コンパイラの Rust ポート）専用。
The English summary is being prepared. Showing the original description.
Dispatch code-reviewer agent for two-stage review. Use after completing implementation tasks.
The English summary is being prepared. Showing the original description.
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm
The English summary is being prepared. Showing the original description.
Multi-agent code review using the Pragmatic Quality framework. Orchestrates parallel review agents (CLAUDE.md compliance, bug scanning, git history, security) with independent confidence scoring to produce high-signal findings. Use when user runs /code-review, /review:code-review, requests a "code review", "review my changes", "PR review", or mentions "review diff", "review branch".
The English summary is being prepared. Showing the original description.
Cursorでreviewer等から割り当てられた観点を評価する担当用native入口。共有code-review-guidanceと担当referenceを読み、結果を親へ返す。
The English summary is being prepared. Showing the original description.
Code-review quality gate and test-enhancement rubric. Use when ROSE needs sharper review output contracts, severity and risk prioritization, evidence anchors, negative review cases, fixture or golden-output drift guidance, or a Chinese review report profile; do not use as a duplicate code-review agent or final PASS authority.
The English summary is being prepared. Showing the original description.
Review GitHub pull requests, or proposed code changes, with specialized agents covering security, performance, architecture, and style. Generate actionable comments, apply quality thresholds, and coordinate automated review workflows.
Review changed code from four angles: reuse, simplicity, efficiency, and whether fixes address the underlying mechanism. Applies suitable improvements within the reviewed scope while preserving intended behavior, and reports fixes or skipped findings.
Configure tools and skills for sub-agents before dispatching development tasks. Role presets cover implementation, planning, reviews, testing, and verification, with defined boundaries for what each agent should do and whether it may modify files.
Explore an unfamiliar codebase using a graph of code relationships. Inspect its structure, find functions and classes, trace calls and imports, follow execution paths, and locate large functions for closer investigation.
Review code changes for security, performance, correctness, and maintainability. Get findings tied to files and lines, severity ratings, practical suggestions with code examples, and a recommendation to approve, request changes, or discuss further.