В каталоге 183 730 навыков в 14 категориях.
Developer tool that analyses feedback entries and generates an improvement backlog. Use when the developer says 'review...
Evaluate and act on code-review feedback with technical judgment. Use before applying external suggestions, especially w...
Process reviewer feedback from the docs-factory review site: fetch open review threads, locate each in this checkout, ed...
Convert repeated review findings into durable harness checks. Use when code review catches recurring agent mistakes that...
Find files approaching context limits and evaluate whether coupling-aware splits are worthwhile
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes,...
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prep...
Final QC gate for a rendered 9:16 video ad, run before it is published. One script checks what a machine can decide — ex...
CodeRabbit PR 리뷰 코멘트 분석 및 수정 적용
Applies saved code-review findings and updates artifact status. Use when fixing a review file, applying severity-filtere...
Grill the current changes — fan out parallel review subagents over the working-tree + branch-vs-base diff, resolve each...
Use this when running the post-review fix loop after a review/devil/critic agent emits findings, when authoring a .findi...
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context unti...
PR作成後に自律的に実行する必要があるフロースキルです。 Trigger: review, pr created, pr open
PR作成後に自動的に実行する必要があるフロースキルです
Follow-up review to verify corrections on a MR. Sequential execution to avoid memory spikes. Checks blocking issues, det...
Optionally validate and resolve findings from a solution-review or code-review report. Classifies each selected finding...
Process follow-up files from autonomous runs (ops:batch-execute, ops:get-to-work). Walks through each item, presents opt...
Example follow-up review skill for Claude Review Automation. Used to verify fixes after initial review.
Production-ready Go code review (QA + security + maintainability) for this project only.
Comprehensive code quality review through expert perspectives (Sandi Metz, Jeremy Evans, Kent Beck, Avdi Grimm, Gary Ber...
Output in the specified format when a review of specific markdown is requested.
Complete code review of a MR/PR with 7 sequential audits (Clean Architecture, DDD, TypeScript Best Practices, SOLID, Cle...
Review React/TS code for UI logic, Tailwind patterns, and render performance.
Comprehensive React/TypeScript frontend code review with optional parallel agents
Use when reviewing, debugging, or improving frontend code in this repo (website/ HTML, CSS, JS, service workers, PWA ass...
Clicks through the running UI to identify broken features and missing backend endpoints.
Review React, Next.js, Vue, Nuxt, Svelte, SvelteKit, Angular, or framework-agnostic web interfaces for functional states...
Complete code review of a fullstack MR/PR with 8 sequential audits (Clean Architecture, DDD, React Best Practices, SOLID...
Review computational protein or gene function predictions and fill PredictionReview YAML files using the COR/CNN/LSP/UNC...
Audit function visibility boundaries and rename misclassified public/private functions
Review an existing game codebase for architecture, performance, and best practices. Use when the user says "review my ga...
Automatically invoked when reviewing game simulation logs. Retrieves saved game data by ID and formats it for analysis.
Review a scope for gaps — what the surface promises but does not deliver — with evidence, then fill after confirm
Use to review a dispatch before handoff, requirements and plans before implementation, or code after implementation. Run...
Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when ex...
Gate skill for managing the PR review → Fix → re-review cycle. Run Code Review + Security Review in parallel, and auto-f...
Run an independent semantic review gate before merging non-trivial work, alongside CI and any configured automated code...
Independent multi-agent review that decides whether a frename change (code PR or design doc) may merge. Use before openi...
Quality gates and review processes
Analyzes and refactors code changes in the current git working tree (staged, unstaged, or recent commits). Ensures chang...
Audit labels, milestones, projects, and path-label ownership.
Review GitHub Skills exercises for learner experience, validation correctness, workflow safety, accessibility, and publi...
Comprehensive Go backend code review with optional parallel agents
Use when reviewing, debugging, or giving feedback on Go code in this repo (exercises/part2, website/tools, or any *.go f...
Codify project review rules as deterministic guards — ast-grep structural rules (with TDD-style rule tests) for mechanic...
Computes a PR's Tier floor and unplanned-changes list with a bundled read-only script, then writes the PR's Tier line an...
Review guidelines. Always use when Claude needs to review the code changes
コードレビューの基準とチェックリスト
各レビュアーエージェントが参照する詳細なレビュー観点（DB設計、セキュリティ、バックエンド、フロントエンド、インフラ）を定義
マージ済み PR のレビュー指摘を knowledge/buffer ブランチに自動収集。前回収集以降に main にマージされた PR を走査し、返信済み指摘を C*O に委任して knowledge/rules/docs に反映する。「...
First-pass strategic-orientation review of a repository. Produces an evidence-cited map (not a grade) calibrated to a re...
Perform a code review focused on bugs, risks, regressions, and missing tests.
Analyze how code changed over time. Use when investigating regressions, understanding why code was written a certain way...
Dedicated design-review subskill for a review workflow or direct invocation. Delegates evidence-based UI and document re...
Use when the user wants the project's linter / formatter / LSP diagnostics run as a check-only pass that emits findings...
Review one provider-generated mechanistic-hypothesis exploration report, including its dataset use, analyses, and artifa...
Review implementation changes for a given task against architectural standards. Use when reviewing a PR, evaluating rece...
Internal scope/classification engine composed by review-change (and reused by the audit skills): consumes the synthesize...
Use after hyperpowers:executing-plans completes all tasks - verifies implementation against bd spec, all success criteri...
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code r...
Use when triaging incoming ideas, requests, or notes into actionable work.
Infrastructure-focused review covering IaC, CI/CD, releases, migrations, logging, and observability. Spawns the senior-r...
Hold a class hierarchy to the is-a test — inheritance only for a true specialization,
Blind-review `TASK_GRAPH.md` and optional `SPLIT_OPTIONS.md`, then write `SPLIT_REVIEW.md` with a ready/not_ready verdic...
Use when receiving external input that needs structured intake before action — PR review feedback, code review comments,...
当需要抓取 Trustpilot 评论、分析评分分布、提炼正负面主题、生成竞品口碑洞察或为广告与转化文案提供评论情报时使用。适用于“抓某品牌 Trustpilot 评论”“分析差评主题”“导出评论 CSV/JSON”“做口碑竞品研究”等场景...
Scrape G2, Capterra, and Trustpilot reviews for your product and competitors, then extract recurring themes, objections,...
Review interface design for functions, classes, modules, components — naming, params, encapsulation, YAGNI, usability. T...
Comprehensive iOS/SwiftUI code review with optional parallel agents
Analyzes iOS test results from xcodebuild test runs. Use immediately after running xcodebuild test, when tests fail, whe...
Review KICS Infrastructure as Code scan results to identify exploitable misconfigurations. Use when analyzing KICS outpu...
Audit the knowledge/ base and the .claude/ skills, agents and workflows for staleness, self-contradiction, and drift fro...
Inside a drive, when it must reach the person, write them a brief they can act on: what we understood, what we built, an...
Review and maintain the knowledge base — find stale entries, orphan entries without connections, missing links between r...
Audit the two latency-critical paths for blocking work, redundant computation, and micro-optimization opportunities
Detect secrets, credentials, and sensitive data leaks before pushing to public repositories.
Synthesizes accumulated QA learnings from .qa-learnings/ledger.md into prioritized, actionable plugin improvements. Use...
Own .agents/review-lessons.md: record a LOCAL lesson, collect review feedback from the user's own past PRs, and re-evalu...
Library of lessons from past build-review loops — not a stage. Use when a review or fix round hits a specific case: a re...
Review code for correct use of the repo's third-party libraries — checks the scoped files against the version-specific c...
Analyze development-set disagreements between human annotations and one Coval text LLM judge, then propose a focused pro...
Detects common LLM coding agent artifacts by spawning four parallel subagents over the project or changed files. Scans f...
Comprehensive review and audit of uncommitted local code changes in git working copy (staged, unstaged, untracked). Use...
Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement sug...
Analyze Claude Code session transcripts for failure patterns and suggest fixes. Triggers "review logs", "session analysi...
レビュー→検証→修正の自動ループ。問題 0 件まで繰り返す。「/vibecorp:review-loop」「レビューして直して」と言った時に使用。
Run exactly 4 review-fix iterations using subagents
実装、レビューと反証、修正を、`[MUST]`と致命的な反証が無くなり検証が通るまで繰り返し、最後にセキュリティの監査を通す手順で、PRを出す前の変更を、親のセッションがローカルでもクラウドでも回すときに使う。
Consolida a fila de review e coordena correções por decisão do auditor no lote ou por indicação do usuário fora dele. Us...
Audit code for DRY violations, dead code, complexity, and consistency issues.
Review Makefiles for best practices, clean code, and proper structure. Use when reviewing, writing, or refactoring Makef...
Optimize review scores and leverage user-generated content for AI visibility and brand trust.
Scan for hot loops over raw buffers that would benefit from MCode (native C) optimization
Audit CLAUDE.md and .claude/rules/ for stale references, outdated architecture claims, and rules now redundant with stat...
Persistent Agentic Memory for code reviews. Remembers user rationale decisions (accepted or dismissed findings) with bra...
Request/execute structured code review: use after completing important tasks, at end of each execution batch, or before...
Analyze team code review activity and performance metrics from GitHub PRs. Use when: (1) User asks about team review sta...
Analyze Mattermost schema migrations against best practices and generate a review report. Pass a migration number/name a...
Nezávislé review naplánovaného milestonu s čistým kontextem — projde všechna jeho issues a posoudí tvar těl proti šablon...