Каталог навыков агентов

Comprehensive code review for quality, security, performance. Triggers on 'review code', 'code review', 'check this PR',...

Clade coverage-driven project review — walks every VERIFY.md checkpoint, fixes failures in-session, converges when all p...

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when t...

Adversarial code review — checks against PRD, LLD, coding standards, and async safety. Proves issues with tests before r...

Review a proposed customer code change against its intended outcome and operational risks. Use for a diff or PR review;...

Review, audit, sanity-check, look-at any review-able target. Triggers on a GitHub PR URL (fetched via the gh CLI), a loc...

中文网文审稿与追读诊断。当用户要审稿、检查剧情漏洞、查伏笔有没有回收、人设是否前后一致、爽点密度够不够、或想知道"读者为什么追读会掉/这章为什么留不住人"时使用。产出数据化诊断报告和可执行的修改建议。

Use when the GATE is green, before simplification, review along two parallel axes (Standards + Spec) then a pass by the...

Perform a structured code review by composing validation checklists from relevant atoms based on what code changed. Load...

Review skill. Read ~/.claude/skills/gstack/review/checklist.md before acting.

Use when reviewing code, handling review feedback, or posting a review to a GitHub PR — 14-dimension quality analysis fo...

Review spec-forge generated documents (tech-design + feature specs) for quality, completeness, and internal consistency....

Review code quality, security, and maintainability before committing. Use when reviewing code changes, checking code qua...

Use when applies to product pages, local business pages, recipes, apps, books, and any page that aggregates user reviews...

../../../engineering-team/playwright-pro/skills/review/SKILL.md

condition: Modelo de ML indisponível ou não carregado

Review a GitHub pull request; defaults to the current branch's PR when no number is given

Perform a code review on recent changes

Pre-landing PR review with two-pass checklist. Pass 1 critical: SQL safety, race conditions, LLM trust boundaries, enum...

対象ファイルの種類を自動判定し、適切なレビュースキル（review-mobile / check-mdx / check-links / code-review / design-review / critical-review）を実行して...

このリポジトリのコードレビュー。「レビューして」「#123 をレビューして」「この差分見て」という依頼で使う。

Comprehensive code review workflow - parallel specialized reviews → synthesis

Analyzes a codebase's modularity imbalances using the Balanced Coupling model and produces a review of design issues. Us...

Reviews PR(s) using comprehensive review guidelines including security, correctness, clean code, TypeScript, React patte...

The lead's review of a lane's finished branch before it merges. Runs code-kit verify on the branch, checks the work agai...

Two-axis Standards and Spec review core of review-phase. Use when the review-phase Run Review gate runs its axes.

Review code changes against WooCommerce iOS standards

Run a lead code review on the current branch or a given PR. Standalone entry point for the lead-reviewer agent.

Review the current diff for correctness, security, and convention drift before shipping. Use after finishing a unit of w...

落地前 PR review。按 diff 对照 base branch，查 SQL 安全、LLM 信任边界、 条件副作用、文档漂移、scope drift，并在适合时自动修复简单问题。 (gstack)

コードレビューを実施。プルリクエストのレビュー、コード品質チェック、改善提案の際に使用。

Review and judgement router: evidence-based local code review, self-reflection, idea critique (roast, challenge), human-...

Run a deep code review across the manifold-csg crates

Multi-agent review with lesson-calibrated reviewers, runtime verification, and severity classification

Orchestrate a stepwise SCI/narrative/systematic review workbench. Use when the user wants to start, resume, audit, or ve...

Initialize a medical SCI review project. Use when setting up the review workbench, recording topic, disease/domain, revi...

Narrow and lock the scientific question for a medical review. Use when converting a broad topic into PICO/PECO, PCC, or...

Build reproducible search strategies for PubMed, Web of Science, Embase, Cochrane, Scopus, CNKI, and preprint databases....

Execute or document literature searches and create a reproducible search log. Use when running database searches, export...

Organize literature exports for Zotero or another reference manager. Use when importing search results, deduplicating, t...

Identify candidate research gaps and refine review angle from retrieved literature. Use after pilot search or initial sc...

Build a benchmark library of high-quality target-style reviews. Use when selecting 5-10 model articles to learn structur...

Classify retrieved papers into review themes and screening categories. Use when grouping references by clinical question...

Track full-text PDF acquisition for included or high-priority references. Use when downloading, locating, naming, and au...

Produce structured deep-reading notes from full-text medical papers. Use when extracting methods, results, mechanisms, l...

Build an evidence matrix for clinical, mechanistic, or bioinformatics review synthesis. Use after deep reading to map cl...

Build a manuscript outline from evidence matrix and benchmark reviews. Use when creating section hierarchy, argument flo...

Plan review figures, tables, graphical abstract, flowcharts, pathway/workflow diagrams, evidence tables, PRISMA flowchar...

Draft or revise the introduction of a medical SCI review using funnel logic. Use when writing background, knowledge gap,...

Draft thematic main-body sections for a medical review. Use when synthesizing mechanisms, clinical evidence, omics findi...

Draft the discussion, limitations, future directions, and conclusion for a medical review. Use after main sections are d...

Verify citations, reference formatting, DOI/PMID accuracy, source quality, publication year, and claim-citation alignmen...

Match a review manuscript to target journals and audit fit. Use when choosing SCI journals based on scope, article type,...

Prepare a medical review submission package. Use when assembling title page, cover letter, highlights, graphical abstrac...

Draft structured reviewer responses and revision plans for medical review manuscripts. Use after peer-review comments, e...

Final personal quality-control audit for medical SCI reviews and translational manuscripts. Use before submission, major...

Route, merge, and validate review-writing skills for a medical literature review workbench. Use when the user asks to co...

Curate, verify, insert, format, and audit high-quality references for medical SCI review manuscripts. Use when the user...

Drive a medical review manuscript through a stepwise writing chain from title and abstract to introduction, body section...

Screen candidate papers, classify inclusion status, obtain or flag PDFs, prepare RIS/NBIB exports for Zotero, and use Zo...

Build high-quality flowcharts, pathway/workflow SVG diagrams, BioRender/Figma redraw plans, graphical abstracts, and Exc...

Organize a medical review manuscript project into a GitHub-ready archive with manuscript drafts, literature search logs,...

Run and initialize a six-step medical SCI review workbench distilled from Codex/Claude review-course videos and external...

Check a screen in the browser at real sizes, like a designer would. Use when the user says "review this screen", "check...

Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and de...

Accessibility audit. Dispatches an accessibility auditor to identify WCAG conformance gaps, prioritize by user impact, a...

Internal accessibility review pass of the agentic-workflow review pack — composed in-turn by review-change and product-a...

A specialised skill for detecting accessibility barriers in React/HTML.

Nezávislé review architektonického rozhodnutí (ADR) s čistým kontextem — posoudí soulad s konvencemi a tvarem logu i kva...

Rigorous sequential-audit code review with a dedicated security block and cited pedagogical lessons. Customize for your...

Review code changes against the active intent's outcomes and constraints. Use after writing code meant to implement an i...

Load this skill when auditing that the codebase matches a SKELETON.md or ITER_NN.md planning document, including variant...

Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when anothe...

Nezávislé review agenta s čistým kontextem — posoudí konformitu s konvencemi (pojmenování podle rolí projektu, povinná p...

Use when an existing GitHub pull request or GitLab merge request already carries review comments from an automated revie...

Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, ver...

Use this skill when reviewing code to ensure features are agent-native - that any action a user can take, an agent can a...

Assemble a bounded readiness review for one frozen agent candidate before a production release, pilot, promotion, or mat...

Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an ag...

Audit security boundaries in AI agents, multi-agent systems, MCP integrations, autonomous workflows, and copilots with s...

Detect agentic coding infrastructure in a project: CLAUDE.md, AGENTS.md, installed skills, MCP servers, hooks, and cross...

Review recent conversations to find improvements for AGENTS.md files.

Creates minimal, effective AGENTS.md files using progressive disclosure. Triggers on "create agents.md", "refactor agent...

Audit the tracked `AGENTS.md` tree against best practices, write `.agents/AGENTS_TREE_REVIEW.md`, and propose cleanup, c...

Guidance on combining findings from multiple review agents into actionable recommendations

Review code base for undocumented AHK engineering accomplishments.

Scan for AHK v1 patterns that slipped into the v2 codebase

Review changes made by AI editors (Codex, Claude, etc.). Run git diff, lint, security scan, tests, and provide a code re...

Review code for AI slop patterns. TRIGGER when user says "review for AI slop", "check for AI patterns", "clean up AI cod...

Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code co...

Comprehensive code review using all 30 review checklists. Spawns the senior-review-specialist agent for thorough file-by...

Holistic cross-GDD review — contradictions between systems, dominant strategies, economic imbalance, cognitive overload,...

Review all game design documents together for cross-system consistency and design-theory risks.

Holistic cross-GDD consistency and game design review. Reads all system GDDs simultaneously and checks for contradiction...