В каталоге 183 730 навыков в 14 категориях.
(ePost) Ultrathink edge cases, then parallel verify with reviewers
自分が書いた差分を、そのリポジトリの規約と設計の境界に照らしてレビューし、must / imo / nits の3段階で会話へ返す。GitHub へは投稿しない。ユーザーが「レビューして」「軽く見て」「セルフレビューして」「/review-...
코드 품질 리뷰
Perform a comprehensive code review of either the current branch or a specific GitHub pull request.
Review code changes for correctness defects, regressions, security risks, data-integrity problems, concurrency hazards,...
Review a diff, branch or pull request for real defects, and verify each finding before reporting it. Use this for any re...
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code fo...
Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and pr...
A thorough multi-agent audit of an existing codebase against the development skills, with one sub-agent per domain. Use...
Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage ga...
Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing...
Read-only workflow for code review, PR review, or feedback on a diff, branch, or specific files. Produces structured, pr...
Assist a human reviewing a pull request or branch locally — diff a source branch against its target (auto-detected or fr...
Review implementation for maintainability, evolvability, anti-slop, and human complexity; emit `M#` findings and durable...
Review implementation fidelity against `PLAN.md` and `AMENDMENTS.md`; emit `PS#` findings and validation-fact gaps into...
Review code quality — separation of concerns, magic numbers, DRY, maintenance issues
Use when reviewing code for quality, security vulnerabilities, and best practices
Open Review of code quality
Use this skill when you need a final review pass to ensure code changes are as simple and minimal as possible. This agen...
Find a code spec's Halt risks before a run: a reader that never wrote the tickets checks every one against the spec, the...
Meticulous local code review ladder (uncommitted changes, a branch, or files) using /recon and /debug-mantra to test eac...
[Review & Quality] ⚡⚡⚡ Scan & analyze the codebase.
Review overall codebase health, architecture, and patterns using Google's engineering principles. Takes optional focus a...
comming soon...
Final code/plan review using Codex CLI. Use as the last review step after sonnet.
Comprehensive validation of collector bot packages using 8 parallel specialized agents. Use to validate existing collect...
Audit comments for staleness — stale identifier references, outdated behavioral claims, and unverifiable flags
Address PR review comments from reviewers (amazon-q-developer, copilot, humans). Use when the user wants to see and resp...
Review and clean up code comments for necessity, accuracy, non-duplication, clarity, and concise explanation of rational...
Process code review comments left in `.review/comments.json` by the Neovim review plugin. Triggered when the user says "...
Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope),...
Quick quality review of staged changes for pre-commit validation. Checks Ruby best practices and flags critical issues.
Use when the user says 'review loop N times', 'build then review', 'fix and re-review', 'review loop until clean', 'have...
Use when the user asks to review finished uncommitted work, commit it and push it in one run. Not for planning or implem...
Steer sequence-building toward short, side-effect-free comprehensions and generator
Audit config registry for dead keys, no-op configs, stale descriptions, and organizational opportunities
Find hardcoded constants that should be user-configurable via config registry
Prüft Topic-JSON-Inhalte auf argumentative Qualität, Ausgewogenheit und intellektuelle Redlichkeit. Verwenden beim Erste...
Review Aztec smart contracts for correctness, security, and best practices. Use proactively after writing or modifying A...
Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide busines...
Contract risk analysis, obligation mapping, and clause review. Use when the user asks to review, analyze, or check a con...
Review SPARTA conversation transcripts and grading with full transparency. Use when asked to review conversations, show...
Review a marketing page or lead form for conversion friction across intent match, value clarity, evidence, interaction c...
Use when coordinating code reviews, agent reviews, and approval workflows across Jira and Harness
Foundational workflow for preparing and structuring detailed reviews(architecture, API, code quality).Triggers: review w...
Code review best practices and checklist
Review code for bugs, incorrect state transitions, races, and failure handling, including closed-world branching, unknow...
Analyze code for bugs and correctness problems using strict determination criteria. Returns structured findings without...
覆奏机制,尚书省汇总完毕提交时触发,门下省事后审查执行结果是否忠于原旨
Verify test coverage for code changes. Analyzes diff against main and reports coverage gaps.
Write code_tour.md, a leveled checklist to understand the code, docs, and tests of a dir
Audit every Critical section for necessity, scope, and duration — find stale or overly broad holds that block the main t...
Unified multi-dimensional code review with automated fix orchestration. Routes to session-based (git changes), module-ba...
Audit the D3D11 interop layer for per-frame waste — buffer allocations, redundant state calls, GPU readback efficiency
Review database migrations, data models, and persistence code for data safety rollback/locking risks, data loss, constra...
Review database migrations, backfills, and data transformations for production safety. Validates ID mappings, catches sw...
Scans for PII leaks, unsafe logging, and real customer data in non-prod environments.
Reviews SQL migrations and Spark scripts for performance and safety across T-SQL, PG, and Spark.
Find and plan removal of dead code (unused functions, variables, unreachable paths)
Internal tech-debt transform pass of the agentic-workflow review pack — composed in-turn by review-change and product-au...
Audit debug logging and diagnostics for ungated disk writes, missing coverage, and overhead
Comprehensive pre-release review pipeline. Runs /review-health, /review-arch, /review-security, /review-perf, /review-a1...
Review deferred verification items. Use when you want to check or clear the deferred review queue without waiting for pr...
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius de...
Compare frontend options and review bundled helper instructions.
Detect package managers and discover outdated or vulnerable dependencies. Returns structured findings without upgrading....
Multi-provider AI design review skill. Submits UI screenshots + design tokens to vision-capable LLMs for structured UX a...
Internal UI/UX design review pass of the agentic-workflow review pack — composed in-turn by review-change and product-au...
Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency,...
Use when reviewing a working-tree diff or specified local Git range and reporting only actionable, evidence-backed findi...
Reviews the current diff against the repo's quality preset, reporting findings as file:line with a severity. Use to self...
Parallel specialist code review — 6 focused agents (correctness, design, performance, safety, docs, complexity) diverge...
Category: Django Development
Render any document the user needs to review (design docs, plans, story bibles, proposals, reports) as a self-contained...
Review all project documentation for correctness, completeness, and freshness. Spawns a doc-maintainer agent to audit an...
Complete review of a documentation-focused MR/PR with 5 sequential audits oriented for documentation projects (markdown-...
Documentation consistency reviewer that checks alignment between code implementation and documentation. Use when user re...
Review documentation for quality, clarity, SEO, and technical correctness. Optimized for Docus/Nuxt Content but works wi...
Step-by-step guidance for docs.
Audit documentation accuracy against code changes. Reports discrepancies without modifying files.
Review and clean technical documentation (Markdown/README/runbooks/ADRs). Improve clarity, consistency, accuracy, and ma...
Review and improve documentation with parallel evaluation and iterative improvement loop.
This skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies...
Audit README, AHK deep-dive, and LLM development pages for broken links, stale numbers, missing features, and new highli...
Use this skill when asked to review the package documentation of the Go implementation of Feather.
ドキュメントの技術的正確性・事実確認を行う際に使用。記載内容の妥当性検証、事実誤認チェック、Web検索による裏付け確認に役立つ。
Specialist subagent for .NET/C# code quality review. Use when: reviewing C# code for correctness, async/await patterns,...
Comprehensive draft story review with parallel specialist sub-agents. Spawns PM, UX, and SM agents to review stories fro...
Favour duck typing: have code depend on the attributes and methods (the protocol) an
3D-Tabellenreview konkret durchführen: jede Zeile in allen drei Perspektiven prüfen und bewerten. Normen: §§ 174 ff. 176...
Comprehensive Elixir/Phoenix code review with optional parallel agents
Hold encapsulation to Python's conventions: a single leading underscore for internal
Use when the user asks to review changes, review a diff, sanity-check a PR before merge, or verify uncommitted work agai...
Activate when the user provides reviewer or co-author feedback (annotated PDF, pasted comments, or reviewer report) and...
Catch two related correctness pitfalls: confusing value equality (==) with object
Example code review skill for Claude Review Automation. Customize this template for your project's review standards.
Explain Harness FME experiment results: winner determination, statistical significance, guardrail metric impact, and dat...
Adversarial, security-first review of a pull request from an EXTERNAL or untrusted contributor — a fork PR, a first-time...
Use when the user says "review the feature", "/review-feature", "audit the feature logic", "is the feature complete", "c...
Reviews a whole suite of `.feature` files against each other and reconciles them. This is cross-file consistency auditin...