Навыки: Тестирование

Run exactly 4 review-fix iterations using subagents

Consolida a fila de review e coordena correções por decisão do auditor no lote ou por indicação do usuário fora dele. Us...

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Audit CLAUDE.md and .claude/rules/ for stale references, outdated architecture claims, and rules now redundant with stat...

Request/execute structured code review: use after completing important tasks, at end of each execution batch, or before...

MDXコンテンツのモバイル視認性・可読性をレビューする。表の不適切な使用、数式の可読性、解説の冗長さを検出し修正案を提示する。 Use when user asks to [モバイルレビュー, 表示確認, 可読性チェック, /review-...

Comprehensive multi-dimensional skill reviews across structure, content, quality, usability, and integration. Task-based...

Test combinatorial interactions between install options, launch modes, and user journeys

Deep code/plan review for architecture, subtle bugs, and test quality. Use after sonnet review for thorough analysis.

Zoom out and find whole classes of performance, bug, or anti-pattern issues hiding in plain sight

Open zoom out and find whole classes of performance, bug, or anti-pattern issues hiding in plain sight

Review ownership.manifest for coupling that can be reduced

Audit the D2D paint pipeline for per-frame waste — allocations, recomputation, redundant API calls at 120-240fps

Comprehensive PDF extraction fidelity auditor for extractor pipeline quality. Compares S00 estimates, S11 structural out...

Performance review. Detects project type and dispatches compute and/or web performance reviewers. Advisory only — no cha...

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

Open performance review

Review a proposed design or implementation plan before implementation

Review implementation plans for parallelization, TDD, types, libraries, and security before execution

Review an implementation plan produced by the Plan agent. It is CRITICAL to review plans before handing off to implement...

Review a planning artifact (plan, shells, or spec) by running internal and peer reviews in parallel and returning combin...

Review plan shells against their source spec: launches an internal shell review and `/peer-review` in parallel and retur...

[Code Quality] Two-pass code review for task completion

Use this skill to produce a read-only audit of an open pull request — by PR number, GitHub URL, or the current branch's...

Review an exact PR head in isolation using trusted-base instructions and execution evidence

Audit a Zeebe BPMN process and its glue-code (workers, process adapter, tests) for consistency and coverage, producing a...

Review app polish — native feel, user-facing text, UX quality, and professional presentation

Review a prompt plan against its source spec: launches an internal prompt plan review and `/peer-review` in parallel and...

Run the Python code review protocol on scripts in code/py/. Checks code quality, reproducibility, pandas idioms, figure...

Comprehensive Python/FastAPI backend code review with optional parallel agents

Use this skill when you need to review Python code changes with an extremely high quality bar. This agent should be invo...

Analyze code for cross-file quality issues: duplicated logic, architectural inconsistencies, and abstraction opportuniti...

Run the R code review protocol on R scripts. Checks code quality, reproducibility, domain correctness, and professional...

Read-only R code review protocol for `.R` scripts. Checks code quality, reproducibility, domain correctness, tidyverse i...

Audit for race conditions in timers, hotkeys, callbacks, and shared state

Open Audit for race conditions in timers, hotkeys, callbacks, and shared state

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or techni...

Audit the paint and frame loop paths for STA message pump reentrancy — COM calls that can dispatch timer/hotkey callback...

Facilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classifi...

Pre-release readiness review. Scans for debug artifacts, version mismatches, changelog gaps, git hygiene issues, breakin...

Comprehensive Remix v2 code review with optional parallel agents. Detects Remix v2 in package.json, loads relevant revie...

Execute /review-renovate slash command.

Audit for memory leaks, handle leaks, GDI leaks, and CPU churn

Open Audit for memory leaks, handle leaks, GDI leaks, and CPU churn

Meta-audit all review skills for stale references, drifted architecture claims, and cross-skill inconsistencies

Review an architecture RFC against project architecture standards and best practices. Use when an RFC document needs des...

Use when preparing a PR description, suggesting reviewers, or flagging risk — produces owner-mapped roles plus historica...

Comprehensive Rust code review with optional parallel agents