Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
\"Search, review, and manage workflow memories — patterns, decisions, lessons, strategies. 搜索、審查、管理工作流記憶：模式、決策、教訓、策略.
Review auto-memory for the current project. Shows accumulated learnings, identifies noise, and helps promote permanent patterns to CLAUDE.md, rules, or skills.
Review code changes for Effect-TS pattern compliance in the Reactive Agents framework. Use when reviewing PRs, completed packages, or any code changes to enforce project…
CODESYS ST 코드 리뷰. PR의 PLC 코드를 Infrastructure 아키텍처, 네이밍 규칙, 시퀀스 데드락, 모듈화 관점으로 분석. 사용법: /review-plc
Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree.
Simulated peer review panel for manuscript prose. Spins discipline-specific agents for multi-perspective review.
Review a PR, branch or file path and recommend the highest ROI improvement opportunities. TRIGGER when the user asks if the code is ready, looks good, or is otherwise complete.
Run the R code review protocol on R scripts. Checks code quality, reproducibility, domain correctness, and professional standards. Produces a report without editing files.
Проверка документа ревью кода на соответствие стандарту — frontmatter, именование, секции Контекст ревью и Итерации, вердикт, статус OPEN/RESOLVED.
This skill reviews Dapr Workflow activity implementations for idempotency, retries, error boundaries, and convention violations.
This skill reviews Dapr Workflow code for non-determinism hazards that would cause stuck workflows on replay.
This skill reviews the HTTP management endpoints (start, status, terminate, pause, resume, raise-event, purge) that an app exposes for Dapr Workflows.
Enable the code review stop hook in .reviewer/settings.local.json. Optionally takes a shell expression for when to enforce (defaults to always).
Reviews GitHub pull requests for the Medusa repository. Checks PR template compliance, contribution guidelines, code conventions, and community contribution limits.
Revisão de código abrangente: qualidade + compliance + segurança. Classifica achados por severidade. Combina revisão de código genérica com validação de domínio regulado.
Analyse, redesign, or complete a GridPonder level. Reads the level JSON, evaluates design quality (aha moment, difficulty, gold path validity, cheap alternatives), then proposes…
Revisa contratos mercantiles contra el playbook del despacho e identifica desviaciones
Revisione approfondita contratto B2B italiano: commessa, SLA, penale, limitazione responsabilità, foro, 1341-1342, IP, recesso, DPA. Nessuna consulenza legale.
Revisione contratto di nomina responsabile (art. 28 GDPR) term-by-term: istruzioni, sub-responsabile, misure, breach, audit, trasferimenti. Output tabella gap con severity.
Revisione approfondita licenziamento: qualificazione (giusta causa, giustificato motivo), procedimento, art. 18, impugnazione, prove. Output memo e checklist rischi.
Revisione NDA / accordo riservatezza B2B italiano: definizioni, scopo, durata, carve-out, legge applicabile, rimedi. Nessuna consulenza legale.
Construction 단계 실행 직전, Inception 아티팩트와 설계 문서를 교차 분석하여 12개 카테고리 기반 위험 체크포인트를 탐지한다. 비즈니스 연속성·보안·외부 통합·데이터 일관성·비용·성능·규제·가용성·장애 전파 반경·운영 복잡도·의존성 취약점·롤백 가능성을 각각 PASS/WARN/BLOCK으로 판정하고…
Workflow completo per richieste interessato GDPR (artt. 15-22): classificazione, verifica identità, mappatura sistemi, esenzioni, bozza lettera e log decisioni.
DevRites menu + router. Without args, renders the menu. With a verb (e.g. `spec`, `build`, `review`), dispatches to the matching `rite-` skill — `/rite spec foo` is…
Decompose an approved `spec.md` into `plan.md` + vertical task slices + `state.md`; every acceptance criterion maps to ≥1 slice.
Compact the current chat into a handoff doc a fresh agent can pick up cold — syncs chat-only context into the canonical `.devrites/` files, references artifacts by path.
Reshape an active plan — decompose / reslice / repair / reorder / split FE-BE / unblock — without changing product behavior unless asked.
Prove the completed feature — full tests + build + typecheck + lint + browser-proof ladder — walking `spec.md` acceptance criteria one by one.
Resolve open `questions.md` entries on the active feature — answer one, drop one, or batch-resolve from a file — and clear `state.md` `Awaiting human` so the workflow resumes.
Final GO / NO-GO gate — walk `spec.md` acceptance against `evidence.md`, fan out reviewers in parallel, block on Critical, ask y/N on Important, demand type-GO before irreversible…
Investigate a new feature and write `spec.md` (placement, gaps, design refs, measurable acceptance) under `.devrites/work//`.
Read-only report on the active feature — phase, active slice, next action, evidence, open questions, drift, risks, handoff readiness.
RM-ODP 全6スキル（5 Viewpoint + Correspondence）をオーケストレーションする統合ワークフロー。 業務シナリオから Enterprise → Information → Computational → Engineering → Technology → Correspondence…
Pipeline retrospective — evaluate the completed pipeline against Anthropic's 9 harness principles.
Show existing code review results for a commit or job. Use to check review status without re-running.
robust-review の S-Critical/S-High Finding を定型修正パターン（unwrap除去、injection対策、未チェックインデックス等）で自動修正し、各修正後に検証ゲート（build/type/test）で安全を確認する。USE WHEN robust-review 直後、Tier 2 Finding…
Generates robustness check code and formats results as a combined table. Use for sensitivity analysis.
Generate Rocaille-style domain warping shaders, mouse-reactive liquid logo effects, depth-map parallax heroes (Astryx-style hover-reactive statues), and stable fluid simulations…
Execute operational tasks after validated implementation: runtime controls, git/PR/release flow, and governance checks.
Orchestrate single-thread baton handoff across Manager -> Collaborator -> Admin -> Consultant with explicit entry/exit contracts.
Implement scoped changes and produce validation evidence matching manager-defined gates.
Perform independent post-execution critique, risk scoring, and recommendation synthesis without changing implementation scope.
Execute IT operations: fleet hardware, service management, and environment provisioning.
Define scope, constraints, acceptance criteria, and verification gates before implementation begins.
Откат analysis chain (ROLLING_BACK → REJECTED) — 5 фаз оркестрации, валидация артефактов, отчёт, подтверждение пользователя.
Revisa term sheets y pactos de inversión (SHA) para rondas de financiación. Analiza cláusulas clave, identifica risk flags y orienta la negociación.
Audit M3UAndroid Room schema and migration changes for versioning, schema artifacts, data preservation, indices, defaults, DAO compatibility, and migration validation.
ROS2 QoS 兼容性检测 — Reliability/Durability/Deadline/Lifespan 四个维度的兼容性判断，控制命令/sensor数据/lifecycle节点的 QoS 配置规则
Reconcile ALL prior agent conversations (Claude Code, Codex, Droid/Factory, Hermes, Cursor) with git history and docs into a cited ground truth, and distill durable decision…
Scaffold and clean up rough meeting notes in a vault's scratchpad/. Two modes — prep (creates a pre-meeting template from a short brief) and cleanup (reads a rough dump, asks…
Phase 5 verification orchestrator: three-stage (module→top→final) parallel verification pipeline covering lint, SVA/formal, CDC, protocol, functional regression, coverage,…
Создание нового rule-файла в .claude/rules/ с frontmatter и регистрацией. Используй при добавлении нового автоматического правила для Claude Code — контекстного или глобального.
Обновление содержания, деактивация или миграция rule-файла в .claude/rules/. Используй при изменении правил для Claude Code, переименовании rule или выводе устаревшего правила из…
Проверка rule-файла на соответствие стандарту — frontmatter, формат, пути, триггеры. Используй после создания или изменения rule, при code review или аудите правил Claude Code.
Manage CLAUDE.md and rules — extract learnings, add rules, restructure, and review. Use when updating project conventions.
Execute PHP code on 3v4l.org to test runtime behavior across multiple PHP versions. Use when you need to verify what PHP actually does with a piece of code.
Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate.
Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowled — from…
Guide runbook creation, maintenance, and drill exercises. Use when: writing runbooks, planning drills, auditing runbook coverage, post-incident runbook updates.