Anti-AI-generic design guidelines. Use when creating UI prototypes, reviewing designs for generic AI patterns, or setting up a project design system.

Use when creating or planning weekly GitHub Issues from github-projects/week*_issues_complete.csv or similar weekly CSV files and adding them to a GitHub Project. Trigger for tasks that mention GitHub Projects, weekly issues, week_n labels, CSV issue files, sprint/week setup, repository/project issue import, or adding the corresponding week's issues to a project with gh CLI.

Review Swoosh frontend code for performance risks on weak devices and slow networks. Use when analyzing bundle size impact, re-render frequency, memory leaks, network waterfalls, TTI, FCP, CLS, heavy client components, list rendering, image loading, route composition, or cache and request behavior in the Next.js client.

Orquesta notificaciones de NEXO AV hacia Microsoft 365 manteniendo trazabilidad en el ERP. Use when implementing or reviewing Outlook, Teams or Power Automate notifications for planning, assignments, visits, ready-to-invoice states, incidents or approval requests that must stay linked to ERP tasks and notifications.

Review a release or major change for deployment readiness, including configuration, migrations, monitoring, rollback, and operational gaps.

>

Use the free first-party `dotnet format` CLI for .NET formatting and analyzer fixes. Use when a .NET repo needs formatting commands, `--verify-no-changes` CI checks, or `.editorconfig`-driven code style enforcement.

Generate Vitest + React Testing Library tests for Dify frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.

You are performing a structured, multi-stage code review. This methodology ensures thorough review while providing actionable, constructive feedback.

Use this skill when reviewing an existing mystery story, detective story, whodunit, clue puzzle, suspect structure, or locked-room plot in order to reconstruct its truth, knowledge gaps, clues, suspects, scene information flow, and fairness. Use it when Codex should judge whether the work actually functions as a mystery, where it breaks, and which extracted elements are missing, weak, or unfounded.

Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.

**Tier:** POWERFUL

Review UI code for Web Interface Guidelines compliance. Use when asked to review UI quality, UX, accessibility, or design-system adherence for specific files or routes.

Read `.code-review.md` in the current working directory and apply every review comment.

코드 리뷰. 작업 후 변경사항을 Z.AI 모델로 깊이 있게 검토. /rr 또는 'GLM 리뷰' 요청 시 사용. (기본: glm-4.7-flash 무료)

GLM-5 코드 리뷰 (유료). /rr의 상위 버전 — GLM-5 744B 모델로 더 깊은 리뷰. /rrr 또는 'GLM-5 리뷰' 요청 시 사용.

>-

PR 管理：浏览、摘要、创建、更新、查看 review 评论、回复 review。触发词：'pr'、'pull request'、'创建 PR'、'回复 review'。

Use when managing PR review threads. Reply does NOT auto-resolve threads. Trigger with /manage-threads.

Plan, build, review, or extend a stateless Bash CLI wrapper for the publicly documented EODHD API, intended for OpenClaw agents and Clawhub.ai distribution. Use when Codex needs to define command structure, auth handling, error semantics, redaction rules, CI, packaging, or skill metadata for an open source EODHD integration that must follow OpenClaw secrets management and avoid leaking sensitive data to stdout, stderr, logs, examples, or repo artifacts.

>

Transform design documents into TDD-based implementation plans with parallelizable tasks. Triggers: 'plan implementation', 'create tasks from design', or /plan. Enforces the Iron Law: no production code without a failing test first. Requires an existing design document — use /ideate first if none exists. Do NOT use for brainstorming, debugging, or code review.

Quality assurance system that verifies deliverables match user requirements and execution plans. Features: (1) Auto-Memory - record conversations and tasks, (2) Double Check - verify deliverables in 3 scenarios: plan confirmation, post-delivery verification, user-triggered check, (3) Idle Reflection - periodic review and lesson extraction. Triggers on 'double check it', 'dc it', 'what's wrong', '再检查一下', '到底怎么回事'.

pinterest-pin-writer

Evaluates pro-rata and follow-on investment decisions with portfolio construction, signaling effects, and reserve management. Use when making follow-on decisions, managing reserves, or evaluating pro-rata rights.

Structured, taxonomy-guided code review with selective category focus. Performs two-pass review (detect then verify) across 16 error categories with independent severity, confidence, and qualifier axes. Use when reviewing a PR, reviewing staged changes, performing a pre-merge quality gate, or when asked to review specific files or a diff.

GitHub operations via gh CLI for pull requests/PRs, GitHub code search, and drafting exact gh commands. Always use instead of WebFetch for github.com.

Scan content and websites for SEO gaps, identify opportunities to outrank competitors. Use when: (1) Analyzing page SEO, (2) Checking meta tags and structured data, (3) Reviewing content for keyword optimization, (4) Auditing technical SEO factors.

Maintain and debug existing LabOne Q experiment/analysis workflows in this repository. Use for bug fixes, review follow-ups, and minor behavior changes under qubit_experiment/, experiments/, analysis/, and qpu_types/.

Gate the greenfield workflow on user verification after an implementation step. Reads the implementation digest, shows verification steps, and waits for the user to confirm before advancing. Part of the gf (greenfield) skill family.

Senior software architecture workflows and tooling for system design, scalability and reliability planning, API/data modeling, trade-off analysis, ADR writing, and producing clear architecture diagrams (Mermaid). Use when you need to define or revise architecture for a feature/system, choose technologies, document decisions, or review an existing codebase’s architecture.

'Master of defensive Bash scripting for production automation, CI/CD

사용자가 CLAUDE.md 파일 검토/확인/리뷰를 요청할 때, 또는 /claudemd-review를 입력할 때 사용한다. Claude Code 공식 원칙 6가지 기준으로 프로젝트 내 모든 CLAUDE.md를 감사한다.

Quantum ESPRESSO experiment-spec and validation guidance for electronic-structure stages. Use when defining SCF inputs, checking QE workdir artifacts, reviewing convergence expectations, or mapping QE outputs into downstream Autolab stages.

Validate code quality, run all tests, and create a PR only if everything passes.

Manage — When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions

Code Reviewer — Protocols and standards for performing thorough, structured code reviews. Covers the reviewer's core mandate, step-by-step review protocol, and all review lenses: security (secret scanning), code quality (SOLID, DRY, KISS), architecture (Separation of Concerns, Atomic Design), and testing (AAA pattern). Use when reviewing pull requests, merge requests, or any code changes across any language or framework.

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).

Create a concise pull request with conventional commit title, summary, and labels

Review one normalized evidence bundle against one selected feature package slice and produce one bounded reconcile decision. Use after evidence normalization to decide accepted vs patch-required vs relaunch vs hold. Do not use for package authoring, compile-only work, or raw evidence normalization.

Normalize one bounded run result into one structured evidence bundle for one selected package slice. Use after execution artifacts exist and before reconcile review. Do not use for package authoring, package readiness review, compile-only work, or final reconcile classification.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Review the current diff for bugs, security issues, and code quality concerns

Essay and writing review with structure analysis, coherence checks, and style improvement

Generates real (non-stub) code, config, docs, and test artifacts for the skill-forge. Replaces writer.sh logic with a Planner→Coder→Reviewer pipeline. Use for all artifact generation tasks.

Improve code structure without changing intended behavior