Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Audit SwiftUI iOS feature code for accessibility against WCAG 2.2 Level A/AA and return patch-ready fixes. Use when reviewing SwiftUI views/screens (including auth, forms, settings, and custom controls) and you need both standards traceability (WCAG + WCAG2Mobile interpretation) and practical, minimal code changes in a concise priority-grouped Markdown format with user follow-up checks for code-indeterminate behavior.
Create GitHub pull requests with the gh CLI using the reductstore/.github PR template, then update CHANGELOG.md with the created PR ID and commit the changelog (do not push). Use when a user asks to open a PR and record its ID in the changelog.
Use for QUICK PR reviews with structured checklists (architecture, patterns, security, performance). Provides step-by-step review process, git diff commands, and review report templates. Best for pull request reviews and pre-commit checks. NOT for deep refactoring analysis (use code-review instead).
Uses the Selora AI MCP server to inspect home state, validate/create automations, manage automation lifecycle, and handle proactive pattern/suggestion workflows. Use when users ask to analyze their home, review Selora automations, validate YAML, create/enable/delete automations, list or act on suggestions/patterns, trigger a scan, or continue Selora chat sessions.
Apply SOLID, SRP, cohesion, composition-over-inheritance, and small-file discipline to code changes. Use when refactoring large files or classes, setting maintainability limits in `AGENTS.md`, documenting justified exceptions, or reviewing design quality.
Influencer marketing AI — brief, pitch, rate evaluation, performance review แบบ data-driven
Cloud Architect — AWS/GCP/Azure solution design, cost optimization, HA/DR, multi-region, IaC (Terraform/CDK), Well-Architected Review
สร้าง mobile app iOS/Android ด้วย React Native Flutter Swift Kotlin พร้อม deploy ขึ้น store
Review โค้ด debug refactor และอธิบายโค้ดแบบ senior developer รองรับทุกภาษา
Academic research assistant — literature review + methodology (quant/qual) + paper outline (IMRaD) + citation + research gap analysis
Study Technique Coach — Spaced Repetition, Active Recall, Feynman Technique, exam plan, schedule สำหรับนักเรียนและนักศึกษาไทย
Develop zgrok tunnel service following project conventions, issue specs, and Rust best practices. Use when implementing features, fixing bugs, or reviewing code in this repository.
Weekly health review — sleep trends, workout adherence across wger/Fitbod/Peloton, nutrition averages, and recovery analysis.
Rails 8.x application architecture, implementation, and review guidance for production codebases. Use when building or reviewing Ruby on Rails 8 features across models, controllers, routes, Hotwire, jobs, APIs, performance, security, and testing. Trigger for requests mentioning Rails 8, Active Record, Active Job, GoodJob, Solid Queue, Turbo/Stimulus, REST resources, migrations, code quality, naming, and production readiness.
>
Talkdesk platform help — cloud contact center (CCaaS) with AI virtual agents, omnichannel routing, workforce management, and quality management. Use when setting up Talkdesk ACD routing or Studio IVR, calls keep dropping or audio quality is bad, AI features like Autopilot and CoPilot are expensive add-ons, comparing Talkdesk pricing tiers (Digital $85 to Industry $225/agent/mo), integrating Talkdesk with Salesforce Service Cloud Voice, Talkdesk reporting is hard to customize, WFM forecasting or scheduling not working, or implementation taking too long. Do NOT use for building a general coaching program (use /sales-coaching) or reviewing a specific call transcript (use /sales-call-review).
Use when you need adversarial review of any artifact — design docs, implementation plans, code, PRs, or documentation. Iterates until clean or stagnation.
>
Ask Claude via local CLI and capture a reusable artifact
Multi-LLM parallel code review with specialized agent personas.
Review input system code for vector reference bugs, cleanup issues, coordinate misuse, and adapter violations. Use when modifying input handlers, adapters, or touch/mouse/keyboard code.
> **Full agent type definitions:** See `references/agents.md` for complete 37 agent role specifications across 7 swarms (Engineering, Operations, Business, Data, Product, Growth, Review).
> **Note:**
構造化されたアプリ開発と問題解決のためのトークン効率の良いSerena MCPコマンド。デバッグ、設計、レビュー、実装のパターンを提供し、インテリジェントな開発支援を実現します。
Applies project Git commit message conventions. Use when writing commit messages, reviewing staged changes, or when the user asks for git commit help.
Review, write, or fix unit tests in TypeScript repos that use Vitest, Angular TestBed, and component-driven rendering. Use this when adding tests, debugging flaky or failing tests, preventing ExpressionChangedAfterItHasBeenCheckedError, improving beforeEach setup, or standardizing safe render patterns. Do not use for end-to-end tests, backend integration tests, or broad refactors unrelated to test behavior.
10 high-impact React patterns and anti-patterns - state management, performance, hooks, and component design. Use when writing or reviewing React components.
Review budget allocation and ROI
>
Render Compose @Preview functions to PNG outside Android Studio. Use this to verify UI changes, iterate on designs, and compare before/after states across Android (Jetpack Compose) and Compose Multiplatform Desktop projects.
forge-bugfix
forge-review
Orchestrate specialized review agents for code quality assessment. Use when: レビューして, コードレビュー, 品質チェック, code review, quality check. Do NOT use for quick PR screening (use /preview instead).
> CI/CD pipeline analysis, deployment strategy design, and environment management. From commit to production with confidence.
> Organizations that conduct blameless post-incident reviews after every significant security
> Deep soundness analysis of specs and plans. Auto-fixes inferrable issues, surfaces design decisions to you. Runs automatically before sign-off.
<!-- Generated by harness generate-slash-commands. Do not edit. -->
> Lightweight orchestrator — dispatches isolated phase-agents, tracks state, chains artifacts between phases. Delegates all planning/execution/verification/review to dedicated persona agents.
> Aesthetic direction workflow. Capture design intent, generate DESIGN.md with anti-patterns and platform notes, review components against aesthetic guidelines, and enforce design constraints at confi
> Detect documentation that has drifted from code. Find stale docs before they mislead developers and AI agents.
Extracts clinical data from prior authorization requests, validates ICD-10 diagnosis codes via MCP, notes CPT/HCPCS procedure codes (format validation handled by orchestrator pre-flight), searches supporting literature via PubMed and clinical trials, and structures a clinical narrative with per-field confidence scoring.
> Lightweight pre-commit quality gate — mechanical checks first, AI review second. Fast feedback before code leaves your machine.
The gh CLI is GitHub's official command line tool for interacting with GitHub repositories, issues, pull requests, and more. When needs to interact with GitHub repositories, issues, pull requests, and more, use this skill.
In-depth code review that fans out parallel subagents across different review perspectives (correctness, tests, security, performance, product). It is CRITICAL to use this skill after ANY non-trivial development phase — changes are usually not 100% correct. Development CANNOT be called done until the code has been reviewed. Use when the user asks for a review, PR feedback, bug hunt, or code quality check.
Review an implementation plan produced by the Plan agent. It is CRITICAL to review plans before handing off to implementation — plans often have gaps, incorrect assumptions, or suboptimal sequencing that are cheaper to catch now than after coding. Use when the user asks to 'review the plan', 'check my plan', 'is this plan ready', or after the Plan agent produces a plan.md.
Monitor a pull request until CI status or Copilot review is available. Use when: monitor PR, watch PR, land PR, wait for CI, wait for checks, wait for review, check PR status. Starts two async terminal tasks (CI + Copilot review) and reacts when either completes.
Multi-model council review for diffs, pull requests, and risky changes. It is CRITICAL to use this skill after ANY non-trivial development phase — changes are usually not 100% correct. Development CANNOT be called done until the code has been reviewed. Use whenever the user asks for a review, PR feedback, a bug hunt in recent edits, or wants multiple models to inspect the same change independently. Also use when the user asks to 'discuss findings', 'cross-review', or 'debate' review results between models.
Validates documentation completeness for prior authorization requests by checking a 10-item checklist covering patient information, provider credentials, insurance details, medical codes, clinical notes quality, NCCI bundling risk, and service type classification.
Ultracite enforces strict type safety, accessibility standards, and consistent code quality for JavaScript/TypeScript projects using Biome's lightning-fast formatter and linter.
> Load on-demand when spawning agents