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 →Create standardized git commits with Conventional Commits. Use when the user asks to commit changes, generate a commit message, or at the end of an implementation. Analyzes the actual diff to determine type, scope, and message. Supports logical file grouping and work item references (GitHub Issues and Azure DevOps). Do not use for branch creation (use git-branch), push, or pull requests (use pull-request).
Branch management for implementation. Use when you need to create a branch, switch branches, checkout, or verify branching strategy before implementing code. Do not use for commits (use git-commit), pull requests (use pull-request), or advanced git operations (rebase, merge).
Systematic debugging with structured triage. Use when tests fail, builds break, runtime behavior does not match expectations, or any unexpected error occurs during implementation. Do not use for planned refactoring (use code review), for test strategy (use implement agent's TDD flow), or for security-specific issues (use security-review).
Complete workflow for creating and managing ADRs (Architecture Decision Records). Includes duplicate checking, status determination, Microsoft documentation lookup, Azure cost estimates, and completeness validation. Use when you need to create or update ADRs during planning. Do not use for decisions that don't need an ADR (use conventions in plan.md).
Socratic guide for engineering practice decisions (DevOps, SRE, CI/CD, branch strategy, observability, IaC). Guides the agent to ask questions based on project context, rather than prescribing solutions. Use during planning of initial features. Do not use for application architecture decisions (use devsquad.plan) or for pipeline/infra creation (use devsquad.implement).
Use when user requests analysis of Indian stocks, fundamental assessment, technical review, comparisons, or investment reports for NSE/BSE listed companies.
>
>-
**Best-of-N parallel implementation for any task type.**
Internal repo-health lens for Green Goods — dead code detection, dependency health, invariant drift, and concrete broken or brittle spots. Prefer this after `/review` or `/status` reveals broader drift beyond a single change.
Internal architecture lens for Green Goods. Prefer this inside `/plan` or `/review` when boundaries, placement, or structural refactors need focused judgment. Use a dedicated pass only when the user explicitly asks for it.
Analyzes recently modified code and creates pull requests with simplifications that improve clarity, consistency, and maintainability while preserving functionality
Generate an executive assessment report from GitHub Quick Review (ghqr) scan data. Produces an executive summary, a dedicated section per validated subject with all findings, and a prioritized 30/60/90-day remediation plan. Use when the user asks for a report, executive summary, best practices posture overview, or a remediation roadmap from ghqr scan results.
Multi-language code quality standards and review for TypeScript, Python, Go, and Rust. Enforces type safety, security, performance, and maintainability. Use when writing, reviewing, or refactoring code. Includes review process, checklist, and Python PEP 8 deep-dive.
Run OpenAI Codex CLI locally for second-opinion audits, code review, and non-interactive task execution.
React and Next.js performance optimization guidelines from Vercel Engineering. Use when writing, reviewing, or refactoring React/Next.js code. 45 rules across 8 categories prioritized by impact.
Terraform infrastructure-as-code skills from HashiCorp. Covers HCL code generation with style conventions, testing with .tftest.hcl files, and module refactoring. Use when writing, reviewing, generating, or refactoring Terraform configurations, creating tests, or designing modules.
Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.
Explains test types & guides test selection using car analogy.
Comprehensive UX/UI evaluation meta-skill combining design theory and UX methodology. Use when conducting UI/UX audits, visual design reviews, accessibility compliance (WCAG 2.2), user flow analysis, responsive testing, interaction design evaluation, or design system audits. Evaluates using Nielsen's heuristics, Gestalt principles, typography theory, color theory, and modern methodologies (OOUX, JTBD, Cognitive Walkthrough).
toolkit for llm-friendly interaction with GitHub pull requests; using this skill the LLM can fetch PR data and analyze it
C# coding standards and conventions for DataFactory.MCP. Use when writing or reviewing C# code.
Create, review, and merge GitHub pull requests using GitHub CLI and best practices. Use when the user asks to open a PR, review a PR, merge a branch, squash merge, or work with GitHub pull requests and merges.
Add or modify tasks in Implementation Plan. Use when user proposes new requirements, changes priorities, or adjusts existing task scope.
Deep analysis and investigation
Full R017 verification (5+3 rounds) before commit
**Version 1.0.0**
**Version 1.0.0**
Use Gemini CLI for long-context codebase exploration, architecture review, refactor impact analysis, documentation synthesis, or structured data analysis when the host should hand off a large cross-file problem instead of solving it file-by-file.
Use when reviewing storyboard outputs at any production stage (beat breakdown, beat board, sequence board, motion prompts), providing quality assurance feedback, or identifying revision requirements for Director agent
Guide for authoring SAM aliases and vars files. Use when a user wants to create, edit, or review aliases.yaml or vars.yaml files for SAM, add new aliases to a .sam folder, or structure a new SAM namespace.
Padrão de revisão de Pull Requests contra padrões do TikTickets-zing
Test and validate an existing codebase. Analyzes code structure, performs automated code review with auto-fix, runs API endpoint tests and UI tests via Chrome browser automation, generates documentation. Phase 4 (code generation) is skipped since code already exists. Use when user asks to test existing code, run quality assurance, perform code review, or validate a system.
Export WordPress content to portable local packages. Import to another site with smart ID remapping. Auto-backup before AI edits. Full builder data preservation, human-readable markdown previews, and
Comprehensive on-page SEO and Answer Engine Optimization (AEO) audit and auto-fix system. Scans all content, detects issues, generates intelligent schema markup, and creates optimized duplicates for r
Autonomously review Magento 2 module code against coding standards, architectural rules, and security requirements. Produces a severity-rated findings report.
Safe refactoring with test guard — improve code quality without changing behavior
Conventional commits, PR creation, and quality gate verification
Check for license compliance, PII, and IP risks
Implements advanced AI patterns like Reflection, ReAct, Planning, and Tool Use.
Review tax returns, identify missed deductions, and suggest strategies to reduce tax liability.
Systematic review of existing architecture using ATAM-lite methodology. Evaluates architectural fitness against quality attribute scenarios, identifies risks, sensitivity points, tradeoffs, and anti-patterns. Produces structured review report with findings and recommendations.
Use the `gh` CLI for ALL GitHub-related tasks including working with issues, pull requests, Actions workflows, releases, and repositories. If given a GitHub URL, use `gh` to get the information needed
`src/renderer/store` is the single source of truth for workspace state (`appStore.ts`) and theme preference state (`themeStore.ts`).
Hand off code review tasks to OpenAI's Codex CLI for an independent AI perspective on code changes.
Expert Quarterly Business Review facilitation for maximizing customer value and strategic alignment. Use when designing QBR programs, preparing executive presentations, demonstrating ROI and value realization, conducting strategic account planning, aligning product roadmaps, identifying risks and opportunities, facilitating business reviews, or automating QBR processes. Use for EBR preparation, success metrics presentation, renewal preparation, and stakeholder engagement.
Provides comprehensive, structured reviews of Remotion video implementations against motion design specifications. Identifies issues, assesses impact, and generates actionable revision lists.
Teach and apply Effect-TS practices (effect, @effect/schema, @effect/platform) for architecture, typed errors, Layers, dependency injection, resource safety, testing, and migration from async/await/Promise. Use when a user asks how to use Effect, requests best practices, wants to refactor to Effect, or needs mapping from platform modules to Node/Bun/Browser APIs.
forces the model to ask more during review
Assesses and responds to incoming code review feedback on PRs (reviewer comments, requested changes), especially when suggestions are unclear, technically questionable, or scope-expanding. Use before implementing review suggestions to align on intent and keep changes minimal.