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 →Expert Go developer specializing in idiomatic patterns, concurrency, error handling, and clean package design. This skill should be used PROACTIVELY when working on any Go code - implementing features, designing APIs, debugging issues, or reviewing code quality. Use unless a more specific subagent role applies.
Define, review, and scaffold Go service directory structures using hexagonal (ports-and-adapters / “jexagonal”) architecture and Go best practices. Use when creating or refactoring Go services, deciding package boundaries, organizing cmd/internal/api/config/deploy/migrations, or choosing layouts for common service types (HTTP REST API, gRPC API, async worker/consumer, scheduled job, CLI, multi-binary repos).
Go language consultant providing guidance on best practices, testing with testify, concurrency patterns, error handling, and technology stack recommendations. Use when answering Go questions, reviewing Go code, or advising on Go implementation approaches.
Review Go code against comprehensive style guide, focusing on critical bugs and important maintainability issues.
Reviews Go test code for proper table-driven tests, assertions, and coverage patterns. Use when reviewing *_test.go files.
Use this skill to write, refactor, or review Go code according to the Uber Go Style Guide. It ensures strict adherence to correctness, safety, and idiomatic patterns.
Use this skill when writing Go code following the Uber Go Style Guide. Provides comprehensive guidance on idiomatic Go patterns, error handling, concurrency safety, performance optimization, and test-driven development. Covers all critical Uber Go rules including channel sizing, goroutine management, interface design, and proper error handling. Appropriate for any task involving .go files, Go code reviews, refactoring, or implementing Go best practices.
Track goal progress, derive state from execution, identify gaps, trigger actions. Use for goal status checks, progress reviews, and operational goal management.
Comprehensive Go code review meta-skill. Coordinates 5 specialized domain skills. For targeted reviews, use domain-specific skills (concurrency-safety, clean-architecture). For full audits, use this meta-skill.
golang-cli-review
Comprehensive Go code review skill for PR reviews, architecture assessment, and test quality analysis. Use when reviewing Go code to ensure adherence to Go best practices, security standards, and project-specific patterns. Applies to full PR reviews, single file/function reviews, architecture evaluation, and test code quality checks.
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
Applies Google's engineering practices for strict, health-focused code reviews.
This skill provides comprehensive guidance for optimizing web content and documentation for search engine discoverability based on Google's official SEO Starter Guide. Use this skill when creating new
Use when writing or reviewing technical documentation to follow Google's documentation style guide - https://developers.google.com/style
Use when blocked, stuck, or needing fresh perspective. Consults GPT experts via Codex CLI with graceful fallback.
GPUI Component project style guide based on gpui-component code patterns. Use when writing new components, reviewing code, or ensuring consistency with existing gpui-component implementations. Covers component structure, trait implementations, naming conventions, and API patterns observed in the actual codebase.
Grades and improves CLAUDE.md (Claude Code) and AGENTS.md (Codex/OpenCode) configuration files. Use when asked to grade, score, evaluate, audit, review, improve, fix, optimize, or refactor agent config files. Triggers on 'grade my CLAUDE.md', 'score my AGENTS.md', 'is my CLAUDE.md too big', 'improve my agent config', 'fix my CLAUDE.md', 'optimize context usage', 'reduce tokens in CLAUDE.md', or 'audit my config files'. Automatically grades both files if present, generates improvement plan, and implements changes on approval.
Expert knowledge of research grant compliance requirements, deliverables tracking, and funder expectations. Use when reviewing work against grant specifications, preparing progress reports, or ensuring alignment with funding requirements from NSF, NIH, EU, and other agencies.
Use when writing or reviewing NIH, NSF, or foundation grant proposals. Invoke when user mentions specific aims, R01, R21, K-series, significance, innovation, approach section, grant writing, proposal review, research strategy, or needs help with fundable hypothesis, reviewer-friendly structure, or compliance with grant guidelines.
Write compelling grant proposals for academic research, creative projects, and nonprofit initiatives. Covers federal (NSF, NEA, NEH), foundation, and institutional grants with attention to narrative, budget justification, and review criteria. Triggers on grant writing, funding proposals, research funding, or fellowship applications.
Build context-efficient, reusable skills using graph-based workflow orchestration with Claude Code subagents. Combines PocketFlow-inspired graph abstraction with multi-model optimization (Haiku for exploration, Sonnet for analysis). Use when building complex workflows, converting external frameworks to Claude skills, or optimizing for cost and context efficiency.
This skill should be used to answer questions and guide workflows related to the Graphite CLI. It assists with creating, managing, submitting, and synchronizing stacked code changes (diffs).
You are the **Graphite Workflow Expert**. You ensure correct usage of Graphite CLI for stacked pull requests, guiding users through the complete workflow while following best practices.
Comprehensive implementation auditor that grills code quality, plugin structure, consistency, and identifies problems. Use when reviewing increment quality, auditing modules, or analyzing the entire codebase for issues. Spawns parallel subagents for thorough analysis.
Write and validate Grove technical specifications with consistent formatting, ASCII art headers, diagrams, and the Grove voice. Use when creating new specs, reviewing existing specs for completeness, or standardizing spec formatting.
Write effective, maintainable tests that catch real bugs and enable confident refactoring. Use when deciding what to test, reviewing test quality, or writing tests for Grove features. Focuses on philosophy and strategy—pair with javascript-testing for implementation details.
GSAP animation best practices for web design - scroll triggers, performance optimization, accessibility, responsive animations, and testing integration. Use when implementing or reviewing animations on WordPress or any web project.
Graphite (gt) is a CLI tool for managing stacked pull requests - breaking large features into small, incremental changes built on top of each other. This skill provides the mental model, command refer
Proactively audit Cloudflare configurations for security vulnerabilities, resilience gaps, cost traps, AND budget/privacy risks. Use this skill when reviewing wrangler configs, before deployments, investigating issues, or when ANY architecture decision involves Durable Objects, R2, Workers AI, or high-volume operations. This skill PROACTIVELY warns about cost impacts before users ask.
Provides guidance for installing, configuring, and choosing Git graphical interface clients (GitKraken, Sourcetree, GitHub Desktop) across platforms. Compares features, licensing, and workflows. Troubleshoots graphical tool configuration and setup issues. Use when installing Git graphical clients, setting up Git visualization tools, configuring graphical commit tools, choosing between options, or troubleshooting configuration. Covers Windows, macOS, and Linux. All tools are optional and based on user preference.
Comprehensive smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specifications, review architecture, check upgradeability patterns, assess implementation quality, identify pitfalls, review dependencies, and evaluate testing. Provides actionable recommendations. (project, gitignored)
Generates comprehensive, professionally-formatted changelogs for SDL3 HammerEngine from git history. Analyzes code changes, runs tests, includes architect review, and produces detailed documentation following World Update format. Use when documenting updates, preparing releases, or creating detailed change reports.
Runs comprehensive code quality checks for SDL3 HammerEngine including compilation warnings, static analysis (cppcheck, clang-tidy), coding standards validation, threading safety verification, and architecture compliance. Use before commits, pull requests, or when the user wants to verify code meets project quality standards.
Configure the behaviour for the handler of incomplete tasks.
Handles GitHub pull request review comments. Use when asked to fix review comments, address PR feedback, or resolve review threads. Fetches comments via GitHub CLI, fixes issues in code, replies to reviewers, and resolves threads.
Manages Appwrite Storage for buckets, permissions, and image previews. Use when handling file uploads or displaying gallery images.
Create a short summary of recent handoff log entries without modifying the append-only log.
Main coding agent for autonomous harness system. Continues work from previous sessions, implements one feature per session, coordinates with testing and review skills, and maintains clean handoffs via Archon. This is the workhorse of the harness system for multi-session development.
Harness MCP (Model Context Protocol) server integration for AI-powered CD operations, pipeline management, Git repositories, pull requests, code review comments, and bidirectional Jira synchronization
Use when designing content delivery APIs for headless CMS architectures. Covers REST and GraphQL API patterns, content preview endpoints, localization strategies, pagination, filtering, caching headers, and API versioning for multi-channel content delivery.
Review account health across portfolio
Production-ready Helm chart creation and review guide. Covers chart structure, ArgoCD/GitOps integration, secrets management, testing strategies, deployment patterns (blue-green, canary), monitoring, and troubleshooting. Use when creating charts, reviewing for security/quality, integrating with ArgoCD, or debugging chart issues.