Script and automate repetitive tasks and workflows.
Enforces minimum quality thresholds in CI including code coverage, linting, type checking, and security scanning. Provides required checks, PR rules, and automated enforcement. Use for "quality gates", "CI checks", "code quality", or "PR requirements".
Generates comprehensive unit tests with AAA pattern (Arrange-Act-Assert), edge cases, error scenarios, and coverage analysis. Creates test files matching source structure with complete test suites. Use for "unit testing", "test generation", "Jest tests", or "test coverage".
Use when replacing approaches or dismissing patterns. Traces decision history through git/jj logs, commit messages, and decision records to avoid repeating failures and rediscover abandoned solutions. Triggers: refactoring, replacing patterns, 'simplify', 'modernize', 'outdated', 'legacy', 'clean up', architectural changes.
Git commitの作成。pre-commit検査遵守、意味のある最小単位でのコミット、Emoji Prefix対応。
Generates semantic commit messages following the Conventional Commits specification with proper types, scopes, breaking changes, and footers. Use when users request "write commit message", "conventional commit", "semantic commit", or "format commit".
Generate a conventional commit message from staged git changes. Use this skill when the user wants to create a commit message for their staged changes.
Automatic project context detection with priority-based resolution (Manual setting → Git remote → Subdirectory pattern → Local path → Custom patterns). Auto-activates at start of every CCPM command to ensure correct project context. Supports monorepos with subdirectory detection using glob patterns and priority weighting. Handles ambiguous detection (multiple matches) by asking user to clarify. Caches detection result for command duration (fast reuse). Provides clear error messages with actionable suggestions when no project detected. Displays project context in command headers (e.g., "📋 Project: My Monorepo › frontend"). Supports auto-detection mode (cd = switch) or manual setting (stable context across sessions). Performance: <100ms for auto-detection, 0ms for manual.
MUST use before any commit operation. Detects VCS type (prefers jujutsu over git), enforces atomic commits, validates messages, runs tests. Required before: 'git commit', 'jj commit', 'commit these changes', 'let me commit', 'ready to commit', 'git add', creating commits, branch operations, pull requests.
Automatically maintains project documentation including CHANGELOG.md, README files, inline code documentation, and cross-references. Use proactively after implementing features, fixing bugs, making API changes, or completing significant work. Updates CHANGELOG.md with conventional commit format, adds README sections for new features, generates inline documentation for new functions/structs/components, and ensures documentation cross-references are up-to-date. Covers Rust doc comments, TypeScript JSDoc, conventional commits (feat/fix/docs/refactor/test/chore), and multi-level README organization.
This skill should be used before committing code to ensure it meets Breenix quality standards. Use for running clippy checks, fixing compiler warnings, verifying no log side-effects, checking for dead code, and enforcing project coding standards from CLAUDE.md.
Audit semantic noise and namespace integrity. Produces a severity-grouped report with namespace/rename suggestions.
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
Guidelines for automated and manual verification of code changes. When to use: - After making code changes to ensure correctness As part of the implementation workflow
To run static analysis across a Dart or Flutter project, analyze files to find compile and lint errors.
Instructions for reviewing changes using subagents. Use after implementation and verification are complete
Codex CLI config optimization skill. Use when: - Editing agents.md or agents/ - User asks about Codex CLI config best practices - User says "codex cli changelog" or "codex cli updates" - User asks about new features or changes in Codex CLI
程式碼簡化與重構工作流程。當使用者提到簡化程式碼、清理 PR、重構、程式碼優化、code cleanup、refactor、simplify code、clean up complex code 時自動啟用。靈感來源於 Anthropic Claude Code 團隊內部使用的 code-simplifier agent。A code simplification and refactoring workflow. Inspired by the official code-simplifier agent used internally by the Claude Code team at Anthropic.
Extracts durable insights from temp/ files to SoT during EPIC Phase E. Triggers at EPIC completion or explicit `/ghm-harvest` invocation. Outputs new SoT entries and archive manifest.
Makes architectural changes through ADR-first workflow with staged intent clarification. Use when the user asks to "add a component", "change architecture", "refactor X", "implement feature", "fix bug", "create new service", "update diagram", or "remove component". Requires .c3/ to exist. All changes flow through ADR process. For questions, route to c3-query instead.
Identify relevant files, understand architecture patterns, and find code by functionality. Use when you need to understand where specific functionality lives or find files related to a feature area.
Use when architectural patterns evolve, tech stack changes, or foundational rules need updates - creates new constitution version directory, migrates/organizes content into modular files, updates symlink, and documents changes
