원클릭으로
dotfiles
dotfiles에는 mei28에서 수집한 skills 14개가 있으며, 저장소 수준 직업 범위와 사이트 내 skill 상세 페이지를 제공합니다.
이 저장소의 skills
Analyzes git diffs and automatically creates fine-grained commits with rule-based commit messages following Angular.js conventions. Use when you have multiple unstaged changes that need to be organized into logical commits.
Delegate implementation of an approved plan to Antigravity CLI (agy) via `agy --headless --approve all`, then summarize the resulting diff. Use as an alternative to codex-implement when Codex is unavailable or at its limit.
Delegate implementation of an approved plan to OpenAI Codex via `codex exec`, the Codex TUI, or a final-only MCP call, then summarize the resulting diff. Use after planning in Claude Code, to offload heavy implementation to Codex and conserve Claude's budget.
Get a second-opinion code review from Antigravity CLI (agy) on the current working-tree diff or branch, returning an APPROVED/WARNING/BLOCKED verdict. Use to cross-check Claude Code's own review with a different model.
Get a second-opinion code review from OpenAI Codex (read-only) on the current working-tree diff or branch, returning an APPROVED/WARNING/BLOCKED verdict. Use to cross-check Claude Code's own review with a different model.
Generates CHANGELOG.md from git commit history following Keep a Changelog format with semantic versioning and automatic categorization
Automated code review tool that analyzes code quality, detects bugs, identifies security vulnerabilities, and suggests improvements based on industry best practices
Detects and removes unnecessary additions in AI-generated code, improving codebase consistency. Use when reviewing AI-generated code for over-engineering, excessive comments, or style inconsistencies.
Identifies ambiguities in requirements and architecture through structured questions, helping clarify implementation plans before coding begins
Generates comprehensive API documentation from code including OpenAPI/Swagger specs, JSDoc/TSDoc comments, and API reference guides
Generates comprehensive PR descriptions in English (default) or Japanese by analyzing pull request changes using GitHub CLI
Suggests and applies code refactoring improvements including complexity reduction, code smell removal, and pattern improvements based on static analysis
Automatically generates comprehensive unit tests for functions, classes, and modules with meaningful test cases including edge cases
Write or update `.tmp/progress.md` so work can be resumed by the other AI tool (Claude Code <-> Codex), typically before switching tools when one nears its usage limit. Captures Goal/Plan/Done/Next/Open/Resume.