菜单
Refactor bloated skill.md files using progressive disclosure pattern. Moves detailed content to references/ while keeping skill.md focused and discoverable. Use when a skill is approaching 500 lines or needs better organization.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | skill-refactoring |
| description | Refactor bloated skill.md files using progressive disclosure pattern. Moves detailed content to references/ while keeping skill.md focused and discoverable. Use when a skill is approaching 500 lines or needs better organization. |
Refactor bloated skill.md files to follow best practices using the progressive disclosure pattern.
This skill works for both Claude Code and Codex skills:
~/.claude/skills/~/.codex/skills/Both platforms use the same skill.md format and 500-line limit.
This skill helps refactor large skill.md files into focused, maintainable skills that use reference files for detailed content. Official limit is 500 lines, but targeting shorter is better for context efficiency.
Use this skill when:
# Check skill size
wc -l ~/.claude/skills/my-skill/skill.md
# If large or hard to navigate, invoke this skill:
# "Refactor the my-skill using progressive disclosure pattern"
references/methodology.md)Read this for:
references/templates.md)Read this for:
references/best-practices.md)Read this for:
methodology.md when refactoring a skilltemplates.md when creating new filesbest-practices.md when making decisionsWorks for both Claude Code and Codex skills:
~/.claude/skills/~/.codex/skills/Both platforms use the same SKILL.md format and progressive disclosure pattern.
Screenshot every view/screen of an app for marketing, product sites, and documentation. Use when asked to "screenshot the app", "capture all views", "get marketing screenshots", "screenshot every screen", or "product shots". Works with macOS native apps (screencapture), web apps (Puppeteer/Playwright), and Electron apps.
Recover working context from a prior Claude Code session by reading its JSONL conversation log and turning it into a clean handoff for Codex or another agent. Use when the user wants Codex to continue where Claude left off in the same repo, asks you to get up to speed on previous work, wants to resume a Claude thread after an interruption or outage, or needs help finding and summarizing the relevant file in ~/.claude/projects/.
Deep dive on any topic. Decomposes into subtopics, researches each in parallel with thorough source gathering, then synthesizes into a comprehensive report (4,000-10,000+ words, 40-100+ sources). Scales depth dynamically based on topic complexity. Use when asked for a deep dive, deep research, comprehensive analysis, or thorough investigation of a topic.
Send messages to other Claude Code or Codex sessions via tmux. Hand off complex debugging context, get second opinions, share detailed technical findings across sessions.
Branch the current Claude Code or Codex session into a new tmux session. Creates a parallel conversation that can diverge independently. Use when you want to explore an alternative approach without losing your current context.
Spawn a new Claude Code or Codex session in a project directory with context handoff. This skill should be used when discussion shifts to a different project/repo and the user wants to work on it in a dedicated session. Creates a handoff document with relevant context from the current conversation, then launches a new tmux session ready to continue.