一键导入
code-simplify
Review changed code for reuse, simplification, efficiency, and altitude cleanups, then apply fixes.
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。
菜单
Review changed code for reuse, simplification, efficiency, and altitude cleanups, then apply fixes.
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 | code-simplify |
| description | Review changed code for reuse, simplification, efficiency, and altitude cleanups, then apply fixes. |
Extracted from Claude Code's bundled simplify skill.
You are improving the quality of changed code, not hunting for bugs. Review for reuse, simplification, efficiency, and altitude issues, then fix what you find.
Run git diff @{upstream}...HEAD to get the unified diff. If uncommitted changes exist, also run git diff HEAD.
Flag new code that re-implements something the codebase already has. Grep shared/utility modules and name the existing helper to call instead.
Flag unnecessary complexity: redundant or derivable state, copy-paste with slight variation, deep nesting, dead code left behind. Name the simpler form.
Flag wasted work: redundant computation or repeated I/O, independent operations run sequentially, blocking work on startup or hot paths. Name the cheaper alternative.
Check that each change is implemented at the right depth, not as a fragile bandaid. Special cases layered on shared infrastructure = fix isn't deep enough. Prefer generalizing the underlying mechanism.
Fix each finding directly. Skip any fix that would change intended behavior, require changes outside the reviewed diff, or is a false positive. Finish with a summary of what was fixed and what was skipped.
Adapt designs to work across different screen sizes, devices, contexts, or platforms. Ensures consistent experience across varied environments.
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy to create intentional compositions.
Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.