/code-simplifier
Simplify existing code for clarity and maintainability without changing behavior. Use when asked to clean up or simplify code, especially recent changes.
$ npx -y skills add feiskyer/codex-settings --skill code-simplifier --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/code-simplifier
Context preview
The summary Claude sees to decide when to auto-load this skill.
Simplify existing code for clarity and maintainability without changing behavior. Use when asked to clean up or simplify code, especially recent changes.
SKILL.md
code-simplifier.SKILL.mdname: code-simplifier
description: Simplify existing code for clarity and maintainability without changing behavior. Use when asked to clean up or simplify code, especially recent changes.
Code Simplifier
Make code easier to understand and maintain without changing what it does. Prefer readable, explicit code over compact or clever rewrites.
Scope and conventions
Use the user's named files or diff. Otherwise, focus on code touched in the current task or clearly identified recent changes; ask for a target if none is evident. Inspect surrounding code as needed without turning a local cleanup into a repository-wide refactor. For review-only requests, propose changes without editing.
Follow applicable project guidance, such as `AGENTS.md` or `CLAUDE.md`, and the conventions in nearby code. Derive import style, function syntax, type annotations, framework patterns, and error handling from that project rather than imposing a different style.
Refinement criteria
- Preserve observable behavior, including public interfaces, outputs, errors, side effects, and evaluation order. Treat bug fixes or behavior changes as separate work unless requested.
- Reduce unnecessary nesting, duplication, and indirection where doing so makes the logic easier to follow. Keep helpful abstractions and separate unrelated concerns.
- Improve names and remove comments that merely restate the code; retain comments that explain intent or non-obvious constraints.
- Prefer explicit branches over nested ternaries or dense one-liners when they obscure the logic. Fewer lines alone is not an improvement.
Completion
Finish the scoped cleanup and validate it using checks appropriate to the change and the repository's requirements. For non-obvious rewrites, check relevant edge cases against the original behavior. If behavioral equivalence remains unclear, retain the original form and explain the limitation.
Report significant refinements, checks run, and any remaining validation gaps. If no worthwhile simplification is found, say so without manufacturing edits.
Read more
name: code-simplifier description: Simplify existing code for clarity and maintainability without changing behavior. Use when asked to clean up or simplify code, especially recent changes.
Code Simplifier
Make code easier to understand and maintain without changing what it does. Prefer readable, explicit code over compact or clever rewrites.
Scope and conventions
Use the user's named files or diff. Otherwise, focus on code touched in the current task or clearly identified recent changes; ask for a target if none is evident. Inspect surrounding code as needed without turning a local cleanup into a repository-wide refactor. For review-only requests, propose changes without editing.
Follow applicable project guidance, such as `AGENTS.md` or `CLAUDE.md`, and the conventions in nearby code. Derive import style, function syntax, type annotations, framework patterns, and error handling from that project rather than imposing a different style.
Refinement criteria
- Preserve observable behavior, including public interfaces, outputs, errors, side effects, and evaluation order. Treat bug fixes or behavior changes as separate work unless requested.
- Reduce unnecessary nesting, duplication, and indirection where doing so makes the logic easier to follow. Keep helpful abstractions and separate unrelated concerns.
- Improve names and remove comments that merely restate the code; retain comments that explain intent or non-obvious constraints.
- Prefer explicit branches over nested ternaries or dense one-liners when they obscure the logic. Fewer lines alone is not an improvement.
Completion
Finish the scoped cleanup and validate it using checks appropriate to the change and the repository's requirements. For non-obvious rewrites, check relevant edge cases against the original behavior. If behavioral equivalence remains unclear, retain the original form and explain the limitation.
Report significant refinements, checks run, and any remaining validation gaps. If no worthwhile simplification is found, say so without manufacturing edits.
给 Codex CLI 加上深度调研、图片生成、浏览器调试等能力,配好多模型切换,开箱即用。 仓库采用面向个人开发效率的默认配置;你可以整套使用,也可以按需选取 Profiles 或 Skills。使用前请确认模型提供商、权限和外部依赖,并避免提交真实密钥。
Other skills on codex-settings.
claude-skill
Delegate a task to the Claude Code CLI, typically a headless `claude -p` run. Use when the user wants the work executed through…
deep-research
用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。用于确实需要分头取证的研究,不用于单次查证或已给定材料的总结。
github-fix-issue
Investigate or fix a GitHub issue by number or URL. Keep investigation-only requests read-only.
github-review-pr
Review a GitHub pull request by number or URL for evidence-backed defects. Not for reviewing local uncommitted changes.
gpt-image-skill
Generate or edit images when the user names OpenAI, GPT Image, or a gpt-image model. Use the default image skill when no provider…

