菜单
Audits a stylesheet folder for hard-coded values that duplicate an existing design token — colors, spacing, radii — and reports each with the token to use instead. Use before a release or after importing third-party CSS.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/brokenrobot-xyz/agent-skills --skill auditing-css-tokens命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Autonomously improves a Claude Code skill in a review→fix→re-review loop: each round invokes the reviewing-claude-skills review non-interactively, applies every blocking finding — High and structural findings included — without per-fix approval, commits the round, and re-reviews, until the review's verdict is acceptable, the blocking findings plateau, or the round cap is hit. Advisory findings are reported, never chased. Asks one question only: confirming the intent brief at kickoff. Use when the user asks to improve a skill autonomously, in a loop, or until it passes review.
Autonomously improves a Claude Code subagent definition in a review→fix→re-review loop: each round invokes the reviewing-claude-subagents review non-interactively, applies every blocking finding — High and structural findings included — without per-fix approval, commits the round, and re-reviews, until the review's verdict is acceptable, the blocking findings plateau, or the round cap is hit. A gated verdict recommending a different artifact form — 'this should be a skill' — ends the loop for the human instead of being applied. Advisory findings are reported, never chased. Asks one question only: confirming the intent brief at kickoff. Use when the user asks to improve a subagent autonomously, in a loop, or until it passes review.
Reviews a Claude Code skill — its SKILL.md, evals, and referenced files — in two passes. Structure first: a workflow whose shape fails High stops at a structural verdict with a redesign recommendation. Otherwise a full detail sweep against skill-authoring and prompting best practices plus the host project's conventions produces a severity-ranked gap analysis ending in a computed verdict — acceptable, or not yet — honoring the skill's recorded waivers, optionally applying approved fixes. Use when the user asks to review, audit, or improve a skill.
| name | auditing-css-tokens |
| description | Audits a stylesheet folder for hard-coded values that duplicate an existing design token — colors, spacing, radii — and reports each with the token to use instead. Use before a release or after importing third-party CSS. |
| model | claude-sonnet-5 |
| allowed-tools | Read Grep Glob |
Find hard-coded values that duplicate a design token, and report the token each one should use.
Copy this checklist into your reply and tick each item as you go:
Audit progress:
- [ ] 1. Load the token definitions
- [ ] 2. Sweep the stylesheets
- [ ] 3. Match values to tokens
- [ ] 4. Report
Read the token file the user names and collect every token's name and value.
Grep the stylesheet folder for color, spacing, and radius literals. Collect every match with
its file and line — a match dropped here never reaches the report.
Compare each literal against the token values. Report an exact match as a replacement; report a near match (within one step of the spacing scale) as a candidate for the user to judge.
One table: file, line, literal, token, exact or near. When nothing matches, say so and name the files swept.