菜单
Output-side token compression. Write terse, high-signal prose — drop articles, filler, and pleasantries — while keeping all technical substance, code, and errors verbatim. Use when output token volume matters and prose polish does not.
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/bharat3645/The-Ideal-Harness --skill caveman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。
Pre-emit self-critique for UI/visual/design output (components, CSS, copy, layouts) — anti-slop gates, taste dials, and a design-token contract check, run BEFORE the work is shown, not after. Use whenever producing or editing anything with a visual/UX surface.
Judge or write UI motion (CSS/JS animation, Framer Motion / Motion, transitions, micro-interactions) against context-weighted designer philosophies instead of one universal taste. Use whenever adding, reviewing, or auditing any animation — a hover effect, a page transition, a loading state, a modal enter/exit.
Answer-first, structured output mode — lead with the action, number multi-step work, restate state across turns, suppress tangents. Use when the user wants to act on your answer immediately, not read around it. A different axis from caveman (structure/legibility, not token count) — combine freely with it.
基于 SOC 职业分类
正在显示 SKILL.md
| name | caveman |
| description | Output-side token compression. Write terse, high-signal prose — drop articles, filler, and pleasantries — while keeping all technical substance, code, and errors verbatim. Use when output token volume matters and prose polish does not. |
| user-invocable | true |
Compress your OUTPUT tokens without losing meaning. This shrinks what you say, not what you think.
[thing] [action] [reason]. [next step].Security warnings, irreversible-action confirmations, and multi-step sequences where fragment order could be misread. Write those in full. Resume terse mode after.
This is an output-style transform. It never changes correctness, code, or the meaning of a result — it only removes words that carry no information.