跳到正文
cccskills
免费在 GitHub 公开

prose-quality

Use when the deliverable is authored or edited prose whose wording matters (docs, READMEs, release notes, public copy) or when the user asks to tighten, de-AI, or review writing. Not for chat answers, code review, or explanations of current work.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(3)

  • SKILL.md1.7 KB
  • agents/openai.yaml221 B
  • LICENSE.txt1.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Prose quality

An edit succeeds only if readers draw the same conclusions from the new text, with less effort.

Keep meaning fixed

  • Keep each claim at its original strength and scope. Carry over hedges, conditions, sample sizes, units, hardware, baselines, and "experimental" or "may not" limits. Never turn "did not measure X" into "X was unchanged."
  • Add no facts, numbers, or benefits the source lacks. Ask, or leave a marked gap.
  • Preserve commands, paths, flags, symbols, quotations, and normative text (MUST, SHOULD) exactly.
  • When the text describes code or a tool you can read, check its behavioral claims against it. Fix or flag mismatches and say what you checked.

Edit to the requested depth

  • Review only: return findings ranked by reader impact, errors (wrong, ambiguous, out of order) before style. No rewrite.
  • Editing: keep the author's voice, terms, structure, and the document's conventions (heading case, quote style, spelling). One name per concept.

Remove generated-sounding patterns

Cut puffery, signposting, filler, stacked hedges, summary closers, and decorative bold, emoji, or headers. Thin out em-dash chains, "not X but Y" contrasts, and forced triplets without substituting another tic. Keep a negation that states a real limit or hazard.

Before returning

Compare old and new for any claim that got stronger, weaker, or lost a qualifier. Name material ambiguities instead of writing around them.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when creating, revising, or critiquing a chart, dashboard, or KPI display that makes a quantitative comparison someone will act on. Covers honest comparison and rendered checks; leave palette, marks, and library mechanics to the medium's own skill. Skip decorative graphics and diagrams with no data.

中文简介正在准备中。当前显示原文说明。

macintog/codex-spine112026年10月9日 更新

Audit a codebase or subsystem for architecture simplification - shallow or pass-through modules, scattered concepts, naming drift, sibling workflows that disagree, weak test seams. Use when the user asks what to simplify or restructure. Not for a narrow fix or for implementing an already chosen design.

中文简介正在准备中。当前显示原文说明。

macintog/codex-spine112026年10月9日 更新

Judge performance or resource claims on real hardware: benchmark design or review, latency, throughput, memory or headroom numbers, and accept-or-reject decisions on optimizations. Not for refactors with no resource claim.

中文简介正在准备中。当前显示原文说明。

macintog/codex-spine112026年10月9日 更新

Audit an existing agent skill or instruction file for lines that do not change behavior, routing overlap, and portability, or vet a third-party skill before installing it. To create or edit a skill, use the platform's skill-creator instead. Not for running a skill's own task.

中文简介正在准备中。当前显示原文说明。

macintog/codex-spine112026年10月9日 更新

查看 macintog 的全部技能

报告此技能的问题