humanizer
starsforks
How to install humanizer?
woodfishhhh/ez_math_model/humanizer
$npx -y skills add woodfishhhh/EZ_math_model --skill humanizerUse after EZ_math_model writer creates paper.md and before quality audit when a long modeling paper needs less AI-like prose while preserving formulas, data, citations, tables, and figures.
SKILL.md
| 1 | # humanizer — 论文正文去 AI 味 |
| 2 | |
| 3 | ## 何时使用 |
| 4 | |
| 5 | - writer 已落盘 `paper.md`。 |
| 6 | - `quality_audit` 尚未运行。 |
| 7 | - 正文长度通常不少于 5000 字。 |
| 8 | - 用户或配置要求降低 AI 写作痕迹。 |
| 9 | |
| 10 | ## 调用方式 |
| 11 | |
| 12 | 优先加载宿主 `humanizer` skill。输入 `paper.md` 正文，要求： |
| 13 | |
| 14 | - 保留所有数值。 |
| 15 | - 保留引用编号。 |
| 16 | - 保留公式块和行内公式。 |
| 17 | - 保留 Markdown 表格。 |
| 18 | - 保留图片标签 ``。 |
| 19 | - 不修改章节标题。 |
| 20 | |
| 21 | 默认写到： |
| 22 | |
| 23 | ```text |
| 24 | workdir/{task_id}/paper.humanized.md |
| 25 | workdir/{task_id}/humanizer_diff.md |
| 26 | ``` |
| 27 | |
| 28 | 只有用户显式开启 `--humanize-overwrite` 时才覆盖 `paper.md`。 |
| 29 | |
| 30 | ## 结构化 diff 硬门 |
| 31 | |
| 32 | humanizer 后必须生成 `humanizer_diff.md`，并至少比较以下集合： |
| 33 | |
| 34 | - 数值集合； |
| 35 | - 引用编号集合； |
| 36 | - 公式块 hash 集合； |
| 37 | - 图片引用集合； |
| 38 | - Markdown 表格数量； |
| 39 | - 一级/二级标题集合。 |
| 40 | |
| 41 | 任一集合变化时，不得覆盖 `paper.md`；只能保留 `paper.humanized.md`，并在 |
| 42 | `diagnostics.md` 中记录。quality audit 必须检查实际打包版本，不能审原文却打包 |
| 43 | humanized 版本。 |
| 44 | |
| 45 | ## 检查重点 |
| 46 | |
| 47 | - 夸张象征语和营销式措辞。 |
| 48 | - 空泛转折和堆叠连接词。 |
| 49 | - 过度三段式。 |
| 50 | - 模糊归因。 |
| 51 | - 频繁使用 em dash 或英文 AI 高频词。 |
| 52 | |
| 53 | ## 失败诊断 |
| 54 | |
| 55 | | 情况 | 处理 | |
| 56 | |---|---| |
| 57 | | 宿主 skill 未安装 | 跳过，不阻塞 packaging | |
| 58 | | 数值、公式、引用被改坏 | 回滚到原 `paper.md` | |
| 59 | | 字数明显缩水 | quality_audit 标记字数风险 | |
People who liked this also viewed
6 picksType
- azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026
- just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026
- firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 2026
- firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 2026
- firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 2026
- firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 2026
