feat: 新增女娲与 Humanizer 双语版三个第三方入口 (#82)

## 概述

以 `entry.json` pointer 形式收录三个第三方技能,均为 MIT、社区维护、SHA 锁定:

| id | 上游 | category | ref | 简介 |
|---|---|---|---|---|
| `nuwa-skill` |
[alchaincyf/nuwa-skill](https://github.com/alchaincyf/nuwa-skill) |
productivity | `27642f5` | 输入一个名字即自动调研→提炼→验证,把任何人的心智模型、决策启发式与表达 DNA
蒸馏成可运行的人物 Skill |
| `humanizer` | [blader/humanizer](https://github.com/blader/humanizer)
| creative | `523374d` | 基于维基百科「Signs of AI writing」指南去除文本 AI 痕迹,纯
Markdown 可跨 agent 运行 |
| `humanizer-zh` |
[op7418/Humanizer-zh](https://github.com/op7418/Humanizer-zh) | creative
| `91f3d39` | Humanizer 汉化版,按中文写作习惯去痕,附核心规则、快速检查清单与质量评分 |

后两者是同一技能的英文原版与汉化版,故合并在一个 PR 内提交便于对照 review。

## 遵循 ADR-038(市场元数据注册表与两层技能模型)

- **只放元数据、不放内容**:仅新增三个 `skills/<id>/entry.json`,正文留在上游源仓库,不 vendoring
任何源码或二进制。
- **市场第三方层**:三者均 `stewardship: community`、`license:
MIT`、`redistribution: allowed`。
- **source pointer**:`kind=git` + repoUrl + repoBranch,`ref` 锁定完整 SHA
保证可复现。
- **轻量 i18n**:仅 name/shortDesc(zh-CN / en-US),列表本地化可离线。
- **无需 `source.path`**:三个上游的 `SKILL.md` 均在仓库根目录(已用 GitHub API 核对树结构),不涉及
#81 修复的 pointer 路径问题。
- **不声明 children**:`nuwa-skill` 的 `examples/` 下 15 个人物 perspective
是女娲的产出示例而非并列子技能,按 `gen-collection-children.py` 的排除规则不计入。
- 第三方 entry 未进 `builtin-skills.json`。

## 变更

- 新增
`skills/nuwa-skill/entry.json`、`skills/humanizer/entry.json`、`skills/humanizer-zh/entry.json`
- `manifest.json`:`stats.totalSkills` 57 → 60,`version` 1.2.24 →
1.2.25,`lastUpdated` → 2026-08-09
- `README.md`:external 25 → 28、total 57 → 60,外部条目清单按字母序插入三个新入口

## 验证

\`\`\`
$ uv run scripts/i18n/validate-i18n.py
OK: no i18n issues found.
\`\`\`

统计核对:`entry.json` 目录 28 + `SKILL.md` 目录 32 = 60,与
`manifest.stats.totalSkills` 一致。
This commit is contained in:
mashagua
2026-08-09 18:14:38 +08:00
committed by GitHub
parent 27589d013d
commit e15f152ed0
5 changed files with 106 additions and 9 deletions

View File

@@ -0,0 +1,32 @@
{
"id": "humanizer-zh",
"name": "Humanizer 中文版",
"category": "creative",
"icon": "<svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M3.5 6h7M3.5 11h5M3.5 16h8\" stroke=\"#2563EB\" stroke-width=\"1.7\" stroke-linecap=\"round\"/><path d=\"m19.4 5.6-6 6-2.4.5.5-2.4 6-6a1.3 1.3 0 0 1 1.9 1.9Z\" stroke=\"#2563EB\" stroke-width=\"1.6\" stroke-linejoin=\"round\"/><path d=\"M15.5 17.5h5\" stroke=\"#2563EB\" stroke-width=\"1.7\" stroke-linecap=\"round\"/><path d=\"M18 15.5v4\" stroke=\"#2563EB\" stroke-width=\"1.7\" stroke-linecap=\"round\"/></svg>",
"tags": ["writing", "editing", "ai-detection", "humanize", "chinese"],
"i18n": {
"zh-CN": {
"name": "Humanizer 中文版",
"shortDesc": "Humanizer 的汉化版本,按中文写作习惯去除 AI 生成痕迹,附核心规则、快速检查清单与质量评分,适配 Claude Code、Codex 等"
},
"en-US": {
"name": "Humanizer (Chinese)",
"shortDesc": "Chinese localization of Humanizer that removes AI writing patterns following Chinese prose conventions, with core rules, a quick checklist and quality scoring for Claude Code and Codex"
}
},
"maintainer": {
"name": "歸藏 (op7418)",
"verified": false,
"account": "op7418",
"url": "https://github.com/op7418/Humanizer-zh"
},
"stewardship": "community",
"license": "MIT",
"redistribution": "allowed",
"source": {
"kind": "git",
"repoUrl": "https://github.com/op7418/Humanizer-zh.git",
"repoBranch": "main",
"ref": "91f3d394db8419c20d67ebe22a96cf8fee0a404b"
}
}