xhs-image-text-generator SKILL.md skillA

xhs-image-text-generator from sanqi-cd/sanqi-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sanqi-cd/sanqi-skills/xhs-image-text-generator@v1.1.1

Pins v1.1.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sanqi-cd/sanqi-skills
Path
xhs-image-text-generator/SKILL.md
Versions recorded
4
Latest version
v1.1.1, committed Sep 30, 2026
First version recorded
Jun 7, 2026
Size
8,881 bytes
Repository stars
28
License
MIT

将 HTML、Markdown、文章、访谈记录、产品资料或主题转化为可直接发布的 6-10 页小红书/RedNote 图文轮播,完成内容提炼、分页、视觉设计、生图、失败重试和交付校验。适用于“小红书配图”“把文章做成卡片”“直接生图并给发布文案”等请求。Use when the user needs final carousel assets, not only prompts or generic summaries.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 小红书图文生成器

## 适用场景

当用户提供以下任一输入,并希望生成小红书图文笔记时,优先使用本技能:

- HTML 网页 URL 或 HTML 文件
- Markdown 文章
- 纯文本内容、访谈记录、产品资料、研究笔记
- 一个主题、想法、工具清单或案例素材

本技能的目标不是只写文案,而是生成一套最终用户可以直接发小红书的交付包。

## 默认工作流

### Step 1:统一输入素材

如果用户提供的是 URL、HTML、Markdown 文件或较长文本,优先使用脚本抽取正文:

```bash
python3 scripts/normalize_input.py "<input>" --output "<normalized.md>"
```

说明:
- `<input>` 可以是 URL、本地文件路径,或 `-` 表示从标准输入读取
- 脚本会自动识别 `html`、`markdown`、`text`
- 如果当前目录不是本 skill 根目录,请使用脚本的实际路径

短主题或一句话需求可以不运行脚本,直接进入 Step 2。

### Step 2:补齐关键上下文

先从素材中推断:

- 目标人群:例如打工人、内容创作者、职场新人、读书博主、AI 初学者
- 核心收益:省时间、涨粉、赚钱、效率提升、审美提升、认知提升
- 内容类型:工具清单、教程步骤、方法复盘、模板分享、观点拆解、案例拆解
- 可视化素材:数据、步骤、工具图标、前后对比、截图、金句、清单
- 评论区需求:领取资料、是否免费、怎么安装、国内能否用、适合谁

如果以下信息缺失且会影响成品,直接问用户 1-3 个短问题后继续:

- 发布账号/人设:例如 AI 工具号、个人成长号、职场干货号、读书号
- 目标人群:默认从素材推断
- 期望风格:默认选择最适合赛道的爆款风格
- 是否需要真实品牌/头像/个人照片:默认不用
- 是否允许直接生图:默认允许,除非用户明确只要文案
- 交付数量:默认 1 篇,8 页图文

不要为可合理默认的信息反复追问。

**高风险主题开工门槛:**涉及投资、个人理财、赚钱、医疗或法律时,如果用户只给了宽泛主题,且素材不足以确定适用人群、具体角度或事实依据,先停在本步骤,最多问 3 个短问题:面向谁及适用地区/情境、想讲哪一类知识或问题、有哪些可核查来源或事实依据。第三问必须明确提到来源或证据;若用户没有素材,可询问是否允许先查证公开资料并只做不含个性化建议的通用科普。在收到回答前,不输出分页脚本、图片或可直接发布的成品;不要凭默认人设、风险承受能力、收益率或法规填补空白。如果用户明确同意采用合理默认值,也只能在可核查事实的范围内制作通用科普,并在成品中写明适用边界。素材已足够明确时直接继续,不重复追问。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sanqi-cd/sanqi-skills/xhs-image-text-generator@sha256:866f747d2df3c8c7

The line at the top of this page pins the label v1.1.1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2su4baw42twwblnk.svg)](https://markdownregistry.com/a/art_2su4baw42twwblnk)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jun 7, 2026 and Sep 30, 2026, about one every 38 days.

versioncommittedcommitsizeaudit
v1.1.1 latest2026-09-30 faa1a75 8,881 BA view · diff
v1.1.02026-09-29 297b429 7,951 BA view · diff
v1.0.02026-08-03 df6d69c 7,909 BA view · diff
git:20260607.12ce5932026-06-07 12ce593 7,801 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8881 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

sanqi-cd/sanqi-skills · 28 stars · license MIT · pushed 2026-10-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2su4baw42twwblnk
GET https://markdownregistry.com/api/v1/resolve?ref=sanqi-cd/sanqi-skills/xhs-image-text-generator
GET https://markdownregistry.com/api/v1/blob/866f747d2df3c8c7db4ddc35874f309cd7070ab06b4988ce417a92d548201037

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from sanqi-cd/sanqi-skills

learning-path-designer SKILL.md skill
sanqi-cd/sanqi-skills · learning-path-designer/SKILL.md · 根据学习目标、当前基础、时间约束和应用场景,设计从入门到实际运用的个性化学习路径,并交付可勾选、可保存进度的单文件 HTML 成长地图。适用于“规划学习路线”“从零掌握一项技能”“备考证书”“规划转岗学习”等请求。Use when a…
v1.1.0 · audit A · 28 stars
paper-explainer SKILL.md skill
sanqi-cd/sanqi-skills · paper-explainer/SKILL.md · 用通俗但准确的语言深度解释学术论文,覆盖问题背景、方法、公式、实验、创新、局限和相关工作,并输出可独立阅读的 Markdown 学习笔记。适用于论文精读、方法拆解、实验分析和跨领域理解;若证据不完整,必须继续获取全文或明确证据边界。Use…
v1.1.0 · audit A · 28 stars
skill-builder SKILL.md skill
sanqi-cd/sanqi-skills · skill-builder/SKILL.md · 通过渐进式需求澄清、工作流设计、资源拆分、实现和评测,创建或优化高质量 Agent Skill。适用于“创建一个 skill”“把工作流封装成 skill”“优化 SKILL.md”“补充…
v1.1.0 · audit A · 28 stars
youtube-podcast-to-md SKILL.md skill
sanqi-cd/sanqi-skills · youtube-podcast-to-md/SKILL.md · 提取 YouTube 播客、访谈或长视频字幕并整理为中文 Markdown,支持核心摘要与对话高保真还原、字幕降级策略、说话人处理和时间戳溯源。用户提供 YouTube 链接并要求总结、转写、翻译、整理文章或笔记时优先使用。Use for…
v1.1.1 · audit A · 28 stars

Every file in sanqi-cd/sanqi-skills

Browse by kind, by grade A, or by owner.