Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sanqi-cd/Sanqi-Skills --skill xhs-image-text-generatorgit clone --depth 1 https://github.com/sanqi-cd/Sanqi-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sanqi-cd/sanqi-skills/xhs-image-text-generator)<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/xhs-image-text-generator"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/xhs-image-text-generator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/xhs-image-text-generator"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/xhs-image-text-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00107 | $0.02160 |
| Opus 5 | $0.00053 | $0.01080 |
| Sonnet 5 | $0.00021 | $0.00432 |
| Haiku 4.5 | $0.00011 | $0.00216 |
Grade A, and why
xhs-image-text-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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：
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。
Step 3：生成发布方案
输出必须包含以下模块：
-
选题角度
- 给 3-5 个角度
- 标注适合人群、核心钩子、保存价值
-
标题候选
- 生成 10 个标题
- 覆盖结果型、痛点型、清单型、反常识型、教程型
-
封面方案
- 给 3 个封面方案
- 每个包含主标题、副标题、视觉元素、配色、构图建议
-
分页脚本
- 默认 8 页，可按素材调整为 6-10 页
- 每页包含页面标题、页面文案、视觉建议
- 按
references/carousel-schema.md保存为carousel.json，它是页面文字的唯一数据源
-
正文
- 适合小红书发布的短段落
- 包含收益、适合谁、怎么用、避坑、互动引导
-
标签
- 12-18 个标签
- 覆盖核心词、人群词、场景词、长尾搜索词
-
评论运营
- 置顶评论
- 资料/模板领取评论
- 3-5 条常见问题回复
-
质量评分
- 按 6 个维度打分并给修改建议
Step 4：生成图片页
如果用户需要可直接发布的结果，必须生成图片页：
- 默认生成 8 张竖版图文页，比例 3:4 或 4:5，适合小红书图文
- 每张图必须有明确页面角色：封面、痛点、总览、步骤、案例、避坑、总结
- 先写
image-prompts.md，再直接调用生图模型生成图片 - 如果生图模型一次只能生成单张，就按页逐张生成
- 图片必须避免文字过密；每页只放一个主信息点
- 生成后检查：文字是否可读、是否跑题、是否适合小红书首图/分页
先生成可校验的排版基准：
python3 scripts/render_carousel_html.py "<package>/carousel.json" "<package>/cards.html"
cards.html 用于锁定逐页文字、层级和页数，也可以由浏览器逐页截图。使用生图模型时，以它作为内容基准：模型负责视觉素材，中文文字必须和 carousel.json 一致；发现乱码、缺字或文字溢出时应重试或改用浏览器排版截图。
Step 5：整理最终交付包
最终交付必须包含：
manifest.md：标题、选题、页面列表、发布说明caption.txt：可直接复制的小红书正文hashtags.txt：标签comments.txt：置顶评论和常见回复image-prompts.md：每页生图提示词- 图片页：
page-01到page-08，或工具实际返回的图片引用 quality-check.md：质量评分和发布前检查清单carousel.json：分页文案、角色、视觉系统和事实来源
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 318 B
- evals/evals.json 1.5 KB
- evals/trigger-evals.json 1.7 KB
- references/carousel-schema.md 1.1 KB
- references/delivery.md 3.4 KB
- references/playbook.md 4.8 KB
- scripts/init_delivery_package.py 2.8 KB runs code
- scripts/normalize_input.py 5.6 KB runs code
- scripts/render_carousel_html.py 5.8 KB runs code
- scripts/validate_delivery.py 2.5 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 201 lines · 107 tokens per session scan A 212f0ac835fd
xhs-image-text-generator is a skill published in the GitHub repository sanqi-cd/Sanqi-Skills (27 stars, last pushed 10d ago), licensed MIT. It adds 107 tokens to every session and 2,160 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
officecli-pitch-deck
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
morph-ppt-3d
3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-cover
A novel-cover generator that creates a cover with the book title and author name. It chooses a visual style from the book information and can use Codex's image-generation tool.
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…