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 wpsnote/wpsnote-skills --skill xiaohongshu-note-creatorgit clone --depth 1 https://github.com/wpsnote/wpsnote-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/wpsnote/wpsnote-skills/xiaohongshu-note-creator)<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/xiaohongshu-note-creator"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/xiaohongshu-note-creator/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/wpsnote/wpsnote-skills/xiaohongshu-note-creator"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/xiaohongshu-note-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00204 | $0.06377 |
| Opus 5.5 | $0.00082 | $0.02551 |
| Sonnet 5.5 | $0.00041 | $0.01275 |
| Haiku 4.5 | $0.00020 | $0.00638 |
Grade A, and why
xiaohongshu-note-creator 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 1mo 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 — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xiaohongshu Note Creator - 笔记转小红书图文
脚本路径说明:本 Skill 依赖的
image_gen.py位于此 SKILL.md 同目录的scripts/下。 AI 执行前,先确认脚本存在:ls {SKILL所在目录}/scripts/image_gen.py运行命令时指定路径:python3 {SKILL所在目录}/scripts/image_gen.py ...
将 WPS 笔记内容转化为完整的小红书图文方案,包含每页图文、AI 配图和话题标签。
铁律(最高优先级)
0. 读图(必须在 Step 2 之前完成)
调用 outline 找出所有图片 block,逐张调用 read-image 读取并做视觉描述,记录每张图的画面内容、风格色调、适合用于哪页。
wpsnote-cli outline --note_id {note_id} --json
wpsnote-cli read-image --note_id {note_id} --block_id {block_id} --json
MCP 降级:read_image({ note_id, block_id })
读取完成后,在对话中汇报:「原文共 N 张图,图1 [画面描述],适合 P{页码};图2...」
原文无图时:说「原文无图」,继续。
1. 所有输出必须写入 WPS 笔记,禁止在对话中直接输出正文
- 禁止在对话消息里输出任何图文内容、文案正文、标签列表
- 唯一合法的输出方式:通过
create_note+batch_edit/edit_block写入 WPS 笔记 - 写入成功后对话中只说:笔记标题、页数、一句话摘要、「已写入笔记」
- 违反以上任一条,立刻停止并重新通过工具写入
2. 提问必须附备选项
对话中只能做两件事:提问 + 状态通知。
- 提问时必须附上 2-4 个备选选项
- 状态通知:调用工具前一句话告知正在做什么
4. 文案必须忠于原文(最容易犯错,最高优先级)
核心原则:这是一个"改写压缩"任务,不是"重新创作"任务。
- 每页正文必须来自原文对应章节的真实内容,不得 AI 自由发散补充
- 直接改写原文段落为口语化小红书风格,核心观点、数据、例子必须与原文一致
- 优先保留原文金句,如"整理是 AI 的事,思考是用户的事"、"往里扔就行"等
- 每页对应原文哪个章节必须明确(规划时就标注,如"P2 → 原文 01 笔记软件的周期律")
严禁的行为:
❌ 用自己的话"总结"原文,丢失具体细节
❌ 添加原文没有的观点、类比、案例
❌ 用通用小红书套话替换原文独特表达
❌ 把多个不相关章节内容混写成一页
5. 生图必须优先使用原文图片垫图
有原文图片时,禁止直接文生图:
- Step 2 读取源笔记时,必须扫描所有
imageblock,优先用 CLI 读取 base64 并立刻用视觉理解描述图片内容(见 Step 2 第 3 步):
MCP 降级:wpsnote-cli read-image --note_id {note_id} --block_id {block_id} --json # 返回 data.image_base64 字段read_image({ note_id, block_id }) - 生图时,根据页面内容就近选取一张原文图片作为垫图:
# 先将 base64 保存为临时文件 python3 -c "import base64; open('/tmp/ref_pN.jpg','wb').write(base64.b64decode('{data.image_base64}'))" # 再传入 --image python3 scripts/image_gen.py ... --image /tmp/ref_pN.jpg - 视觉描述(prompt)必须基于图片的真实画面来写,不是凭空编写氛围图:
✅ 原图是:男生坐在电脑前,周围漂浮着笔记软件图标,困惑表情,线条插画风 → prompt:年轻男生坐在书桌前,Notion/Obsidian图标环绕飘散,眉头紧皱,同款线条插画风,奶油色调,竖版构图 ❌ 凭空写:温馨书房,女生整理笔记,日系风格(完全不参考原图) - 只有在以下情况才允许纯文生图:
- 原文没有图片
- provider 是 dashscope(不支持垫图)
- provider 是 ark(即梦)且只有本地图片(ark 只支持公网 URL)
What ships with it
1 file 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.
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.
- 1mo ago First seen · 516 lines · 204 tokens per session scan A 0aa3c8d089cb
xiaohongshu-note-creator is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed today), licensed MIT. It adds 204 tokens to every session and 6,377 once invoked, about $0.0008 per session on Opus 5.5. 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
gap-to-topic
Turn a research area into a go/no-go decision dossier for candidate thesis/proposal topics (zero or multiple justified options) — a 3-gate verdict (is the gap open? is it a contribution? is it feasible?) with the evidence laid out so the researcher can verify it. Use when the user asks "is this gap worth pursuing"…
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
research-workflow-orchestrator
Run a resumable end-to-end research workflow that automates low-risk work, pauses at explicit human decision gates, records provenance, and routes each stage to the appropriate research-hub skill or MCP tool.
literature-triage-matrix
Turn a list of papers (Zotero collection, Obsidian cluster, manual list) into a compact comparison matrix written to .research/literaturematrix.md, instead of generic per-paper summaries. Use when the user asks to "make a literature matrix", "compare these papers by method/data/limitations", or "decide which papers…
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
ccgui-plugin-creator
A plugin-building workflow for CC GUI, a desktop client that can be extended with plugins written as configuration or JavaScript modules.