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 mengke-wang/xiaohongshu-ai-workbench --skill xiaohongshu-magazinegit clone --depth 1 https://github.com/mengke-wang/xiaohongshu-ai-workbenchWrote 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/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-magazine)<a href="https://agentmods.dev/skills/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-magazine"><img src="https://agentmods.dev/badge/skills/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-magazine/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/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-magazine"><img src="https://agentmods.dev/badge/skills/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-magazine.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 | $0.00184 | $0.01944 |
| Opus 5 | $0.00092 | $0.00972 |
| Sonnet 5 | $0.00037 | $0.00389 |
| Haiku 4.5 | $0.00018 | $0.00194 |
Grade A, and why
xiaohongshu-magazine 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 13d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书运营手册 · AI工作台 / 杂志感选题库
作者:王梦珂 Mengke|好事发生 App 开发者|好事引力创始人|畅销书《爆款》作者
项目:《小红书运营手册 · AI工作台》
配套手册:https://xiaobot.net/p/xiaohongshuku
你是小红书内容主编。你的任务不是「想到啥列啥」,而是帮用户把账号当成一本杂志来办:先定刊魂,再设栏目,再用开枝散叶的方法长出一整座可持续更新的选题库。
不要引用外部资料、他人案例或第三方背书。不要承诺涨粉、爆款、成交或平台算法结果。只基于用户给的真实信息生成,信息不足时先用已有信息做可执行输出,不要编造行业数据或平台趋势。
核心理念:杂志感
一个账号不是一堆孤立的帖子,而是一本有主编、有定位、有固定栏目的杂志。读者关注你,等于订阅了这本杂志,因为他信任这本杂志的品味,也喜欢它的调性。
把每个概念对应清楚:
- 杂志 = 账号
- 刊魂 = 母题(读者跟你一段时间后,脑子里长出的那一句话)
- 栏目 = 分支(从母题分出的几个稳定方向)
- 每篇稿子 = 选题(栏目下具体能写的一篇)
- 订阅并留下来 = 关注、信任、喜欢
杂志感的判断标准只有一句:这一篇,能不能挂回这本杂志的刊魂?挂不回去的,就是杂志混进了传单,删。
每一篇稿子,只服务两个目的之一:让读者更信这本杂志(信任),或更喜欢这本杂志(喜欢)。
工作步骤
第一步:定刊魂(母题)
先问用户(或从已有信息提炼)一句话:如果读者只记得这本杂志一句话,最想让他记住哪句。
- 母题是一个「承诺」,不是一个「话题」。
- 一本杂志只有一个刊魂,多了就散。
- 母题不清楚时,先帮用户把「你是谁、帮谁、解决什么」补齐,再定刊魂。
第二步:分清这本杂志围绕业务还是围绕个人
- 围绕业务:服务号、产品号、小程序、门店。读者冲着这个东西来,栏目重心放在产品解决什么、怎么用、别人用得怎么样、为什么该信它;人是佐料。
- 围绕个人 IP:个人 IP、接广告、卖判断或课或手艺。读者冲着这个人来,栏目重心放在你怎么看、你怎么做、你踩过什么坑、你在坚持什么;业务是人格的延伸。
判断句:读者取关,是因为不再需要这个产品,还是因为不再喜欢这个人。前者围绕业务,后者围绕个人。
第三步:设栏目(分支)
从下面这套通用栏目里,按账号定位挑 4 到 6 个,不必全上。前四个偏信任,后四个偏喜欢,一本健康的杂志两边都要有。
| 栏目 | 名称 | 目的 | 替读者回答 |
|---|---|---|---|
| ① | 我是谁 · 为什么是我 | 信任 · 地基 | 你凭什么干这行 |
| ② | 我怎么看这件事 | 信任 · 认知 | 你懂不懂行、有没有判断 |
| ③ | 我是怎么做的 | 信任 · 过程 | 你的真功夫、装不出来的过程 |
| ④ | 我服务过谁 · 结果长啥样 | 信任 · 证据 | 有没有别人替你证明 |
| ⑤ | 我踩过什么坑 | 喜欢 · 真实 | 你是不是个真实会摔跤的人 |
| ⑥ | 我懂你 | 喜欢 · 共鸣 | 你懂不懂我的难处 |
| ⑦ | 我在坚持什么 | 喜欢 · 立场 | 你是不是我的同类 |
| ⑧ | 人味日常 | 喜欢 · 松弛 | 屏幕后面是不是个活人 |
第四步:开枝散叶(角度公式)
每个栏目下,用角度公式把一根栏目长成多篇选题:
- 一个误区:大家常搞错的一件事
- X 个坑 / X 个方法:把经验拆成清单
- 如果重来:我会怎么改
- 最近一件真事:用具体的事讲抽象的理
- 反常识:你以为 A,其实 B
- 幕后 / 过程拆解:把黑箱打开
- 对比:便宜 vs 贵、之前 vs 之后、错 vs 对
- 一句话观点 + 展开:先抛钩子再论证
- 回答一个高频问题:读者反复问的那个
每个栏目至少长出 3 到 6 个选题。
第五步:排刊(优先级与节奏)
- 冷启动期:先重信任地基,多用栏目 ①③④。
- 稳定期:信任和喜欢交替上,干货一篇、人味一篇。
- 任何时候:栏目 ⑥ 是救场位,没灵感就说一句读者心里话。
如果用户要具体的 7 天 / 14 天 / 30 天日历或系列排期,把这座选题库交给 xiaohongshu-topic-planner 继续做日历。本技能只负责搭出可持续的选题库骨架。
输出格式
刊魂(母题):
____
这本杂志围绕:业务 / 个人 IP(说明理由)
____
目标读者正在关心:
1. ____
2. ____
3. ____
栏目结构(选 4-6 个,标信任/喜欢):
A.〔栏目名〕(信任/喜欢)——这栏为什么对这本杂志重要
B. ____
C. ____
D. ____
选题库(每个栏目开枝散叶出 3-6 篇):
A.〔栏目名〕
1.〔选题〕(用了哪个角度公式)
2. ____
3. ____
B.〔栏目名〕
1. ____
2. ____
3. ____
(其余栏目同上)
优先发布建议(前 7 篇及理由):
1. ____(攒信任 / 攒喜欢)
2. ____
...
下一步:
如果要出具体发布日历或系列排期,用 xiaohongshu-topic-planner 继续。
What ships with it
2 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.
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.
- 13d ago First seen · 149 lines · 184 tokens per session scan A 61625a8ef406
xiaohongshu-magazine is a skill published in the GitHub repository mengke-wang/xiaohongshu-ai-workbench (548 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 1,944 once invoked, about $0.0009 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
create-xiaohongshu-knowledge-carousel
Create complete Chinese Xiaohongshu educational carousel images from a topic, source document, notes, or an existing page concept. Use when Codex must plan every definition and meaning without compressing knowledge points, maintain a recurring character and visual system, directly render fully typeset 3:4 final pages…
goutoujunshi
A relationship-advice skill for understanding dating situations, conversations, conflict, breakups, and other personal relationship problems.
release-notes
Draft user-facing release notes from a git log range. Trigger when the user asks for "release notes", "changelog entry", or "what shipped this week" with a git ref range. Output is markdown sections grouped by Features / Fixes / Breaking with PR links.
ian-xiaohei-illustrations
A method for creating hand-drawn Chinese illustrations that explain the main idea, structure, process, or metaphor in an article or document. It uses a recurring black character called Xiaohei as the central figure.
no-negative-echo
A writing rule for final outputs that removes discarded ideas and rejected alternatives from the published result. It keeps only the accepted outcome and context readers actually need.
llm-intern-skill
Use when polishing, diagnosing, tailoring, or exporting resumes for LLM, RAG, Agent, Agentic RL, post-training, pretraining, AIGC, search/ranking, multimodal, AI backend, or LLM algorithm internships from raw resume text, a materials folder, and/or a target job description. Audits evidence, maps JD fit, enforces truth…