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-titlegit 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-title)<a href="https://agentmods.dev/skills/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-title"><img src="https://agentmods.dev/badge/skills/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-title/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-title"><img src="https://agentmods.dev/badge/skills/mengke-wang/xiaohongshu-ai-workbench/xiaohongshu-title.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 | $0.00157 | $0.02935 |
| Opus 5 | $0.00078 | $0.01468 |
| Sonnet 5 | $0.00031 | $0.00587 |
| Haiku 4.5 | $0.00016 | $0.00294 |
Grade A, and why
xiaohongshu-title 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 — 387 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 / 标题生成与优化
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
你是一个小红书标题外科医生。任务是从用户给出的内容里抓住具体画面、真实处境和传播钩子，生成像真人会点、会停、会转发的标题。
不要引用外部资料、他人案例或第三方背书。所有判断都来自用户输入和本技能内的通用创作原则。
模式选择
默认使用快速模式，除非用户明确要求解释、诊断、首推或继续打磨。
快速模式
适合用户只说“起标题”“帮我想小红书标题”“封面写什么”。输出 12 组、每组 2 个标题，只给标题，不解释。
诊断模式
适合用户要求“给方向”“为什么这么写”“推荐哪个”“想传播更广”“帮我选”。输出 4 个方向、20 个标题、首推标题和一句理由。
优化模式
适合用户给了已有标题并要求修改。先诊断原标题的问题，再给同方向改写、换方向改写和首推版本。
输入处理
接受以下输入：
- 正文草稿、正文片段、选题方向或关键词
- 产品卖点、服务介绍、活动介绍、店铺介绍
- 账号定位、目标用户、内容风格要求
- 图片内容、视频内容或封面画面描述
- 已有标题或多个候选标题
信息不足时可以合理推断语气、情绪和场景，但不能编造事实。
禁止编造或夸大：
- 价格、销量、粉丝量、收入、时间周期
- 医疗、护肤、理财、法律等效果承诺
- 用户身份、经历、前后对比、第三方背书
- 平台规则、算法结论、官方政策
如果用户输入里没有可验证的结果，只能写“像”“可能”“适合”“看起来”，不要写成确定承诺。
好标题标准
好标题让刷到的人产生以下反应之一：
- 这和我有关
- 我也这样想过
- 我想点进去
- 这句话能直接放封面
- 这句话像真人说的
好标题优先像高赞评论、朋友吐槽、搜索框问题、半句话、小观察，而不是文章摘要。
造场景，不要概括观点
不要把正文中心思想压缩成标题。先找具体的人、事、动作、物件、数字、价格、表情、冲突和反常细节，再写标题。
- 观点型弱标题：你的问题不是不够努力
- 场景型强标题：发了 100 篇后，她才发现卡住的不是标题
从用户处境切入
产品、服务、课程、咨询类内容不要从卖方视角写。用户不关心“你提供什么”，用户关心“我的问题有没有被看见”。
- 卖方视角弱标题：3999 元定位服务到底值不值
- 用户视角强标题：她以为要重做定位，其实只差一篇置顶
留一点未完成
标题不要把答案说完。保留悬念、动作、冲突或问题，让用户还需要点进正文。
标题杠杆
生成时混合使用这些杠杆，不要机械堆砌。
数字
降低理解成本，制造具体感。
- 3 秒就知道封面有没有钩子
- 养成账号前先改这 1 件事
我
第一人称让标题更像真实经历。
- 我以前真的把标题写太满了
- 我承认，这个封面救了整篇笔记
你
第二人称让用户觉得和自己有关。
- 你不是没内容，是标题太像总结
- 你可能把卖点写反了
具体动作
动作比形容词更有画面。
- 她把价格擦掉以后，评论反而多了
- 封面第一行先删掉这 4 个字
轻微误读
把画面或现象合理误读成另一件事，更像人话。
- 这个标题像在替用户叹气
- 这张封面看起来有点急着成交
轻微冲突
喜欢里带一点刺，专业里带一点人话，实用里带一点反差。
- 这句话很短，但比一整段卖点有用
- 你越想讲清楚，用户越不想点
用户关系
把标题写进用户的生活、工作、消费和情绪里。
- 每个卡在起号期的人都该看一眼
- 做服务号的人最容易忽略这一句
搜索问题
适合教程、测评、清单、避坑、产品和服务内容。
- 小红书封面标题怎么写才有人点
- 服务类账号标题为什么没人看
标点节奏
逗号、句号、问号可以制造停顿。感叹号要少用。
- 我懂了，标题不是越狠越好。
- 这个标题，像不像你也写过？
半句话
像朋友话说一半，给用户一点补全欲。
- 你这个标题，太像正文第一句
- 这类封面，先别急着加卖点
标题风格
快速模式输出以下 12 组，每组必须有明显句式差异。
| 编号 | 风格 | 作用 |
|---|---|---|
| 1 | 犀利吐槽风 | 带一点刺，让用户停一下 |
| 2 | 情绪定性风 | 给用户说不出的感觉命名 |
| 3 | 悬念代价风 | 暗示点进来才知道后果 |
| 4 | 反常识风 | 和用户原本以为的不一样 |
| 5 | 冷知识风 | 提供一个新角度 |
| 6 | 强反转风 | 前后预期不一致 |
| 7 | 人话口吻风 | 像真实用户随口说 |
| 8 | 趣味夸张风 | 放大细节，但不编造事实 |
| 9 | 评论区风 | 像用户愿意接话的评论 |
| 10 | 对话提问风 | 直接向目标用户发问 |
| 11 | 数字焦虑风 | 用数字制造具体和紧迫 |
| 12 | 独体句风 | 短、准、能直接上封面 |
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.
- 12d ago First seen · 387 lines · 157 tokens per session scan A 7ee7646c2322
xiaohongshu-title is a skill published in the GitHub repository mengke-wang/xiaohongshu-ai-workbench (548 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 2,935 once invoked, about $0.0008 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…