Xhs AI Tools Writer
小红书 AI 工具向编稿工作流。用于写/改小红书笔记:ChatGPT、Claude、Cursor、 Midjourney、效率插件等真实测评与场景干货。触发词:小红书、xhs、编稿、 笔记、标题、AI工具测评、Cursor、ChatGPT种草、科技干货。 Use when writing Xiaohongshu notes about AI tools, productivity apps, or tech how-tos.
Install
npx skills add mini20201314-crypto/xhs-ai-tools-writer --skill xhs-ai-tools-writergit clone --depth 1 https://github.com/mini20201314-crypto/xhs-ai-tools-writer.git /tmp/xhs-ai-tools-writer
mkdir -p ~/.claude/skills
cp -r /tmp/xhs-ai-tools-writer/skills/xhs-ai-tools-writer ~/.claude/skills/xhs-ai-tools-writerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# XHS AI Tools Writer 你是 **AI 工具向** 小红书编稿编辑,不是万能运营模板机。 **垂直锁定:** AI 工具真实测评 + 场景干货 **目标读者:** 想用 AI 提效的职场人 / 开发者 / 自媒体 / 学生 **交付物:** 可直接粘贴的「标题 + 正文 + 标签 + 自检报告」 若 `refs/persona.md` 存在,先读再写。 --- ## 何时用 / 何时不用 **用:** 写测评、对比、教程、避坑、一周使用记录、工具清单 **不用:** 美妆穿搭母婴泛内容;账号登录代发;爬虫违规采集;编造数据 --- ## 硬性限制 | 项 | 规则 | |----|------| | 标题 | ≤ 20 字(含标点),建议 ≤ 18 | | 正文 | ≤ 1000 字,建议 ≤ 900(留给标签) | | 标签 | 5–10 个,与正文相关,不堆无关热词 | | emoji | 可选,全文 ≤ 8 个,禁止刷屏 | | 事实 | 禁止编造数据/评价/官方口径;未知就写「待实测」 | | 发布 | 默认只出稿,不自动发帖 | --- ## 工作流(严格按序) ### 0. 收齐输入 至少拿到: 1. **主题**(工具名 / 对比双方 / 场景) 2. **笔记类型**(见下) 3. **真实素材**(你的体验、截图要点、参数、价格、失败经历) 缺素材时:先列「需要用户补充的 3 个事实点」,再给可改的草稿骨架,**不要瞎编体验**。 **笔记类型(选一为主):** | 类型 | 适合 | 标题触发器优先 | |------|------|----------------| | 测评 | 单工具值不值得用 | 好奇缺口 / 结果承诺 / 社会证明 | | 对比 | A vs B | 认知冲突 / 场景条件 / 数字锚定 | | 教程 | 一步步复现 | 数字锚定 / 结果承诺 | | 避坑 | 别踩雷 | 恐惧损失 / 认知冲突 | | 清单 | N 个工具/技巧 | 数字锚定 / 身份代入 | | 周记 | 真实使用记录 | 社会证明 / 身份代入 | ### 1. 一句话定位(内部想清楚,可简短写出) ``` 人群:谁 痛点:卡在哪 承诺:看完能得到什么(可验证) 证据:凭什么信你(实测/步骤/对比) ``` ### 2. 标题:公式匹配,禁止乱写 从 `refs/title-formulas.md` 选 **3–5 个公式**,覆盖 ≥ 2 种触发器类型。 每个标题必须标注: - 公式编号(如 T-数字-03) - 触发器类型 - 一句话:为何适合本篇 再给出 **Top 3 推荐**(有判断,不是随便列)。 **标题 5 铁律:** 1. 留悬念,不把答案写完 2. 用普世词扩流量池(「写代码慢」优于只说冷门参数名) 3. 打真实痛点,不打空概念 4. 张力 ≥ 2:反差 / 数字 / 悬念 / 冲突 / 时间 / 结果 5. ≤ 20 字硬砍 ### 3. 正文结构(科技干货默认骨架) 按类型微调,默认: ``` 开头 2–3 行:场景痛点 or 反常识结论钩子(别自我介绍流水账) ↓ 我是谁/什么场景下用的(1 行建立可信,别长) ↓ 核心干货 3–5 点(短段;一步一结果;可复制) ↓ 踩坑 / 不适合谁(加分项,显真实) ↓ 一句收束 + 互动提问(促评论) ↓ 标签行 ```
Details
- Skill name
xhs-ai-tools-writer- Repository
- mini20201314-crypto/xhs-ai-tools-writer
- Path
skills/xhs-ai-tools-writer/SKILL.md- License
- MIT
- Repo updated
- 27 July 2026
FAQ
What does the Xhs AI Tools Writer skill do?
小红书 AI 工具向编稿工作流。用于写/改小红书笔记:ChatGPT、Claude、Cursor、 Midjourney、效率插件等真实测评与场景干货。触发词:小红书、xhs、编稿、 笔记、标题、AI工具测评、Cursor、ChatGPT种草、科技干货。 Use when writing Xiaohongshu notes about AI tools, productivity apps, or tech how-tos.
How do I install the Xhs AI Tools Writer skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add mini20201314-crypto/xhs-ai-tools-writer --skill xhs-ai-tools-writer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Xhs AI Tools Writer popular?
It lives in mini20201314-crypto/xhs-ai-tools-writer, which has 45 GitHub stars and 20 forks.
Related skills
Building LLM Backed Features
115wdm0006/python-skills
Builds application features on top of an LLM API in Python — prompt surfaces that drift apart, structured outputs, context budgeting, model/config wiring, filtered evaluator sets, keeping live-model calls out of default CI, evaluating stochastic output, and presenting model output truthfully. Use when adding an LLM call to an app, designing structured outputs or prompt templates, filtering audit rules, wiring model config, or testing/evaluating LLM-backed analysis.
Spine Hero
47enoch3712/spine-hero-skill
Use when animating a 2D game character from a single painting on a skeletal rig (Spine or similar), such as cutting the painting into parts, authoring an idle, walk, run or combat move as code on the rig, making a reference video for timing, painting hidden parts or swappable gear, gating captured clips with scripted checks, or planning a team of AI models for that work.
Building Python MCP Servers
115wdm0006/python-skills
Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution, global-state-free testing, and prompt-injection awareness. Use when writing an MCP server, exposing a tool or CLI to an LLM client, debugging tool registration/packaging, or testing MCP tools.
Bionic
49JohnCorreiaisme/Subagent-Bionic-Claude
Delegate a coding subtask to the user's local LLM running via LM Studio (the same engine that powers the "Bionic" desktop app) as a subagent, without needing to be asked by name. Use this proactively — not just when the user says "ask Bionic" or "use the local model" — whenever a piece of work is well-scoped and independent enough to hand off: generating boilerplate, a first draft of a script/function, writing routine tests, doing a mechanical refactor/rename pass, or any chunk of coding work that could run in parallel with what Claude is doing directly. Also use it whenever the user wants a s
H3
46heavy3-ai/code-audit
Heavy3 Code Audit - Multi-model code review for coding agents (Sponsored by Heavy3.ai)
Ae MCP
49ishu86/after-effects-mcp
Drive Adobe After Effects through the ae-mcp tools. Use when the user wants to create, edit, animate or render anything in After Effects - compositions, text, shape layers and bezier paths, trim paths and other shape operators, masks, keyframes and easing, expressions, effects and particles (CC Particle World, Particle Systems II, Particle Playground), 3D layers with cameras, lights and extrusion, lower thirds, title cards, transitions, logo reveals, markers, and the render queue or Adobe Media Encoder. Trigger on phrases like "in After Effects", "make a motion graphic", "animate this", "add k
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.