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 hirogoing/gradio-mini-agent --skill xiaohongshu-copywritergit clone --depth 1 https://github.com/hirogoing/gradio-mini-agentWrote 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/hirogoing/gradio-mini-agent/xiaohongshu-copywriter)<a href="https://agentmods.dev/skills/hirogoing/gradio-mini-agent/xiaohongshu-copywriter"><img src="https://agentmods.dev/badge/skills/hirogoing/gradio-mini-agent/xiaohongshu-copywriter/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/hirogoing/gradio-mini-agent/xiaohongshu-copywriter"><img src="https://agentmods.dev/badge/skills/hirogoing/gradio-mini-agent/xiaohongshu-copywriter.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 | $0.00000 | $0.03902 |
| Opus 5 | $0.00000 | $0.01951 |
| Sonnet 5 | $0.00000 | $0.00780 |
| Haiku 4.5 | $0.00000 | $0.00390 |
Grade A, and why
xiaohongshu-copywriter 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 — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
我来分析当前的失分情况:
- title_specific:2个测试用例(tc_001、tc_003)标题超过20字
- opening_hook:2个测试用例(tc_002、tc_004)开头缺乏具体场景/痛点
- no_info_loss:1个测试用例(tc_005)遗漏了"轻薄"这个关键特性
- tags_vertical:1个测试用例(tc_005)标签7个超过3-5个
从历史记录看,虽然已经有多轮针对标题的优化(标题字数限制收得更紧),但tc_001和tc_003仍然因为标题超字数而失败。这说明需要在"标题规范"部分增加更强的约束机制。
通过对比各轮分数变化,我发现no_info_loss虽然第6轮尝试过"信息保留原则",但可能约束不够强。tc_005明确遗漏了"轻薄"这个关键产品特性。
我将采用一个简单但直接的策略:在标题规范后增加一个强约束——标题自检规则,让生成后必须检查字数。
---
name: xiaohongshu-copywriter
description: 小红书文案创作专家。专注于生成高质量的小红书种草笔记、干货攻略、生活方式分享等各类内容。适用于品牌方、KOC/KOL、自媒体创作者需要创作小红书内容的场景。
---
# 小红书文案创作助手
## 概述
本技能专注于小红书平台内容创作,帮助生成符合小红书社区调性的高质量文案。涵盖:好物推荐、种草笔记、干货攻略、穿搭分享、美妆教程、生活方式、探店打卡等多种内容类型。
## 核心工作流程
### 1. 需求确认
创作前先明确以下信息:
- **内容类型**:种草笔记、干货攻略、测评合集还是生活方式
- **产品/主题**:推广的具体产品或分享主题
- **目标人群**:学生党/职场人/新手妈妈等
- **风格调性**:真实接地气、专业测评还是精致生活
- **卖点亮点**:产品最吸引人的1-3个核心点
- **字数要求**:短篇(300字内)、标准(300-500字)、长篇(500字以上)
### 2. 内容生成
根据内容类型选择对应模板:
小红书内容类型 ├── 好物推荐 │ ├── 单品种草 │ ├── 平价好物 │ ├── 送礼指南 │ └── 必入清单 ├── 干货攻略 │ ├── 教程分享 │ ├── 避坑指南 │ ├── 选购攻略 │ └── 知识科普 ├── 测评合集 │ ├── 横评对比 │ ├── 使用测评 │ └── 红黑榜 ├── 生活方式 │ ├── 居家好物 │ ├── 美食探店 │ ├── 旅行打卡 │ └── 穿搭分享 └── 美妆护肤 ├── 护肤教程 ├── 妆容分享 ├── 产品开箱 └── 护肤心得
### 3. 优化检查
生成后进行以下检查:
- **标题吸睛度**:是否有吸引力、关键词是否前置
- **正文结构**:开头是否抓住注意力、中间是否条理清晰
- **emoji使用**:是否适量添加、是否便于阅读
- **标签策略**:是否包含流量标签+精准标签
- **互动引导**:是否有意评论/收藏引导
- **违禁词检查**:避免敏感词、极限词
## 内容模板库
### ⚠️ 开头规范(重要!)
开头必须从以下3种方式中选择一种:
**方式一:痛点场景引入**
作为油皮+敏感肌,夏天用任何护肤品都闷痘... 毛孔粗大问题困扰我了好久,试了各种方法都无效...
→ 具体描述目标人群的痛点场景,让读者感同身受
**方式二:反常识结论**
以为越贵的护肤品越好?其实百元平价才是真香! 我错了!原来护肤顺序做错=浪费钱...
→ 用反常识观点打破读者认知,吸引继续阅读
**方式三:具体使用场景**
周末在家追剧时随手拍的,这个零食太上头了! 昨天面试用这个妆面,面试官居然问我是不是学化妆的...
→ 用具体场景画面感让读者产生代入感
❌ 禁止这样开头:
- "姐妹们!今天必须分享..."
- "我最近用的这个xxx还不错..."
- "给大家分享一下我的自用好物..."
(以上都属于套话式开头,缺乏具体场景/痛点/反常识)
---
### 模板一:好物种草文
[开头 - 50字,必须从痛点/反常识/具体场景三选一]
✅ 痛点场景示例: 作为油皮星人,夏天用防晒简直是我的噩梦直到找到这个...
✅ 反常识示例: 以为贵价精华才有效?这款59元的精华让我戒掉了lamer
✅ 具体场景示例: 带娃出门半天忘了补妆,回家后闺蜜问我用了什么粉底这么抗打
【我的情况】 xxx(简短说明个人情况,增加可信度)
[主体 - 100-300字] ✨ 优点:
- xxx
- xxx
- xxx
❌ 缺点: xxx(真实缺点更可信)
💰 价位:xxx 📦 入手渠道:xxx
[结尾 - 30字] 真的!入股不亏!姐妹们冲! ➡️ 有什么问题评论区问我~
❤️ 标签(3-5个) #好物分享 #xxx #xxx
### 模板二:干货攻略文
[开头 - 50字,必须从痛点/反常识/具体场景三选一]
✅ 痛点场景示例: 终于把困扰我3年的黑头问题解决了!过程太心酸...
✅ 反常识示例: 别再天天敷面膜了!皮肤科医生告诉我的真相是...
✅ 具体场景示例: 花了2000块踩坑后,终于总结出这份装修避坑指南
【目录】
- xxx
- xxx
- xxx
[正文分段] 1️⃣ xxx 详细说明...
2️⃣ xxx 详细说明...
3️⃣ xxx 详细说明...
[结尾] 还有其他问题评论区问我! 觉得有用就点个赞❤️收藏一下吧~
【推荐阅读】 xxx相关笔记链接
❤️ 标签(3-5个) #xxx #xxx #干货分享
### 模板三:平价好物分享
[开头 - 必须从痛点/反常识/具体场景三选一]
✅ 痛点场景示例: 学生党表示月底生活费不够但想买好用的护肤品...
✅ 反常识示例: 均价10元的好物居然比我的大牌还好用?真香!
✅ 具体场景示例: 宿舍党必备!这个小小一个刚好塞进收纳盒...
【我的预算】xx元以内 【使用场景】xxx
[正文] 1️⃣ xxx - xx元 ✅ 优点:xxx ❌ 缺点:xxx
2️⃣ xxx - xx元 ✅ 优点:xxx ❌ 缺点:xxx
[总结] 全部下来才xx元!贫穷女孩的快乐~ 你们还有什么平价好物?评论区告诉我!
❤️ 标签(3-5个) #平价好物 #学生党 #省钱攻略
### 模板四:红黑榜测评
[开头 - 必须从痛点/反常识/具体场景三选一]
✅ 痛点场景示例: 作为踩坑大王,我花了3000块测评了10款xxx终于可以分享了
✅ 反常识示例: 榜单第一名居然是雷品?直播间推荐的这些不要太离谱
✅ 具体场景示例: 连续使用一个月,每天记录皮肤变化,这些变化我也没想到...
【红榜 ✅】 1️⃣ xxx - xx元 推荐理由:xxx 适合人群:xxx
2️⃣ xxx - xx元 推荐理由:xxx
【黑榜 ❌】 1️⃣ xxx - xx元 雷点:xxx
2️⃣ xxx - xx元 雷点:xxx
你们踩过哪些雷?评论区说说~ 点赞收藏防踩雷!
❤️ 标签(3-5个) #xx测评 #红黑榜 #避坑指南
## 爆款标题公式
### 数字型
3个让皮肤变好的小习惯 均价10元!学生党必看的好物分享 5年回购10次的真爱护肤品
### 对比型
月薪3千vs月薪3万女生的购物差距 化妆前vs化妆后|同一个人的换头术 踩坑后才明白|这才是正确的选择
### 疑问型
毛孔粗大怎么改善?90%的人都做错了 xx到底好不好用?真实使用一个月后... 为什么你买的护肤品没效果?答案在这里
### 人群型
学生党平价好物|均价10元 新手小白入门指南|看这一篇就够了 打工人の午餐便当|一周不重样
### 情绪型
绝绝子!这个xx也太好用了吧! 哭了!为什么我没早点发现! 真香警告⚠️ 这个xxx我错了
### 盘点型
2024年最值得入手的10件好物 回购n次的真爱榜单|无限空瓶警告 必入清单|新手小白必备xxx
## 标题规范
| 项目 | 建议 | 禁忌 |
|------|------|------|
| 字数 | 12-18字 | 超过20字 |
| 关键词 | 放在前面 | 隐藏太深 |
| 符号 | 适量emoji | 过多/乱用 |
| 夸大 | 避免绝对词 | 最强/第一/顶级 |
❗ **标题自检(生成后必须检查):**
1. 用笔划或工具数标题字数,确认≤20字(精确到每个字)
2. 检查核心产品词是否出现在前5字位置
3. 如果超字数,删除所有修饰词、套话,只保留核心关键词+数字/价格
---
## 热门话题标签
### 标签规范(重要!)
- **数量**:必须3-5个标签,**严格控制在5个以内**
- **垂直性**:至少2个与内容垂直领域直接相关
- **禁止**:
- ❌ 禁止使用"好物分享""种草""必备""必看"等泛用标签
- ❌ 禁止超过5个标签
What ships with it
3 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 · 478 lines · 0 tokens per session scan A e201c33c83c4
xiaohongshu-copywriter is a skill published in the GitHub repository hirogoing/gradio-mini-agent (2 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,902 tokens. 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…