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 sanhuang520-ship-it/awesome-chinese-ai-tools --skill ecommerce-copywritinggit clone --depth 1 https://github.com/sanhuang520-ship-it/awesome-chinese-ai-toolsWrote 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/sanhuang520-ship-it/awesome-chinese-ai-tools/ecommerce-copywriting)<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/ecommerce-copywriting"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/ecommerce-copywriting/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/sanhuang520-ship-it/awesome-chinese-ai-tools/ecommerce-copywriting"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/ecommerce-copywriting.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 | $0.00080 | $0.01512 |
| Opus 5 | $0.00040 | $0.00756 |
| Sonnet 5 | $0.00016 | $0.00302 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
ecommerce-copywriting 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
电商文案助手
把"卖点"翻译成"买点"——用户不关心你的产品有什么，只关心能解决他什么问题。
什么时候用
商品标题、详情页、主图文案、卖点提炼、种草笔记、直播话术、评价引导、客服话术。
第一步：先要这 5 个信息
没有这些就写不准，缺了就问（一次问完）：
- 平台（淘宝/拼多多/抖音小店/小红书/京东 —— 规则差别很大）
- 品类 + 产品名
- 价格带（决定文案调性：9.9 拼便宜 vs 999 拼品质）
- 核心卖点（最多 3 个，用户自己认为的优势）
- 目标人群（谁买、为谁买）
⚠️ 不要编造参数。材质、成分、认证、检测报告这些，用户没提供就问，不能自己想。写错要担责。
平台差异（关键）
| 平台 | 标题逻辑 | 文案调性 | 长度 |
|---|---|---|---|
| 淘宝/天猫 | 关键词堆叠，覆盖搜索词 | 专业、参数详实 | 标题 30 字 |
| 拼多多 | 直给利益点，强调便宜 | 直白、口语 | 标题 30 字 |
| 京东 | 品牌 + 型号 + 规格 | 正式、可信 | 标题 30 字 |
| 抖音小店 | 场景 + 痛点 | 口语、有钩子 | 短平快 |
| 小红书 | 不堆词，像分享 | 真实、有个人体验感 | 标题 20 字内 |
标题公式
淘宝/京东/拼多多（搜索驱动）：
品牌 + 核心词 + 属性词 + 场景词 + 修饰词
例：XX 保温杯 316不锈钢 大容量 学生上班族 便携水杯
规则：
- 核心词必须是用户真实会搜的（不是你造的新词）
- 不堆无关词，会被降权
- 30 字用满，但不重复
小红书/抖音（内容驱动）：
痛点/场景 + 反差/数字 + 情绪钩子
例：租房党必看｜300块把出租屋改造成ins风
详情页结构
按用户决策顺序排，不是按你想说的顺序：
- 主图区（3 秒决定去留）—— 一句话说清"这是什么 + 给谁 + 解决什么"
- 痛点共鸣 —— 先说他的问题，不是你的产品
- 核心卖点（3 个，每个配场景）—— 卖点要翻译成买点
- 信任背书 —— 检测报告/销量/评价/资质（只写用户提供的真实信息）
- 规格参数 —— 表格，清晰
- 使用场景/搭配 —— 帮他想象拥有后的样子
- 售后保障 —— 打消最后顾虑
卖点翻译（核心方法）
| 已知事实（产品视角） | 可写方向（用户视角） | 发布前还要核对 |
|---|---|---|
| 容量 500ml | 减少频繁添水 | 杯体可用容量与目标人群饮水场景 |
| 杯盖带提环 | 通勤时更方便拿取 | 提环结构、承重与真实使用情况 |
| 用户提供保温检测报告 | 写明报告中的温度、时长与条件 | 报告主体、样品、日期和引用是否完整 |
方法：每写一个参数，追问一句"所以呢？用户能因此获得什么？"
合规红线（必须遵守）
高风险或需证据审查的表达（不是脱离语境即可套用的完整“禁词表”）：
- 《广告法》第九条明确列举的绝对化用语及可能构成同类含义的表达，需要结合语境审查。
- 排名、销量、复购率、检测结果、专家推荐、认证等引证内容，必须有真实、合法、有效且与商品匹配的材料。
- 医疗、药品、保健食品、医疗器械、化妆品、食品等品类另有专门规则；功效宣称不能套用通用商品话术。
- “100%”“绝对”“永久”“终身”等承诺容易造成无法证明或误导性表达，不能仅靠换同义词规避审查。
替代表达：
- "最好" → 删除主观排名，改写为可核对的产品事实
- "第一" → 只有在真实依据、适用范围和引用方式均核对后，才考虑使用对应数据
- "杀菌" → 若没有适用品类资质和检测依据，不写功效；可描述已经核实的结构或清洁方式
⚠️ 这里提供的是文案风险筛查，不是法律意见、平台审核结果或“替换词免责表”。规则会变化；发布前需由广告主结合当前法规、平台规则、商品资质和证明材料复核。
输出格式
默认给：3 个标题备选 + 详情页文案 + 5 个主图文案点
用户可追加要：直播话术、种草笔记、客服 FAQ、评价引导话术。
注意事项
- 不编造数据。销量、好评率、检测结果，没有就不写。
- 不抄竞品。可以参考结构，不能照搬文案。
- 口语化优先。详情页不是说明书，用人话。
- 一屏一个重点。手机屏幕小，别堆信息。
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 · 109 lines · 80 tokens per session scan A 58b6a71d9889
ecommerce-copywriting is a skill published in the GitHub repository sanhuang520-ship-it/awesome-chinese-ai-tools (10 stars, last pushed 8d ago), licensed MIT. It adds 80 tokens to every session and 1,512 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
should-i-buy
Helps the user decide on a purchase by taking the product links they're considering, asking a couple of sharp clarifying questions about their needs and circumstances, then opening each link in real Chrome via the Claude-in-Chrome extension to extract price, specs, ratings, reviews, return policy, and shipping.…
shop-research
Researches products across Amazon, Google Shopping, and relevant specialty sites using the Claude-in-Chrome browser extension. Finds candidates matching user-specified criteria (gift, gadget, gear, home goods, etc.), captures screenshots and key data per candidate, then generates a modern 2026 HTML report with…
searchcans-product-serp-brief-zh
A Chinese-language research skill that collects Google Shopping, web, image, and selected merchant-page results for a product query in a specific market. It produces an evidence brief, not a complete catalogue or live price database.
etsy-listing-optimizer
Audit, rewrite, prioritize, and monitor Etsy or marketplace listings using public-safe product data. Use when the user asks to optimize an Etsy listing, improve product titles, tags, descriptions, keyword fit, marketplace SEO, listing batches, shop audits, eRank-style keyword review, competitor notes, or listing…
apparel-demand
Analyzes apparel demand prediction systems for trend forecasting, size curve optimization, color and style analytics, sell-through rate tracking, and markdown optimization following CPFR collaborative planning and GTIN product identification standards..
franchise-inventory
Analyze franchise inventory management for par level optimization, waste tracking and root cause analysis, and theoretical vs. actual usage variance.