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 feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting-skillgit clone --depth 1 https://github.com/feichanggege/ecommerce-visual-copywriting-skillWrote 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/feichanggege/ecommerce-visual-copywriting-skill/ecommerce-visual-copywriting-skill)<a href="https://agentmods.dev/skills/feichanggege/ecommerce-visual-copywriting-skill/ecommerce-visual-copywriting-skill"><img src="https://agentmods.dev/badge/skills/feichanggege/ecommerce-visual-copywriting-skill/ecommerce-visual-copywriting-skill/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/feichanggege/ecommerce-visual-copywriting-skill/ecommerce-visual-copywriting-skill"><img src="https://agentmods.dev/badge/skills/feichanggege/ecommerce-visual-copywriting-skill/ecommerce-visual-copywriting-skill.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 | $0.00224 | $0.05249 |
| Opus 5.5 | $0.00090 | $0.02100 |
| Sonnet 5.5 | $0.00045 | $0.01050 |
| Haiku 4.5 | $0.00022 | $0.00525 |
Grade A, and why
ecommerce-visual-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 today.
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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
电商视觉策划与执行
把“原始商品资料”转成“可直接交给设计师或生图模型执行”的视觉方案。默认中文；用户要求英文或双语时切换语言，但不改变证据边界和合规边界。
运行原则
- 证据优先：用户提供的包装、参数、资质、检测、品牌资料和明确事实 > 已核验的官方最新平台规则 > 本 Skill 的参考资料 > 合理假设。
- 按任务路由：只交付用户需要的层级，不强制走完整流程；不要为了“流程完整”重复追问已知信息。
- 不把假设写成事实：缺资料时标记“待确认”，不要补造销量、评价、证书、检测、专利、资质、功效、排名或平台规则。
- 先统一视觉，再写细节：同一套图必须先锁定产品身份、构图、色彩、光影、字体、背景和禁止漂移项。
- 平台规则有时效性：涉及当前尺寸、禁限词、类目政策、主图要求、资质或审核规则时，优先查官方最新来源；无法核验时明确标记“未核验”，不要凭旧规则下结论。
- 高风险合规不做最终法律结论：食品、保健品、医疗器械、健康护理、儿童用品等场景，按保守口径处理，并说明需要以目标市场法律、监管和平台最新规则为准。
执行模式
根据用户意图自动选择，不要机械暂停。
统一格式：任何模式输出完整方案或正式审查报告前，必须读取 references/output-contracts.md；标准模式的完整策略/分镜也适用。简短局部改词无需加载整份模板。
A. 标准模式
适用于缺关键证据、方向不清，或用户明确要求“先策划/先分镜/确认后再做”。
- 输出《视觉策略与证据账本》，一起列明缺口。
- 再输出可支持的 Storyboard；缺资料的部分标为待定，不虚构分镜细节。
- 只在 Storyboard 后停一次，合并必要补证与方向确认；确认后直接进入执行稿和质量门，不再逐张确认。
B. 一次性交付模式
用户明确说“直接出完整方案”“一次性给我”“按你判断做完”，或资料已经足够明确时，直接完成策略、Storyboard、执行稿和质量门，不做不必要的中途确认。
C. 审查/改稿模式
用户已经有主图、详情页、文案、Prompt 或设计稿时，不从零重做。先找出问题，再给最小必要修改：
- 转化逻辑问题
- 视觉层级问题
- 证据或合规问题
- 平台适配问题
- 文案与画面不一致
- 风格漂移
D. 设计师交接模式
用户需要“给设计师开工”的执行稿时，直接使用 references/output-contracts.md 的结构化交付格式。
模式默认值（用户没有明确说时）
用户明确指定的模式、先后顺序与确认要求优先；未指定时按下列顺序判断，命中即停：
- 已有待审/待改的主图、详情页、文案或 Prompt 成品 → C 审查/改稿；产品原图、包装图作为输入资料不自动触发审查。
- 要交给设计师或运营直接使用的执行稿 → D 设计师交接。
- 产品、平台/市场、人群、必要素材与证据足以支持本次范围 → B 一次性交付；不为凑数量强求三条卖点。
- 缺关键证据、平台/人群不清或方向需确认 → A 标准模式，只在 Storyboard 后合并确认一次。
用一句话说明当前模式。明确要求一次性交付或交接但资料有缺口时，完成可支持部分并在稿外列阻断项；不伪造事实，也不把缺口包装成已完成。
Step 0：任务路由与最小输入
先判断用户要的是哪一类产出：
- 主图 / 商品图
- 详情页 / PDP
- Amazon Listing / A+ / Brand Story
- 广告素材 / 短视频封面
- 图内文案
- Storyboard / 图片规划
- 生图 Prompt
- 合规审查 / 改稿
- 跨境本地化
优先获取以下信息：产品是什么、目标平台/市场、目标人群、核心卖点与参数、可用证据、已有视觉资料/参考图。
只有缺失信息会改变定位、合规边界或关键画面时才提出补充问题，最多 3 个；标准模式统一放在 Storyboard 后的唯一检查点。其余展示层缺口采用合理假设继续，并显式标注，不假设产品事实。
Step 1：建立证据账本
任何会进入最终页面的事实型、数据型、效果型或资质型宣称，先放入证据账本。
| 宣称/卖点 | 来源 | 状态 | 最终处理 |
|---|---|---|---|
| 包装或资料直接支持，且已核对对象/适用范围 | 包装图、参数表等具体材料 | 已确认 | 可使用，保持原意；口述不等于检测/认证证明 |
| 可由参数直接推导 | 用户资料 | 有依据 | 可转成利益表达，但不扩大 |
| 需要检测/认证/平台规则支持 | 缺少证据 | 待补证 | 改中性表达或保留占位 |
| 涉及治疗、保证性效果、虚构背书 | 无合法依据 | 禁止 | 不进入最终稿 |
What ships with it
17 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.
- agents/openai.yaml 187 B
- assets/showcase-output.svg 65 KB
- assets/showcase/figure-desktop-scene.jpg 219 KB
- assets/showcase/figure-multi-angle.jpg 182 KB
- assets/showcase/lumina-pendant-lamp.jpg 261 KB
- assets/showcase/musang-king-durian-main.jpg 175 KB
- assets/showcase/thumbs/figure-desktop-scene-thumb.jpg 88 KB
- assets/showcase/thumbs/figure-multi-angle-thumb.jpg 68 KB
- assets/showcase/thumbs/lumina-pendant-lamp-thumb.jpg 43 KB
- assets/showcase/thumbs/musang-king-durian-main-thumb.jpg 46 KB
- examples/durian-worked-example.md 4.4 KB
- examples/README.md 5.1 KB
- references/compliance-rules.md 10 KB
- references/output-contracts.md 5.2 KB
- references/platform-playbooks.md 10 KB
- references/source-notes.md 9.7 KB
- scripts/count-copy.py 754 B runs code
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.
- today Changed · +65 lines · +5 tokens per session f8f86a6f8447
- 1mo ago Changed · -30 lines · -12 tokens per session ae3a5c05c07b
- 1mo ago First seen · 241 lines · 231 tokens per session scan A eba6b45b67af
ecommerce-visual-copywriting is a skill published in the GitHub repository feichanggege/ecommerce-visual-copywriting-skill (968 stars, last pushed today), licensed MIT. It adds 224 tokens to every session and 5,249 once invoked, about $0.0009 per session on Opus 5.5. 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
doku-payment-gateway
Expert guide for integrating DOKU Payment Gateway: DOKU Checkout (Hosted & Modal Popup with HMAC-SHA256), Direct API SNAP BI Standard (VA, QRIS, Direct Debit with HMAC-SHA512), and Direct API Non-SNAP (Card Payment Page, OVO Push). Covers single-integration checkout, direct host-to-host APIs, webhook verification, and…
saas-billing
Implement and audit SaaS billing systems, subscription state machines, secure webhooks, and local database synchronization / Implementasi dan audit sistem billing SaaS, state machine langganan, webhook aman, dan sinkronisasi database lokal.
payment-gateway-expert
Expert guide for integrating payment gateways (Stripe, PayPal, Xendit, Midtrans, DOKU SNAP BI) and secure webhooks into SaaS platforms / Panduan ahli integrasi payment gateway dan webhook aman.
amazon-display-ads
Amazon Sponsored Display campaign strategy and optimization. Audience targeting, retargeting campaigns, creative optimization, and performance management. Use when the user asks about Amazon display ads, audience targeting, retargeting, or Sponsored Display campaigns.
amazon-a-plus-content
Amazon A+ Content strategy and creation. Module layouts, persuasive copy, comparison charts, image briefs, and conversion optimization. Use when the user asks about A+ Content, Enhanced Brand Content, product storytelling, or Amazon listing enhancement.
amazon-advertising-strategy
Comprehensive Amazon advertising strategy and campaign optimization. Sponsored Products, Sponsored Brands, Sponsored Display campaign management, budget allocation, ACoS optimization, and performance tracking. Use when the user asks about Amazon PPC, advertising strategy, campaign optimization, or Amazon ads…