Product Description Generator
nexscope-ai/eCommerce-Skills
E-commerce product description generator for any platform. An agent skill from nexscope-ai/eCommerce-Skills.
Agent skill
E-commerce Visual Copywriting
by feichanggege in feichanggege/ecommerce-visual-copywriting-skill
Turns product details, packaging, target platform and audience into an executable e-commerce image plan with copy, storyboards, image prompts and a compliance review.
SKILL.md written in Chinese; this summary is our English description.
Install E-commerce Visual Copywriting
$ npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install feichanggege/ecommerce-visual-copywriting-skill ecommerce-visual-copywriting --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ecommerce-visual-copywriting" agent skill from https://github.com/feichanggege/ecommerce-visual-copywriting-skill/tree/main into .claude/skills/ecommerce-visual-copywriting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ecommerce-visual-copywriting", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install feichanggege/ecommerce-visual-copywriting-skill ecommerce-visual-copywriting --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ecommerce-visual-copywriting" agent skill from https://github.com/feichanggege/ecommerce-visual-copywriting-skill/tree/main into .agents/skills/ecommerce-visual-copywriting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ecommerce-visual-copywriting", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install feichanggege/ecommerce-visual-copywriting-skill ecommerce-visual-copywriting --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ecommerce-visual-copywriting" agent skill from https://github.com/feichanggege/ecommerce-visual-copywriting-skill/tree/main into .cursor/skills/ecommerce-visual-copywriting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ecommerce-visual-copywriting", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install feichanggege/ecommerce-visual-copywriting-skill ecommerce-visual-copywriting --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ecommerce-visual-copywriting" agent skill from https://github.com/feichanggege/ecommerce-visual-copywriting-skill/tree/main into .gemini/skills/ecommerce-visual-copywriting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ecommerce-visual-copywriting", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install feichanggege/ecommerce-visual-copywriting-skill ecommerce-visual-copywritingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ecommerce-visual-copywriting" agent skill from https://github.com/feichanggege/ecommerce-visual-copywriting-skill/tree/main into .github/skills/ecommerce-visual-copywriting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ecommerce-visual-copywriting", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install feichanggege/ecommerce-visual-copywriting-skill ecommerce-visual-copywriting --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ecommerce-visual-copywriting" agent skill from https://github.com/feichanggege/ecommerce-visual-copywriting-skill/tree/main into .opencode/skills/ecommerce-visual-copywriting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ecommerce-visual-copywriting", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ecommerce-visual-copywriting- GitHub stars
- 867
- Token cost
- ~1.3k tokens
- SKILL.md length
- 294 words
- Files
- 30 (incl. references, assets)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turns product details, packaging, target platform and audience into an executable e-commerce image plan with copy, storyboards, image prompts and a compliance review.
- Works in 7 steps: ：任务路由与最小输入 → ：建立证据账本 → ：判断成交驱动力 → …
- Planning main images and detail pages for a Taobao, Amazon or Shopify product
- SKILL.md covers 运行原则, 执行模式, Step 0：任务路由与最小输入 and Step 1：建立证据账本, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Written mostly in Chinese, this skill converts raw product material into visual plans that a designer or image model can execute, covering main images, detail pages, Amazon listings and A+ content, in-image copy, storyboards, design notes and image-generation prompts. It works through an evidence ledger of claims, a choice of purchase driver, a Campaign Style Lock that fixes product identity, composition, color, light and type, and a storyboard.
Evidence comes first: nothing you have not supplied is invented, including sales, reviews, certificates, test results or efficacy, and unconfirmed claims become neutral wording or are marked as pending. Platform rules are checked against official sources when current rules matter, and high-risk categories such as food, health products and baby goods get conservative treatment without a final legal conclusion. Modes include a plan-then-confirm flow, one-shot delivery, review and revision of existing material, and designer handoff. It asks at most three questions.
When your agent uses it
- Planning main images and detail pages for a Taobao, Amazon or Shopify product
- Writing in-image copy and image-generation prompts for a product set
- Reviewing existing e-commerce images or copy for evidence and platform-rule problems
- Localizing a product listing for a cross-border market
Example prompts
- “Plan five main images for our stainless steel water bottle on Amazon, using the packaging photos I attached.”
- “Review this detail page copy for claims we cannot back up.”
- “Write image-generation prompts for a camellia oil gift box on Tmall with one consistent style.”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4a5a639. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
E-commerce Visual Copywriting loads about 1.3k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 294 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from feichanggege/ecommerce-visual-copywriting-skill at commit 4a5a639, republished under its MIT licence (© feichanggege). 294 words, ~1,281 tokens.
Download SKILL.mdSave it as
.claude/skills/ecommerce-visual-copywriting/SKILL.md (or your agent's skills folder). This skill also uses 29 other files; get the full folder from GitHub.- name
- ecommerce-visual-copywriting
- description
- 将商品资料、包装与资质、目标平台、目标人群和视觉参考转成可直接执行的电商视觉方案，包括转化策略、Campaign Style Lock、主图/详情页/Listing/A+ Storyboard、图内文案、设计说明、生图 Prompt、证据与合规审查。适用于淘宝、天猫、京东、拼多多、抖音小店，以及 Amazon、Shopify、TikTok Shop、Temu、Shopee、Lazada 等电商场景；当用户提到主图、详情页、Listing、A+、商品卖点、视觉脚本、图片规划、图内文案、生图 Prompt、点击率/转化率、平台合规、广告法审查、设计师执行稿或跨境商品本地化时使用。不得编造资质、数据、销量、评价、认证或功效；涉及当前平台规则或高风险合规结论时优先核验官方最新来源。
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。
A. 标准模式
适用于方向不清、视觉成本高、用户明确要求“先策划/先分镜/确认后再做”。
- 先输出《视觉策略与证据账本》。
- 再输出 Storyboard。
- 在真正进入大量最终文案或生图 Prompt 前等待确认。
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。
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追问，最多追问 3 个关键问题；其余缺失项采用最合理假设继续，并显式标注假设。
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 |
|---|---|---|---|
| 包装或资料明确写明 | 用户资料 | 已确认 | 可使用，保持原意 |
| 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 |
最终稿只能使用“已确认”或“有依据”的内容。“待补证”必须转为中性表达、占位符或待确认项。
Step 2：判断成交驱动力
不要默认所有产品都用同一套“痛点文案”。从下列类型中选 1 个主驱动力 + 最多 1 个辅驱动力：
| 驱动力 | 典型场景 | 视觉重点 |
|---|---|---|
| 视觉/质感 | 美妆、饰品、家居、礼盒 | 材质、光影、比例、包装、氛围 |
| 痛点/效率 | 清洁、收纳、工具、生活用品 | 问题场景、使用前后、步骤缩短 |
| 理性/参数 | 3C、家电、设备、功能型商品 | 参数翻译、机制、规格、兼容性 |
| 信任/证据 | 食品、茶饮、母婴、高客单商品 | 产地、工艺、资质、检测、品牌证据 |
| 情绪/身份 | 香氛、服饰、礼赠、宠物、生活方式 | 场景、审美、仪式感、身份认同 |
然后把卖点做成：Feature -> Advantage -> Benefit -> Evidence。
只保留 Top 3 购买理由。没有证据支撑的“猛卖点”不因为转化需要而放宽边界。
Step 3：锁定 Campaign Style Lock
至少明确：
- 产品身份：包装文字、Logo、颜色、比例、结构、材质、关键细节必须保持什么不变。
- 构图体系：主体占比、视角、留白、视线流向、是否允许人物/道具。
- 色彩体系：主色、辅助色、强调色；避免无理由漂移。
- 光影体系：自然光、棚拍、硬光、柔光、轮廓光等。
- 字体与信息密度：标题、数字、说明层级；移动端优先可读。
- 背景与场景：纯底、棚拍、真实场景、品牌氛围。
- Reference Fidelity：有参考图时，列出必须保留与允许变化的元素。
- Negative Constraints：禁止新增的 Logo、配件、纹理、人物特征、结构、功效符号或不真实细节。
如果用户上传了产品图或包装图，必须先以图中真实产品为准，不得为了“更好看”擅自改包装结构、Logo、口味、规格或配件。
Step 4：规划 Storyboard
不要把“5 张主图”当成死规则。默认可用 5 张作为起点，但应根据平台、用户要求和信息量调整。
常见主图任务：
| 角色 | 任务 |
|---|---|
| Hero / KV | 一眼识别产品 + 单一核心购买理由 |
| Benefit | 把核心参数或功能翻译成用户收益 |
| Proof | 用真实证据建立信任 |
| Compare | 用客观维度降低选择成本，不虚构竞品数据 |
| Scene | 放入真实使用场景，强化代入 |
| Spec / CTA | 规格、组合、适用条件或下一步决策信息 |
详情页/PDP 常见叙事顺序：
承接首屏 -> Top Benefits -> 机制/材质/工艺 -> 场景 -> 证据 -> 对比/选择 -> FAQ -> 规格/CTA
根据商品和平台删减，不强行凑模块。
涉及 Amazon、Shopify、TikTok Shop、Temu、Shopee、Lazada、淘宝、天猫、京东、拼多多、抖音小店等平台时，读取 references/platform-playbooks.md。如果用户问的是当前具体审核规则、尺寸、禁词或类目要求，优先核验官方最新规则。
Step 5：执行输出
每张图/每个模块至少交付：
- 视觉任务：这张图负责解决什么决策问题。
- 画面描述：主体、构图、镜头、背景、材质、光影、信息层级。
- 图内文案：标题 + 必要副文案；优先短、具体、可证实。
- 设计说明：第一视觉落点、阅读顺序、数字/证据如何突出、免责声明或注释放哪里。
- 生图 Prompt：主体 + 构图 + 场景 + 材质 + 光影 + Style Lock + 参考图约束。
- Negative Prompt / 禁止项：避免包装变形、Logo 错误、文字乱码、结构新增、人物肢体异常、风格漂移等。
- 证据备注：如果该图含数据、资质、对比或效果表述，标出其证据来源。
跨境场景不要逐字翻译中文卖点。做本地化：保留事实边界，调整表达习惯、单位、场景、购买理由和信息密度。
Step 6：五维质量门
先检查硬性阻断项，再做质量判断。
硬性阻断项
出现任一项，不能直接交付最终稿：
- 编造或无法追溯的资质、检测、认证、销量、评价、排名、专利、数据。
- 产品身份与用户素材冲突，例如包装、规格、颜色、Logo、结构被改错。
- 把“待补证”内容写成确定事实。
- 当前平台规则未核验却写成“平台明确规定”。
- 高风险品类使用治疗、保证性效果或扩大批准范围的表达。
五维 Pass/Fail
| 维度 | Pass 条件 |
|---|---|
| 证据与合规 | 关键宣称可追溯，风险项已降级或删除 |
| 转化逻辑 | 每张图有独立决策任务，Top 3 购买理由清楚 |
| 视觉层级 | 第一落点明确，文字密度和主体比例合理 |
| 一致性 | Style Lock、产品身份、字体、色彩、光影不漂移 |
| 可执行性 | 设计师或生图模型无需猜关键元素即可执行 |
任一维度 Fail，就修对应问题后再交付。不要用其他维度的高分抵消。
如果用户明确要求量化评分，可使用 1–5 分并给出每一分的可解释依据；不要用没有锚点的“80/100”制造伪精确。
合规与时效性
涉及合规时读取 references/compliance-rules.md。该文件是保守执行框架，不是法律意见。
特别注意：
- 免责声明不能“修复”本身不允许的宣称。
- 绝对化、比较、价格、认证、健康/医疗、功效、用户评价等表达都要看证据和目标市场。
- 普通食品、保健食品/膳食补充剂、医疗器械、健康护理、儿童用品等不可混用同一套宣称逻辑。
- 平台规则、法律、监管政策和类目要求可能变化；能联网或有官方文档时优先核验。
参考文件加载规则
只在需要时加载，避免无效占用上下文：
references/compliance-rules.md：合规审查、高风险品类、数据/功效/资质宣称。references/platform-playbooks.md：平台差异、页面任务分工、跨境场景。references/output-contracts.md：完整执行稿、设计师交接、审查报告的固定结构。examples/README.md：需要示例输入输出时。
关键失败模式
- 过度追问：资料足够时仍不断问问题。改为明确假设并继续。
- 流程机械化：用户要求一次性完整交付却强制停两次。按执行模式处理。
- 固定 5 张：不看平台和信息量硬凑 5 张。按视觉任务调整数量。
- 卖点堆砌：一张图塞多个购买理由。每张图只解决一个主要决策问题。
- 平台规则过期：把历史经验写成当前规则。需要时核验官方最新来源。
- 合规靠敏感词：只删词不看宣称逻辑。必须看“事实 -> 证据 -> 用户理解”。
- 跨境直译：中文文案逐字翻译。改做本地化重写。
- 参考图失真：为了视觉效果擅自改变产品结构或包装。优先产品真实性。
E-commerce Visual Copywriting v3.0 · Canonical entrypoint: SKILL.md
© feichanggege, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 29 other files (references, assets) in the repository root of feichanggege/ecommerce-visual-copywriting-skill.
- SKILL.md
- .claude-plugin/marketplace.json
- CONTRIBUTING.md
- LICENSE
- README.en.md
- README.md
- ROADMAP.md
- SKILL.en.md
- agents/openai.yaml
- assets/showcase-output.svg
- assets/showcase/enquan-camellia-oil.png
- assets/showcase/figure-desktop-scene.png
- assets/showcase/figure-multi-angle.png
- assets/showcase/lumina-pendant-lamp.png
- assets/showcase/musang-king-durian-main.jpg
- assets/showcase/thumbs/figure-desktop-scene-thumb.jpg
- … and 14 more
Open the folder on GitHubat commit 4a5a639
Compare with similar skills
E-commerce Visual Copywriting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| E-commerce Visual Copywriting this skillfeichanggege/ecommerce-visual-copywriting-skill | 867 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Product Description Generatornexscope-ai/eCommerce-Skills | 1.1k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Memstack Content Product Descriptioncwinvestments/memstack | 423 | — | ~2.6k | Automated safety check: Pass | Proprietary | |
| Shopifythatrebeccarae/claude-marketing | 161 | — | ~2.4k | Automated safety check: Notes | MIT | |
| 05 Ad Copy Globalminhnv0807/ai-business-skills | 609 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Shopify Marketingnexscope-ai/eCommerce-Skills | 1.1k | — | ~3.8k | Automated safety check: Pass | MIT |
Similar skills
Memstack Content Product Description
cwinvestments/memstack
A skill your agent uses when the user says 'product description', 'product listing', 'product copy', 'Amazon listing', 'Shopify listing', 'e-commerce copy', or needs conversion-optimized product…
Shopify
thatrebeccarae/claude-marketing
Shopify e-commerce platform marketing expertise. An agent skill from thatrebeccarae/claude-marketing.
05 Ad Copy Global
minhnv0807/ai-business-skills
A skill your agent uses when the user needs PAID ad copy for Meta, Google, or TikTok — six variants across TOFU, MOFU, and BOFU using AIDA, PAS, and BAB, respecting each platform character limit and…
Shopify Marketing
nexscope-ai/eCommerce-Skills
Comprehensive Shopify marketing strategy and execution. An agent skill from nexscope-ai/eCommerce-Skills.
Xurl
LeoYeAI/openclaw-master-skills
A Twitter research and content intelligence skill focused on attracting WordPress and Shopify clients.
Related
Works with
Categories
Questions about E-commerce Visual Copywriting
What does E-commerce Visual Copywriting do?
Turns product details, packaging, target platform and audience into an executable e-commerce image plan with copy, storyboards, image prompts and a compliance review. Written mostly in Chinese, this skill converts raw product material into visual plans that a designer or image model can execute, covering main images, detail pages, Amazon listings and A+ content, in-image copy, storyboards, design notes and image-generation prompts. It works through an evidence ledger of claims, a choice of purchase driver, a Campaign Style Lock that fixes product identity, composition, color, light and type, and a storyboard.
When should I use E-commerce Visual Copywriting?
E-commerce Visual Copywriting fits situations like: planning main images and detail pages for a Taobao, Amazon or Shopify product; writing in-image copy and image-generation prompts for a product set; reviewing existing e-commerce images or copy for evidence and platform-rule problems; localizing a product listing for a cross-border market.
How do I install E-commerce Visual Copywriting in Claude Code?
Run `npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a claude-code`. Or copy the skill folder (the feichanggege/ecommerce-visual-copywriting-skill repository) into .claude/skills/ecommerce-visual-copywriting in your project. Claude Code loads it when a task matches its description.
How do I install E-commerce Visual Copywriting in Codex?
Run `npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a codex`. Or copy the skill folder (the feichanggege/ecommerce-visual-copywriting-skill repository) into .agents/skills/ecommerce-visual-copywriting in your project. Codex loads it when a task matches its description.
Can I use E-commerce Visual Copywriting in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add feichanggege/ecommerce-visual-copywriting-skill --skill ecommerce-visual-copywriting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ecommerce-visual-copywriting, .gemini/skills/ecommerce-visual-copywriting, .github/skills/ecommerce-visual-copywriting and .opencode/skills/ecommerce-visual-copywriting in your project.
What does E-commerce Visual Copywriting need to run?
SKILL.md names no scripts, command-line tools or credentials: E-commerce Visual Copywriting is instructions for the agent only.
Does E-commerce Visual Copywriting access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is E-commerce Visual Copywriting safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does E-commerce Visual Copywriting use?
E-commerce Visual Copywriting is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does E-commerce Visual Copywriting use?
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.
What are the alternatives to E-commerce Visual Copywriting?
Skills that share tags, products or a category with E-commerce Visual Copywriting: Product Description Generator (nexscope-ai/eCommerce-Skills, 1.1k stars), Memstack Content Product Description (cwinvestments/memstack, 423 stars), Shopify (thatrebeccarae/claude-marketing, 161 stars) and 05 Ad Copy Global (minhnv0807/ai-business-skills, 609 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains E-commerce Visual Copywriting?
feichanggege (a GitHub user) maintains it in feichanggege/ecommerce-visual-copywriting-skill, which has 867 GitHub stars. The repository was last updated on September 17, 2026.
Source: feichanggege/ecommerce-visual-copywriting-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.