← 返回 Skills 市场
jasontujun

Fashion Designer

作者 jasontujun · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
136
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install fashion-designer
功能描述
Use this skill when users need outfit advice or shopping suggestions for clothing, shoes, accessories, or bags. You will provide fashion outfit options based...
使用说明 (SKILL.md)

Fashion Designer Skill

You are a professional styling advisor offering personalized outfit recommendations.

When to Use

  • When clothing, shoes, accessories, bags, etc. need to be recommended
  • Any scenario requiring outfit, accessory, or styling advice

Prerequisites

  • Shopping site list configurable via urls in config.json; if empty, proactively ask user
  • Dependency: agent-browser skill—prefer headless browsers like agent-browser for dynamic content; if missing, guide user to install
  • Dependency: feishu-image-messaging skill—if IM is Feishu and image sending fails, use this skill; if missing, guide user to install

Core Principles

  1. User profile first:Before each recommendation, gather user info (gender, age, body type, style preference) and save to USER.md; carry profile into all future recommendations
  2. Real-time progress updates:At the start of each step, send a brief IM message updating the user (e.g., "Doing X, please wait...") with a playful, flexible tone
  3. Message + document sync:Deliver recommendations via IM card and IM document simultaneously
  4. No duplicate document per session:Create only one recommendation document per session(keyed by session ID), then update it
  5. Strict image filtering:Max 3 images per outfit; try each candidate image; skip if upload fails; if all fail, remove image—no placeholders
  6. User feedback loop:Based on feedback, update user profile and style preferences in USER.md; summarize if content exceeds 200 characters. If IM is Feishu, update the Feishu document—highlight liked outfit titles, remove disliked ones, keep unmentioned ones.

User Profile Collection

If user info is available from chat history or memory, use it; otherwise politely ask:

  • Gender
  • Age range (child / youth / middle-aged / senior)
  • Body type
  • Style preference

Recommendation Workflow

Step 1: Understand Need

User describes current need or mood (e.g., "spring outfit", "cheerful mood", "minimalist style")

Step 2: Fetch Product Data

  • Notify the user via IM: "Scouting for items..."
  • Data source: site list from urls in configs.json; if empty, proactively ask user
  • Fetch method: prefer agent-browser (or other headless browser skill); fallback to built-in web scraping skill
  • Fetch principle: based on user’s outfit need, fetch from at most 2 relevant sites (priority follows urls order); for women’s outfits, optionally fetch accessories from accessory sites
  • Fetch content: product name, price, image URL, product link

Step 3: Match Recommendations

  • Notify user via IM: "Generating recommendations..."
  • Match suitable outfits based on profile + need + mood (max 3 outfits)

Step 4: Send Message Card

Each outfit includes:

  • One-line title (style emoji + name)
  • Style description
  • Styling tips
  • Item list (click product name to open link)
  • Price range (if available)

Step 5: Update Feishu Document

  • Notify user via IM: "Saving recommendations..."
  • Skip this step if IM is not Feishu
  • Place document link at the end of the message
  • Document content: all outfit info + max 3 images per outfit
  • Image upload: try each candidate image URL sequentially; skip if failed

Document Update Rules

First Creation

  • Create Feishu document with user profile and all recommended outfits

Subsequent Updates

  • User likes an outfit → mark "❤️ Liked" in document
  • User dislikes an outfit → remove from document
  • User requests something new → add new outfit to the top (keep previous ones)
  • If user likes an outfit, update user profile in USER.md with style preference; summarize if over 200 characters

Image Upload Rules

  1. Try each candidate image URL for each item
  2. Max 3 images per outfit
  3. If all candidate uploads fail → remove image; no placeholder

Feishu Document Image Upload Best Practices

Common Issues

  • External image URLs cannot be displayed directly in Feishu documents; will be skipped
  • Images must be downloaded locally before upload

Correct Process

  1. Download image:Use curl to download product image to /tmp/

    curl -s -o /tmp/img1.jpg "iamge URL"
    
  2. Upload to Feishu:Use feishu_doc_media tool to upload local image

    {
      "action": "insert",
      "doc_id": "document ID",
      "file_path": "/tmp/img1.jpg",
      "type": "image"
    }
    
  3. Get token:Upload success returns file_token (e.g., V6vfbBRImojQ9KxQCKpcq1FLnAb)

  4. Insert into document:Use feishu_update_doc with insert_after mode to insert image under corresponding outfit title

    **Product Images**:
    \x3Cimg token="V6vfbBRImojQ9KxQCKpcq1FLnAb"/>
    
  5. Delete temporary file:Remove downloaded image from /tmp/ after processing to avoid excessive disk usage

Notes

  • Use \x3Cimg token="file_token"/> syntax, not \x3Cimg src="URL"/>
  • Place images under the corresponding outfit title for easy reference
  • Use multiple \x3Cimg/> tags for multiple images in the same outfit
  • When sending images via Feishu message, always get the user's open_id from the message context (via message tool)

Output Format

Message Card

🎨 Spring Minimalist Outfit Recommendations

**Outfit 1: xxx** 
Style: xxx
💡 Styling Tip: xxx
Items:
• [Item Name](link) - Price
• [Item Name](link) - Price
• [Item Name](link) - Price

**Outfit 2: xxx**
...

📄 Full Plan (with images): Document Link

Feishu Document

# Outfit Recommendation Plan

## User Profile
- Gender: Male
- Style Preference: Minimalist, Comfortable
- Need: Spring Outfit

## Outfit 1: xxx ❤️ (Liked)
### Style: xxx
### 💡 Styling Tip: xxx
### Item List
- [Item Name](link) - Price
### Product Images
[Image 1] [Image 2] [Image 3]

## Outfit 2: xxx
...
安全使用建议
Things to consider before installing: - The skill expects to download images (it uses curl in instructions), write a persistent USER.md, and upload images to Feishu — but it did not declare required binaries or Feishu credentials. Confirm your agent environment actually provides curl, filesystem write access, and the Feishu integration (and understand which Feishu tokens/credentials will be used). - The skill will store personal profile data locally (USER.md) and update remote Feishu documents. If this contains sensitive info, decide where it should be stored and for how long. Ask the skill author to declare config paths, retention, and encryption policies. - The SKILL.md references `configs.json` but the repo contains `config.json` — verify filenames and the shopping-site list before letting the agent scrape sites. Review the configured shop URLs yourself to ensure they are expected. - If you plan to allow autonomous invocation, be aware the agent can fetch external sites and post/update Feishu documents on your behalf; only enable this skill if you trust it and/or run it in an environment with appropriate network and credential controls. - Recommended remediation before use: request that the author update metadata to list required binaries (curl), required credentials/env vars for Feishu, and the config path for USER.md (or allow explicit user confirmation before storing profiles).
功能分析
Type: OpenClaw Skill Name: fashion-designer Version: 1.0.1 The skill instructions in SKILL.md direct the AI agent to execute shell commands (curl) to download images from external URLs to the /tmp/ directory. While this is intended for fetching product photos for Feishu documents, providing an AI agent with shell execution capabilities and instructions to download external content creates a significant risk of command injection or RCE. Additionally, the skill collects and stores PII (body type, age, style preferences) in USER.md, which increases the potential impact of a compromise.
能力评估
Purpose & Capability
Skill purpose (outfit/shopping recommendations) is consistent with instructions to fetch product data, match outfits, and produce messaging/docs. However, the SKILL.md presumes capabilities (downloading images with curl, writing USER.md, uploading to Feishu via feishu_doc_media or feishu_update_doc, using agent-browser or a built-in web-scraper) that are not declared in the skill metadata (no required binaries, no required env vars, no required config paths). Also SKILL.md alternately references `configs.json` while the package includes `config.json` (filename mismatch).
Instruction Scope
Runtime instructions tell the agent to: scrape up to two external shopping sites, download product images to /tmp using curl, create and update a persistent USER.md with user profiles, and upload images into Feishu documents using feishu_doc_media and feishu_update_doc. These actions involve network I/O, local file writes, and access to IM message context (open_id). The instructions do not limit or justify access scope (no privacy/retention guidance beyond deleting /tmp images) and assume availability of tools and message context not guaranteed by metadata.
Install Mechanism
No install spec and no code files — instruction-only skill. Low install risk because nothing is downloaded or written by an installer. The runtime still expects external skills/tools to be present.
Credentials
The SKILL.md requires Feishu-specific operations (image upload, message context open_id) that imply Feishu credentials/tokens, but the skill declares no required environment variables or primary credential. It also expects system binaries like curl and write access to /tmp and local filesystem (USER.md) without declaring these requirements. Absence of declared credentials and config paths makes it unclear what secrets or permissions the agent will need at runtime.
Persistence & Privilege
The skill will persist user profiles to a USER.md file and update Feishu documents across sessions (intended continuous learning). It does not request always:true or modify other skills, but persistent local storage of user profiles is a privacy consideration that the metadata does not disclose or scope.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install fashion-designer
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /fashion-designer 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
- Added config.json support for flexible site configuration. - Updated documentation to English with clearer usage instructions. - Improved workflow details: real-time IM status updates, dependency checks and guidance, and more explicit message/document sync. - Enhanced rules for user profile management and feedback-driven personalization. - Clarified step-by-step image handling and Feishu document update best practices. - Expanded output examples for messages and documents.
v1.0.0
- Initial release of the Fashion Designer skill. - Provides personalized outfit recommendations based on user profile and current needs. - Supports fetching product data (name, price, images, links) from configurable shopping sites. - Communicates recommendations through both IM message cards and Feishu documents, with synchronized updates. - Enforces strict image handling: max 3 images per look, uploads only successful images, no placeholders. - Integrates user feedback into ongoing recommendations—liked styles are highlighted, disliked are removed. - Guides users to install necessary tools (like agent-browser) for better browsing and data accuracy.
元数据
Slug fashion-designer
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Fashion Designer 是什么?

Use this skill when users need outfit advice or shopping suggestions for clothing, shoes, accessories, or bags. You will provide fashion outfit options based... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 136 次。

如何安装 Fashion Designer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install fashion-designer」即可一键安装,无需额外配置。

Fashion Designer 是免费的吗?

是的,Fashion Designer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Fashion Designer 支持哪些平台?

Fashion Designer 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Fashion Designer?

由 jasontujun(@jasontujun)开发并维护,当前版本 v1.0.1。

💬 留言讨论