1. Currently Supported Skills

2. guishu-gpt-image-2: gpt-image-2 Image Generation Skill

guishu-gpt-image-2 is an image generation automation Skill for the LLM API Gateway. It uses an OpenAI-compatible API and calls gpt-image-2 by default. It can turn prompts written by an Agent into images and save the images, request parameters, and a local preview page together.

What You Can Use It For

• Generate illustrations or posters for newsletters, social media posts, and product pages.
• Create advertising assets, community announcements, and event visual drafts in batches.
• Let an Agent generate images automatically while completing a task, such as covers, icons, banners, or product images.
• Give customer demos: enter a description and generate a local image with a preview page.

Installation

clawhub install guishu-gpt-image-2

API Key Configuration

The Skill checks environment variables in the following order. We recommend using LLM_TOKEN_API_KEY first:

1. LLM_TOKEN_API_KEY
2. GUI_SHU_TOKEN_KEY
3. OPENAI_API_KEY

export LLM_TOKEN_API_KEY="sk-你的贵数Token"

Quick Start Example

python3 {baseDir}/scripts/generate.py \
  --prompt "一张精致的蓝色智能音箱产品海报，干净背景，柔和棚拍光，适合电商首页" \
  --size 1024x1024 \
  --quality high \
  --n 1

Output

• Generated image files, saved to the local output directory by default.
• prompts.json: A record of the prompts used for the current run.
• request.json: The request parameters for review and reuse.
• index.html: A local image preview page for quickly checking the results.

Related Links

• Web image generator: https://image2.gpt-agent.cc/
• Detailed guide:

3. feishu-public-table-monitor: Public Feishu Table Monitoring Skill

feishu-public-table-monitor monitors publicly accessible Feishu Wiki and document pages. It locates a pricing or model table near a specified section, detects version date changes, added or removed models, multiplier changes, and pricing changes, then formats them as Markdown suitable for customer notifications or Telegram messages.

What You Can Use It For

• Monitor model pricing tables for multipliers, prices per 1 million Tokens, and model availability.
• Monitor model lists for additions, removals, and naming convention changes.
• Monitor public product tables for changes to plans, pricing, product lists, and promotions.
• Add it to a scheduled task that stays silent when nothing changes and generates a notification when a change is detected.

Installation

clawhub install feishu-public-table-monitor

Quick Start Example

For the first run, print a snapshot to confirm that the correct table was captured.

Before running the command, enable public internet sharing for the target document in Feishu. Then replace PASTE_YOUR_PUBLIC_FEISHU_DOC_URL_HERE below with its public Feishu URL. Links that require sign-in cannot be monitored.

FEISHU_PUBLIC_DOC_URL='PASTE_YOUR_PUBLIC_FEISHU_DOC_URL_HERE'
python3 {baseDir}/scripts/monitor_feishu_price_table.py \
  "$FEISHU_PUBLIC_DOC_URL" \
  --section-title '模型价格与计费说明' \
  --print-snapshot

After confirming the result, run it again to establish a baseline. On future scheduled runs, it outputs NO_REPLY if nothing has changed. If it detects a change, it outputs a formatted Markdown notification.

FEISHU_PUBLIC_DOC_URL='PASTE_YOUR_PUBLIC_FEISHU_DOC_URL_HERE'
python3 {baseDir}/scripts/monitor_feishu_price_table.py \
  "$FEISHU_PUBLIC_DOC_URL" \
  --section-title '模型价格与计费说明' \
  --title '贵数 Token 模型价格变更提醒'

Recommended Workflow

1. Use --print-snapshot to confirm that the correct table was captured.
2. Run the Skill normally once to create a local baseline snapshot.
3. Add it to cron, an OpenClaw scheduled task, or your own Agent workflow.
4. Do not send anything when it outputs NO_REPLY. When it outputs Markdown, send that message directly to customers or group chats.

Related Documentation

• Model list:
• Model pricing and billing:

4. Using the Skills After Installation

Return to the main guide for more information about models, pricing, and API access.