baoyu-skills

Install

npx skills add jimliu/baoyu-skills

This is third-party code. Review the repository files before installing.

What it does

Jim Liu's skill set covers the publishing pipeline. Some skills generate images: illustrations based on article structure, covers, infographics, diagrams, cards and comics through a chosen generation backend. Others handle text: format Markdown, translate documents, turn a web page or YouTube video into Markdown and a summary. Others publish to X, Weibo and WeChat official accounts, including Markdown to WeChat HTML conversion.

Who it is for. For writers and content managers producing articles and posts with an agent.

Example request

Read article.md, find spots that need illustrations and generate them in one style

Limitations

Requires Node.js and bun. Image generation goes through external services or the agent's built-in tools. Publishing needs WeChat API keys and social accounts. Skills prefixed with danger use unofficial access to the Gemini and X web apps, which may violate those services' terms. Some instructions and triggers are in Chinese.

How to disable. Uninstall the baoyu-skills plugin via /plugin or remove individual skills with npx skills remove. Keys live in ~/.baoyu-skills/.env or the project's .baoyu-skills/.env.

Security check

• Publishes posts to social networks on the user's behalf
• Some skills use unofficial access to web services

README in short

The README asks you to install only needed skills and shows installing via npx skills, as a Claude Code marketplace and selectively into .agents/skills for Codex. It explains where to store WeChat keys per user or project and how to publish individual skills to ClawHub. It then documents each skill with parameters and examples. MIT licensed.

SKILL.md

---
name: baoyu-article-illustrator
description: Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".
version: 1.117.4
metadata:
  openclaw:
    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-article-illustrator
---

# Article Illustrator

Analyze articles, identify illustration positions, generate images with Type × Style × Palette consistency.

## User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

1. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.
2. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
3. **Batching**: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.

Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.

## Image Generation Tools

When this skill needs to render an image, resolve the backend in this order:

1. **Current-request override** — if the user names a specific backend in the current message, use it.
2. **Saved preference** — if `EXTEND.md` sets `preferred_image_backend` to a backend available right now, use it.
3. **Auto-select** (when the preference is `auto`, unset, or the pinned backend isn't available):

Related