Skip to content
Back to search

baoyu-skills

MarketplaceWorks with Claude CodeGitHub

Skills shared by Baoyu for improving daily work efficiency with AI Agents (Claude Code, Codex, etc.).

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jimliu-baoyu-skills/badge.svg)](/listings/jimliu-baoyu-skills)

HTML

<a href="/listings/jimliu-baoyu-skills"><img src="/api/listings/jimliu-baoyu-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

> **Tip**: This repository contains 20+ skills. Install only the ones you actually need — bulk-installing every skill adds unnecessary context overhead for your AI agent on every run.

Quick Install (Recommended)

npx skills add jimliu/baoyu-skills

Codex Project-Level Install

If you only need a subset of skills in one project, you do not need to install the full plugin. Codex scans `.agents/skills` inside a project, so copy or symlink each needed skill as a full directory:

<project>/.agents/skills/baoyu-cover-image/SKILL.md
<project>/.agents/skills/baoyu-article-illustrator/SKILL.md
<project>/.agents/skills/baoyu-post-to-wechat/SKILL.md

For a WeChat Official Account article workflow, the usual minimal set is:

- `baoyu-cover-image` - `baoyu-article-illustrator` - `baoyu-post-to-wechat`

You do not need to install `baoyu-markdown-to-html` separately. `baoyu-post-to-wechat` already includes the Markdown to WeChat-ready HTML conversion flow. Install `baoyu-format-markdown` only if you need to first turn raw text or drafts into structured Markdown articles with titles, summaries, headings, bold text, lists, and similar formatting.

Place WeChat API credentials according to the scope you want:

- User-level: `~/.baoyu-skills/.env` - Project-level: `<project>/.baoyu-skills/.env`

Project-level `.env` files are useful when credentials should apply only to the current project. Do not commit them to Git.

Publish to ClawHub / OpenClaw

This repository now supports publishing each `skills/baoyu-*` directory as an individual ClawHub skill.

# Preview what would be published
./scripts/sync-clawhub.sh --dry-run

# Publish all changed skills from ./skills
./scripts/sync-clawhub.sh --all

ClawHub installs skills individually, not as one marketplace bundle. After publishing, users can install specific skills such as:

clawhub install baoyu-image-gen
clawhub install baoyu-markdown-to-html

Publishing to ClawHub releases the published skill under `MIT-0`, per ClawHub's registry rules.

Register as Plugin Marketplace

Run the following command in the Agent:

/plugin marketplace add JimLiu/baoyu-skills

Install Skills

**Option 1: Via Browse UI**

1. Select **Browse and install plugins** 2. Select **baoyu-skills** 3. Select the **baoyu-skills** plugin 4. Select **Install now**

**Option 2: Direct Install**

# Install the marketplace's single plugin
/plugin install baoyu-skills@baoyu-skills

**Option 3: Ask the Agent**

Simply tell the Agent:

> Please install Skills from github.com/JimLiu/baoyu-skills

Available Plugin

The marketplace now exposes a single plugin so each skill is registered exactly once.

| Plugin | Description | Includes | |--------|-------------|----------| | **baoyu-skills** | Content generation, AI backends, and utility tools for daily work efficiency | All skills in this repository, organized below as Content Skills, AI Generation Skills, and Utility Skills |

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 42 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "baoyu-skills",
  3. "owner": {
  4. "name": "Jim Liu (宝玉)",
  5. "email": "junminliu@gmail.com"
  6. },
  7. "metadata": {
  8. "description": "Skills shared by Baoyu for improving daily work efficiency",
  9. "version": "2.5.2"
  10. },
  11. "plugins": [
  12. {
  13. "name": "baoyu-skills",
  14. "description": "Content generation, AI backends, and utility tools for daily work efficiency",
  15. "source": "./",
  16. "strict": false,
  17. "skills": [
  18. "./skills/baoyu-article-illustrator",
  19. "./skills/baoyu-comic",
  20. "./skills/baoyu-compress-image",
  21. "./skills/baoyu-cover-image",
  22. "./skills/baoyu-danger-gemini-web",
  23. "./skills/baoyu-danger-x-to-markdown",
  24. "./skills/baoyu-diagram",
  25. "./skills/baoyu-electron-extract",
  26. "./skills/baoyu-format-markdown",
  27. "./skills/baoyu-image-gen",
  28. "./skills/baoyu-infographic",
  29. "./skills/baoyu-markdown-to-html",
  30. "./skills/baoyu-post-to-weibo",
  31. "./skills/baoyu-post-to-wechat",
  32. "./skills/baoyu-post-to-x",
  33. "./skills/baoyu-slide-deck",
  34. "./skills/baoyu-translate",
  35. "./skills/baoyu-url-to-markdown",
  36. "./skills/baoyu-wechat-summary",
  37. "./skills/baoyu-xhs-images",
  38. "./skills/baoyu-youtube-transcript"
  39. ]
  40. }
  41. ]
  42. }
README.md · README · 1,418 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # baoyu-skills
  2. English | [中文](./README.zh.md)
  3. Skills shared by Baoyu for improving daily work efficiency with AI Agents (Claude Code, Codex, etc.).
  4. ## Prerequisites
  5. - Node.js environment installed
  6. - Ability to run `npx bun` commands
  7. ## Installation
  8. > **Tip**: This repository contains 20+ skills. Install only the ones you actually need — bulk-installing every skill adds unnecessary context overhead for your AI agent on every run.
  9. ### Quick Install (Recommended)
  10. ```bash
  11. npx skills add jimliu/baoyu-skills
  12. ```
  13. ### Codex Project-Level Install
  14. If you only need a subset of skills in one project, you do not need to install the full plugin. Codex scans `.agents/skills` inside a project, so copy or symlink each needed skill as a full directory:
  15. ```text
  16. <project>/.agents/skills/baoyu-cover-image/SKILL.md
  17. <project>/.agents/skills/baoyu-article-illustrator/SKILL.md
  18. <project>/.agents/skills/baoyu-post-to-wechat/SKILL.md
  19. ```
  20. For a WeChat Official Account article workflow, the usual minimal set is:
  21. - `baoyu-cover-image`
  22. - `baoyu-article-illustrator`
  23. - `baoyu-post-to-wechat`
  24. You do not need to install `baoyu-markdown-to-html` separately. `baoyu-post-to-wechat` already includes the Markdown to WeChat-ready HTML conversion flow. Install `baoyu-format-markdown` only if you need to first turn raw text or drafts into structured Markdown articles with titles, summaries, headings, bold text, lists, and similar formatting.
  25. Place WeChat API credentials according to the scope you want:
  26. - User-level: `~/.baoyu-skills/.env`
  27. - Project-level: `<project>/.baoyu-skills/.env`
  28. Project-level `.env` files are useful when credentials should apply only to the current project. Do not commit them to Git.
  29. ### Publish to ClawHub / OpenClaw
  30. This repository now supports publishing each `skills/baoyu-*` directory as an individual ClawHub skill.
  31. ```bash
  32. # Preview what would be published
  33. ./scripts/sync-clawhub.sh --dry-run
  34. # Publish all changed skills from ./skills
  35. ./scripts/sync-clawhub.sh --all
  36. ```
  37. ClawHub installs skills individually, not as one marketplace bundle. After publishing, users can install specific skills such as:
  38. ```bash
  39. clawhub install baoyu-image-gen
  40. clawhub install baoyu-markdown-to-html
  41. ```
  42. Publishing to ClawHub releases the published skill under `MIT-0`, per ClawHub's registry rules.
  43. ### Register as Plugin Marketplace
  44. Run the following command in the Agent:
  45. ```bash
  46. /plugin marketplace add JimLiu/baoyu-skills
  47. ```
  48. ### Install Skills
  49. **Option 1: Via Browse UI**
  50. 1. Select **Browse and install plugins**
  51. 2. Select **baoyu-skills**
  52. 3. Select the **baoyu-skills** plugin
  53. 4. Select **Install now**
  54. **Option 2: Direct Install**
  55. ```bash
  56. # Install the marketplace's single plugin
  57. /plugin install baoyu-skills@baoyu-skills
  58. ```
  59. **Option 3: Ask the Agent**
  60. Simply tell the Agent:
  61. > Please install Skills from github.com/JimLiu/baoyu-skills
  62. ### Available Plugin
  63. The marketplace now exposes a single plugin so each skill is registered exactly once.
  64. | Plugin | Description | Includes |
  65. |--------|-------------|----------|
  66. | **baoyu-skills** | Content generation, AI backends, and utility tools for daily work efficiency | All skills in this repository, organized below as Content Skills, AI Generation Skills, and Utility Skills |
  67. ## Update Skills
  68. To update skills to the latest version:
  69. 1. Run `/plugin` in the Agent
  70. 2. Switch to **Marketplaces** tab (use arrow keys or Tab)
  71. 3. Select **baoyu-skills**
  72. 4. Choose **Update marketplace**
  73. You can also **Enable auto-update** to get the latest versions automatically.
  74. ![Update Skills](./screenshots/update-plugins.png)
  75. ## Available Skills
  76. Skills are organized into three categories:
  77. ### Featured Design Skill: baoyu-design
  78. If you want a design-focused Agent Skill, check out [JimLiu/baoyu-design](https://github.com/JimLiu/baoyu-design). It is a separate project that runs Claude Design locally in Cursor, Claude Code, Codex, Claude Desktop, or any file-capable coding agent, producing polished UI mockups, interactive prototypes, wireframes, landing pages, dashboards, mobile apps, and slide decks as self-contained HTML.
  79. <a href="https://github.com/JimLiu/baoyu-design">
  80. <img src="https://raw.githubusercontent.com/JimLiu/baoyu-design/main/assets/screenshots/cursor-reader-mac-app.webp" alt="Cursor running baoyu-design" width="720">
  81. </a>
  82. ```bash
  83. npx skills add JimLiu/baoyu-design
  84. ```
  85. ### Content Skills
  86. Content generation and publishing skills.
  87. #### baoyu-xhs-images
  88. Xiaohongshu image card series generator. Breaks down content into 1-10 cartoon-style image cards with **Style × Layout** system and optional palette override.
  89. ```bash
  90. # Auto-select style and layout
  91. /baoyu-xhs-images posts/ai-future/article.md
  92. # Specify style
  93. /baoyu-xhs-images posts/ai-future/article.md --style notion
  94. # Specify layout
  95. /baoyu-xhs-images posts/ai-future/article.md --layout dense
  96. # Combine style and layout
  97. /baoyu-xhs-images posts/ai-future/article.md --style notion --layout list
  98. # Override palette
  99. /baoyu-xhs-images posts/ai-future/article.md --style notion --palette macaron
  100. # Direct content input
  101. /baoyu-xhs-images 今日星座运势
  102. # Non-interactive (skip all confirmations, for scheduled tasks)
  103. /baoyu-xhs-images posts/ai-future/article.md --yes
  104. /baoyu-xhs-images posts/ai-future/article.md --yes --preset knowledge-card
  105. ```
  106. **Styles** (visual aesthetics): `cute` (default), `fresh`, `warm`, `bold`, `minimal`, `retro`, `pop`, `notion`, `chalkboard`, `study-notes`, `screen-print`, `sketch-notes`
  107. **Palettes** (optional color override): `macaron`, `warm`, `neon`
  108. **Style Previews**:
  109. | | | |
  110. |:---:|:---:|:---:|
  111. | ![cute](./screenshots/xhs-images-styles/cute.webp) | ![fresh](./screenshots/xhs-images-styles/fresh.webp) | ![warm](./screenshots/xhs-images-styles/warm.webp) |
  112. | cute | fresh | warm |
  113. | ![bold](./screenshots/xhs-images-styles/bold.webp) | ![minimal](./screenshots/xhs-images-styles/minimal.webp) | ![retro](./screenshots/xhs-images-styles/retro.webp) |
  114. | bold | minimal | retro |
  115. | ![pop](./screenshots/xhs-images-styles/pop.webp) | ![notion](./screenshots/xhs-images-styles/notion.webp) | ![chalkboard](./screenshots/xhs-images-styles/chalkboard.webp) |
  116. | pop | notion | chalkboard |
  117. **Layouts** (information density):
  118. | Layout | Density | Best for |
  119. |--------|---------|----------|
  120. | `sparse` | 1-2 pts | Covers, quotes |
  121. | `balanced` | 3-4 pts | Regular content |
  122. | `dense` | 5-8 pts | Knowledge cards, cheat sheets |
  123. | `list` | 4-7 items | Checklists, rankings |
  124. | `comparison` | 2 sides | Before/after, pros/cons |
  125. | `flow` | 3-6 steps | Processes, timelines |
  126. **Layout Previews**:
  127. | | | |
  128. |:---:|:---:|:---:|
  129. | ![sparse](./screenshots/xhs-images-layouts/sparse.webp) | ![balanced](./screenshots/xhs-images-layouts/balanced.webp) | ![dense](./screenshots/xhs-images-layouts/dense.webp) |
  130. | sparse | balanced | dense |
  131. | ![list](./screenshots/xhs-images-layouts/list.webp) | ![comparison](./screenshots/xhs-images-layouts/comparison.webp) | ![flow](./screenshots/xhs-images-layouts/flow.webp) |
  132. | list | comparison | flow |
  133. #### baoyu-infographic
  134. Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics.
  135. ```bash
  136. # Auto-recommend combinations based on content
  137. /baoyu-infographic path/to/content.md
  138. # Specify layout
  139. /baoyu-infographic path/to/content.md --layout hub-spoke
  140. # Specify style (default: craft-handmade)
  141. /baoyu-infographic path/to/content.md --style technical-schematic
  142. # Specify both
  143. /baoyu-infographic path/to/content.md --layout funnel --style corporate-memphis
  144. # With aspect ratio (named preset or custom W:H)
  145. /baoyu-infographic path/to/content.md --aspect portrait
  146. /baoyu-infographic path/to/content.md --aspect 3:4
  147. ```
  148. **Options**:
  149. | Option | Description |
  150. |--------|-------------|
  151. | `--layout <name>` | Information layout (21 options, default: bento-grid) |
  152. | `--style <name>` | Visual style (22 options, default: craft-handmade) |
  153. | `--aspect <ratio>` | Named: landscape (16:9), portrait (9:16), square (1:1). Custom: any W:H ratio (e.g., 3:4, 4:3, 2.35:1) |
  154. | `--lang <code>` | Output language (en, zh, ja, etc.) |
  155. | `--no-confirm` | Skip the combination confirmation step and generate directly |
  156. | `--ref <files...>` | Reference images for style, palette, composition, or subject guidance |
  157. **Layouts** (information structure):
  158. | Layout | Best For |
  159. |--------|----------|
  160. | `linear-progression` | Timelines, processes, tutorials |
  161. | `binary-comparison` | A vs B, before-after, pros-cons |
  162. | `comparison-matrix` | Multi-factor comparisons |
  163. | `hierarchical-layers` | Pyramids, priority levels |
  164. | `tree-branching` | Categories, taxonomies |
  165. | `hub-spoke` | Central concept with related items |
  166. | `structural-breakdown` | Exploded views, cross-sections |
  167. | `bento-grid` | Multiple topics, overview (default) |
  168. | `iceberg` | Surface vs hidden aspects |
  169. | `bridge` | Problem-solution |
  170. | `funnel` | Conversion, filtering |
  171. | `isometric-map` | Spatial relationships |
  172. | `dashboard` | Metrics, KPIs |
  173. | `periodic-table` | Categorized collections |
  174. | `comic-strip` | Narratives, sequences |
  175. | `story-mountain` | Plot structure, tension arcs |
  176. | `jigsaw` | Interconnected parts |
  177. | `venn-diagram` | Overlapping concepts |
  178. | `winding-roadmap` | Journey, milestones |
  179. | `circular-flow` | Cycles, recurring processes |
  180. | `dense-modules` | High-density modules, data-rich guides |
  181. **Legacy Layout Previews**:
  182. > **Note:** These images retain the legacy layout names and are provided as visual references only. They do not represent the current `--layout` values listed above.
  183. >
  184. > **TODO:** Regenerate previews for all 21 current layouts and replace this gallery.
  185. | | | |
  186. |:---:|:---:|:---:|
  187. | ![bridge](./screenshots/infographic-layouts/bridge.webp) | ![circular-flow](./screenshots/infographic-layouts/circular-flow.webp) | ![comparison-table](./screenshots/infographic-layouts/comparison-table.webp) |
  188. | bridge | circular-flow | comparison-table |
  189. | ![do-dont](./screenshots/infographic-layouts/do-dont.webp) | ![equation](./screenshots/infographic-layouts/equation.webp) | ![feature-list](./screenshots/infographic-layouts/feature-list.webp) |
  190. | do-dont | equation | feature-list |
  191. | ![fishbone](./screenshots/infographic-layouts/fishbone.webp) | ![funnel](./screenshots/infographic-layouts/funnel.webp) | ![grid-cards](./screenshots/infographic-layouts/grid-cards.webp) |
  192. | fishbone | funnel | grid-cards |
  193. | ![iceberg](./screenshots/infographic-layouts/iceberg.webp) | ![journey-path](./screenshots/infographic-layouts/journey-path.webp) | ![layers-stack](./screenshots/infographic-layouts/layers-stack.webp) |
  194. | iceberg | journey-path | layers-stack |
  195. | ![mind-map](./screenshots/infographic-layouts/mind-map.webp) | ![nested-circles](./screenshots/infographic-layouts/nested-circles.webp) | ![priority-quadrants](./screenshots/infographic-layouts/priority-quadrants.webp) |
  196. | mind-map | nested-circles | priority-quadrants |
  197. | ![pyramid](./screenshots/infographic-layouts/pyramid.webp) | ![scale-balance](./screenshots/infographic-layouts/scale-balance.webp) | ![timeline-horizontal](./screenshots/infographic-layouts/timeline-horizontal.webp) |
  198. | pyramid | scale-balance | timeline-horizontal |
  199. | ![tree-hierarchy](./screenshots/infographic-layouts/tree-hierarchy.webp) | ![venn](./screenshots/infographic-layouts/venn.webp) | |
  200. | tree-hierarchy | venn | |
  201. **Styles** (visual aesthetics):
  202. | Style | Description |
  203. |-------|-------------|
  204. | `craft-handmade` (Default) | Hand-drawn illustration, paper craft aesthetic |
  205. | `claymation` | 3D clay figures, playful stop-motion |
  206. | `kawaii` | Japanese cute, big eyes, pastel colors |
  207. | `storybook-watercolor` | Soft painted illustrations, whimsical |
  208. | `chalkboard` | Colorful chalk on black board |
  209. | `cyberpunk-neon` | Neon glow on dark, futuristic |
  210. | `bold-graphic` | Comic style, halftone dots, high contrast |
  211. | `aged-academia` | Vintage science, sepia sketches |
  212. | `corporate-memphis` | Flat vector people, vibrant fills |
  213. | `technical-schematic` | Blueprint, isometric 3D, engineering |
  214. | `origami` | Folded paper forms, geometric |
  215. | `pixel-art` | Retro 8-bit, nostalgic gaming |
  216. | `ui-wireframe` | Grayscale boxes, interface mockup |
  217. | `subway-map` | Transit diagram, colored lines |
  218. | `ikea-manual` | Minimal line art, assembly style |
  219. | `knolling` | Organized flat-lay, top-down |
  220. | `lego-brick` | Toy brick construction, playful |
  221. | `pop-laboratory` | Blueprint grid, coordinate markers, lab precision |
  222. | `morandi-journal` | Hand-drawn doodles, warm Morandi tones |
  223. | `retro-pop-grid` | 1970s pop art, Swiss grid, thick outlines |
  224. | `hand-drawn-edu` | Macaron pastels, hand-drawn wobble, stick figures |
  225. | `retro-popup-pop` | Retro popup collage, vintage UI, flat pop colors |
  226. **Selected Style Previews**:
  227. | | | |
  228. |:---:|:---:|:---:|
  229. | ![craft-handmade](./screenshots/infographic-styles/craft-handmade.webp) | ![claymation](./screenshots/infographic-styles/claymation.webp) | ![kawaii](./screenshots/infographic-styles/kawaii.webp) |
  230. | craft-handmade | claymation | kawaii |
  231. | ![storybook-watercolor](./screenshots/infographic-styles/storybook-watercolor.webp) | ![chalkboard](./screenshots/infographic-styles/chalkboard.webp) | ![cyberpunk-neon](./screenshots/infographic-styles/cyberpunk-neon.webp) |
  232. | storybook-watercolor | chalkboard | cyberpunk-neon |
  233. | ![bold-graphic](./screenshots/infographic-styles/bold-graphic.webp) | ![aged-academia](./screenshots/infographic-styles/aged-academia.webp) | ![corporate-memphis](./screenshots/infographic-styles/corporate-memphis.webp) |
  234. | bold-graphic | aged-academia | corporate-memphis |
  235. | ![technical-schematic](./screenshots/infographic-styles/technical-schematic.webp) | ![origami](./screenshots/infographic-styles/origami.webp) | ![pixel-art](./screenshots/infographic-styles/pixel-art.webp) |
  236. | technical-schematic | origami | pixel-art |
  237. | ![ui-wireframe](./screenshots/infographic-styles/ui-wireframe.webp) | ![subway-map](./screenshots/infographic-styles/subway-map.webp) | ![ikea-manual](./screenshots/infographic-styles/ikea-manual.webp) |
  238. | ui-wireframe | subway-map | ikea-manual |
  239. | ![knolling](./screenshots/infographic-styles/knolling.webp) | ![lego-brick](./screenshots/infographic-styles/lego-brick.webp) | |
  240. | knolling | lego-brick | |
  241. #### baoyu-diagram
  242. Generate publication-ready SVG diagrams from source material — flowcharts, sequence/protocol diagrams, structural/architecture diagrams, and illustrative intuition diagrams. Analyzes input material to recommend diagram type(s) and splitting strategy, confirms the plan once, then generates all diagrams. Claude writes real SVG code directly following a cohesive design system. Output is self-contained `.svg` files with embedded styles and auto dark-mode.
  243. ```bash
  244. # Topic string — skill analyzes and proposes a plan
  245. /baoyu-diagram "how JWT authentication works"
  246. /baoyu-diagram "Kubernetes architecture" --type structural
  247. /baoyu-diagram "OAuth 2.0 flow" --type sequence
  248. # File path — skill reads, analyzes, and proposes a plan
  249. /baoyu-diagram path/to/article.md
  250. # Language and output path
  251. /baoyu-diagram "微服务架构" --lang zh
  252. /baoyu-diagram "build pipeline" --out docs/build-pipeline.svg
  253. ```
  254. **Options**:
  255. | Option | Description |
  256. |--------|-------------|
  257. | `--type <name>` | `flowchart`, `sequence`, `structural`, `illustrative`, `class`, `auto` (default). Skips type recommendation. |
  258. | `--lang <code>` | Output language (en, zh, ja, ...) |
  259. | `--out <path>` | Output file path. Generates exactly one diagram focused on the most important aspect. |
  260. **Diagram types**:
  261. | Type | Reader need | Verbs that trigger it |
  262. |------|-------------|------------------------|
  263. | `flowchart` | Walk me through the steps in order | walk through, steps, process, lifecycle, workflow, state machine |
  264. | `sequence` | Who talks to whom, in what order | protocol, handshake, auth flow, OAuth, TCP, request/response |
  265. | `structural` | Show me what's inside what, how it's organised | architecture, components, topology, layout, what's inside |
  266. | `illustrative` | Give me the intuition — draw the mechanism | how does X work, explain X, intuition for, why does X do Y |
  267. | `class` | What are the types and how are they related | class diagram, UML, inheritance, interface, schema |
  268. Not an image-generation skill — no LLM image model is called. Claude writes the SVG by hand with hand-computed layout math, so every diagram honors the design system. Embedded `<style>` block with `@media (prefers-color-scheme: dark)` means the same file renders correctly in both light and dark mode anywhere it's embedded.
  269. #### baoyu-cover-image
  270. Generate cover images for articles with 5 dimensions: Type × Palette × Rendering × Text × Mood. Combines 11 color palettes with 7 rendering styles for 77 unique combinations.
  271. ```bash
  272. # Auto-select all dimensions based on content
  273. /baoyu-cover-image path/to/article.md
  274. # Quick mode: skip confirmation, use auto-selection
  275. /baoyu-cover-image path/to/article.md --quick
  276. # Specify dimensions (5D system)
  277. /baoyu-cover-image path/to/article.md --type conceptual --palette cool --rendering digital
  278. /baoyu-cover-image path/to/article.md --text title-subtitle --mood bold
  279. # Style presets (backward-compatible shorthand)
  280. /baoyu-cover-image path/to/article.md --style blueprint
  281. # Specify aspect ratio (default: 16:9)
  282. /baoyu-cover-image path/to/article.md --aspect 2.35:1
  283. # Visual only (no title text)
  284. /baoyu-cover-image path/to/article.md --no-title
  285. ```
  286. **Five Dimensions**:
  287. - **Type**: `hero`, `conceptual`, `typography`, `metaphor`, `scene`, `minimal`
  288. - **Palette**: `warm`, `elegant`, `cool`, `dark`, `earth`, `vivid`, `pastel`, `mono`, `retro`, `duotone`, `macaron`
  289. - **Rendering**: `flat-vector`, `hand-drawn`, `painterly`, `digital`, `pixel`, `chalk`, `screen-print`
  290. - **Text**: `none`, `title-only` (default), `title-subtitle`, `text-rich`
  291. - **Mood**: `subtle`, `balanced` (default), `bold`
  292. #### baoyu-slide-deck
  293. Generate professional slide deck images from content. Creates comprehensive outlines with style instructions, then generates individual slide images.
  294. ```bash
  295. # From markdown file
  296. /baoyu-slide-deck path/to/article.md
  297. # With style and audience
  298. /baoyu-slide-deck path/to/article.md --style corporate
  299. /baoyu-slide-deck path/to/article.md --audience executives
  300. # Target slide count
  301. /baoyu-slide-deck path/to/article.md --slides 15
  302. # Outline only (no image generation)
  303. /baoyu-slide-deck path/to/article.md --outline-only
  304. # With language
  305. /baoyu-slide-deck path/to/article.md --lang zh
  306. ```
  307. **Options**:
  308. | Option | Description |
  309. |--------|-------------|
  310. | `--style <name>` | Visual style: preset name or `custom` |
  311. | `--audience <type>` | Target: beginners, intermediate, experts, executives, general |
  312. | `--lang <code>` | Output language (en, zh, ja, etc.) |
  313. | `--slides <number>` | Target slide count (8-25 recommended, max 30) |
  314. | `--outline-only` | Generate outline only, skip images |
  315. | `--prompts-only` | Generate outline + prompts, skip images |
  316. | `--images-only` | Generate images from existing prompts |
  317. | `--regenerate <N>` | Regenerate specific slide(s): `3` or `2,5,8` |
  318. **Style System**:
  319. Styles are built from 4 dimensions: **Texture** × **Mood** × **Typography** × **Density**
  320. | Dimension | Options |
  321. |-----------|---------|
  322. | Texture | clean, grid, organic, pixel, paper |
  323. | Mood | professional, warm, cool, vibrant, dark, neutral |
  324. | Typography | geometric, humanist, handwritten, editorial, technical |
  325. | Density | minimal, balanced, dense |
  326. **Presets** (pre-configured dimension combinations):
  327. | Preset | Dimensions | Best For |
  328. |--------|------------|----------|
  329. | `blueprint` (default) | grid + cool + technical + balanced | Architecture, system design |
  330. | `chalkboard` | organic + warm + handwritten + balanced | Education, tutorials |
  331. | `corporate` | clean + professional + geometric + balanced | Investor decks, proposals |
  332. | `minimal` | clean + neutral + geometric + minimal | Executive briefings |
  333. | `sketch-notes` | organic + warm + handwritten + balanced | Educational, tutorials |
  334. | `watercolor` | organic + warm + humanist + minimal | Lifestyle, wellness |
  335. | `dark-atmospheric` | clean + dark + editorial + balanced | Entertainment, gaming |
  336. | `notion` | clean + neutral + geometric + dense | Product demos, SaaS |
  337. | `bold-editorial` | clean + vibrant + editorial + balanced | Product launches, keynotes |
  338. | `editorial-infographic` | clean + cool + editorial + dense | Tech explainers, research |
  339. | `fantasy-animation` | organic + vibrant + handwritten + minimal | Educational storytelling |
  340. | `intuition-machine` | clean + cool + technical + dense | Technical docs, academic |
  341. | `pixel-art` | pixel + vibrant + technical + balanced | Gaming, developer talks |
  342. | `scientific` | clean + cool + technical + dense | Biology, chemistry, medical |
  343. | `vector-illustration` | clean + vibrant + humanist + balanced | Creative, children's content |
  344. | `vintage` | paper + warm + editorial + balanced | Historical, heritage |
  345. **Style Previews**:
  346. | | | |
  347. |:---:|:---:|:---:|
  348. | ![blueprint](./screenshots/slide-deck-styles/blueprint.webp) | ![chalkboard](./screenshots/slide-deck-styles/chalkboard.webp) | ![bold-editorial](./screenshots/slide-deck-styles/bold-editorial.webp) |
  349. | blueprint | chalkboard | bold-editorial |
  350. | ![corporate](./screenshots/slide-deck-styles/corporate.webp) | ![dark-atmospheric](./screenshots/slide-deck-styles/dark-atmospheric.webp) | ![editorial-infographic](./screenshots/slide-deck-styles/editorial-infographic.webp) |
  351. | corporate | dark-atmospheric | editorial-infographic |
  352. | ![fantasy-animation](./screenshots/slide-deck-styles/fantasy-animation.webp) | ![intuition-machine](./screenshots/slide-deck-styles/intuition-machine.webp) | ![minimal](./screenshots/slide-deck-styles/minimal.webp) |
  353. | fantasy-animation | intuition-machine | minimal |
  354. | ![notion](./screenshots/slide-deck-styles/notion.webp) | ![pixel-art](./screenshots/slide-deck-styles/pixel-art.webp) | ![scientific](./screenshots/slide-deck-styles/scientific.webp) |
  355. | notion | pixel-art | scientific |
  356. | ![sketch-notes](./screenshots/slide-deck-styles/sketch-notes.webp) | ![vector-illustration](./screenshots/slide-deck-styles/vector-illustration.webp) | ![vintage](./screenshots/slide-deck-styles/vintage.webp) |
  357. | sketch-notes | vector-illustration | vintage |
  358. | ![watercolor](./screenshots/slide-deck-styles/watercolor.webp) | | |
  359. | watercolor | | |
  360. After generation, slides are automatically merged into `.pptx` and `.pdf` files for easy sharing.
  361. #### baoyu-comic
  362. Knowledge comic creator with flexible art style × tone combinations. Creates original educational comics with detailed panel layouts and sequential image generation.
  363. ```bash
  364. # From source material (auto-selects art + tone)
  365. /baoyu-comic posts/turing-story/source.md
  366. # Specify art style and tone
  367. /baoyu-comic posts/turing-story/source.md --art manga --tone warm
  368. /baoyu-comic posts/turing-story/source.md --art ink-brush --tone dramatic
  369. # Use preset (includes special rules)
  370. /baoyu-comic posts/turing-story/source.md --style ohmsha
  371. /baoyu-comic posts/turing-story/source.md --style wuxia
  372. # Specify layout and aspect ratio
  373. /baoyu-comic posts/turing-story/source.md --layout cinematic
  374. /baoyu-comic posts/turing-story/source.md --aspect 16:9
  375. # Specify language
  376. /baoyu-comic posts/turing-story/source.md --lang zh
  377. # Direct content input
  378. /baoyu-comic "The story of Alan Turing and the birth of computer science"
  379. ```
  380. **Options**:
  381. | Option | Values |
  382. |--------|--------|
  383. | `--art` | `ligne-claire` (default), `manga`, `realistic`, `ink-brush`, `chalk` |
  384. | `--tone` | `neutral` (default), `warm`, `dramatic`, `romantic`, `energetic`, `vintage`, `action` |
  385. | `--style` | `ohmsha`, `wuxia`, `shoujo` (presets with special rules) |
  386. | `--layout` | `standard` (default), `cinematic`, `dense`, `splash`, `mixed`, `webtoon` |
  387. | `--aspect` | `3:4` (default, portrait), `4:3` (landscape), `16:9` (widescreen) |
  388. | `--lang` | `auto` (default), `zh`, `en`, `ja`, etc. |
  389. **Art Styles** (rendering technique):
  390. | Art Style | Description |
  391. |-----------|-------------|
  392. | `ligne-claire` | Uniform lines, flat colors, European comic tradition (Tintin, Logicomix) |
  393. | `manga` | Large eyes, manga conventions, expressive emotions |
  394. | `realistic` | Digital painting, realistic proportions, sophisticated |
  395. | `ink-brush` | Chinese brush strokes, ink wash effects |
  396. | `chalk` | Chalkboard aesthetic, hand-drawn warmth |
  397. **Tones** (mood/atmosphere):
  398. | Tone | Description |
  399. |------|-------------|
  400. | `neutral` | Balanced, rational, educational |
  401. | `warm` | Nostalgic, personal, comforting |
  402. | `dramatic` | High contrast, intense, powerful |
  403. | `romantic` | Soft, beautiful, decorative elements |
  404. | `energetic` | Bright, dynamic, exciting |
  405. | `vintage` | Historical, aged, period authenticity |
  406. | `action` | Speed lines, impact effects, combat |
  407. **Presets** (art + tone + special rules):
  408. | Preset | Equivalent | Special Rules |
  409. |--------|-----------|---------------|
  410. | `ohmsha` | manga + neutral | Visual metaphors, NO talking heads, gadget reveals |
  411. | `wuxia` | ink-brush + action | Qi effects, combat visuals, atmospheric elements |
  412. | `shoujo` | manga + romantic | Decorative elements, eye details, romantic beats |
  413. **Layouts** (panel arrangement):
  414. | Layout | Panels/Page | Best for |
  415. |--------|-------------|----------|
  416. | `standard` | 4-6 | Dialogue, narrative flow |
  417. | `cinematic` | 2-4 | Dramatic moments, establishing shots |
  418. | `dense` | 6-9 | Technical explanations, timelines |
  419. | `splash` | 1-2 large | Key moments, revelations |
  420. | `mixed` | 3-7 varies | Complex narratives, emotional arcs |
  421. | `webtoon` | 3-5 vertical | Ohmsha tutorials, mobile reading |
  422. **Layout Previews**:
  423. | | | |
  424. |:---:|:---:|:---:|
  425. | ![standard](./screenshots/comic-layouts/standard.webp) | ![cinematic](./screenshots/comic-layouts/cinematic.webp) | ![dense](./screenshots/comic-layouts/dense.webp) |
  426. | standard | cinematic | dense |
  427. | ![splash](./screenshots/comic-layouts/splash.webp) | ![mixed](./screenshots/comic-layouts/mixed.webp) | ![webtoon](./screenshots/comic-layouts/webtoon.webp) |
  428. | splash | mixed | webtoon |
  429. #### baoyu-article-illustrator
  430. Smart article illustration skill with Type × Style × Palette three-dimension approach. Analyzes article structure, identifies positions requiring visual aids, and generates illustrations.
  431. ```bash
  432. # Auto-select type and style based on content
  433. /baoyu-article-illustrator path/to/article.md
  434. # Specify type and style
  435. /baoyu-article-illustrator path/to/article.md --type flowchart --style notion
  436. # With palette override
  437. /baoyu-article-illustrator path/to/article.md --style vector-illustration --palette macaron
  438. ```
  439. **Types** (information structure):
  440. | Type | Description | Best For |
  441. |------|-------------|----------|
  442. | `infographic` | Data visualization, charts, metrics | Technical articles, data analysis |
  443. | `scene` | Atmospheric illustration, mood rendering | Narrative, personal stories |
  444. | `flowchart` | Process diagrams, step visualization | Tutorials, workflows |
  445. | `comparison` | Side-by-side, before/after contrast | Product comparisons |
  446. | `framework` | Concept maps, relationship diagrams | Methodologies, architecture |
  447. | `timeline` | Chronological progression | History, project progress |
  448. **Styles** (rendering approach):
  449. | Style | Description | Best For |
  450. |-------|-------------|----------|
  451. | `notion` (default) | Minimalist hand-drawn line art | Knowledge sharing, SaaS, productivity |
  452. | `elegant` | Refined, sophisticated | Business, thought leadership |
  453. | `warm` | Friendly, approachable | Personal growth, lifestyle |
  454. | `minimal` | Ultra-clean, zen-like | Philosophy, minimalism |
  455. | `blueprint` | Technical schematics | Architecture, system design |
  456. | `watercolor` | Soft artistic with natural warmth | Lifestyle, travel, creative |
  457. | `editorial` | Magazine-style infographic | Tech explainers, journalism |
  458. | `scientific` | Academic precise diagrams | Biology, chemistry, technical |
  459. **Palettes** (optional color override):
  460. | Palette | Description | Best For |
  461. |---------|-------------|----------|
  462. | `macaron` | Soft pastel blocks (blue, mint, lavender, peach) on warm cream | Educational, knowledge, tutorials |
  463. | `warm` | Warm earth tones on soft peach, no cool colors | Brand, product, lifestyle |
  464. | `neon` | Vibrant neon on dark purple | Gaming, retro, pop culture |
  465. **Style Previews**:
  466. | | | |
  467. |:---:|:---:|:---:|
  468. | ![notion](./screenshots/article-illustrator-styles/notion.webp) | ![elegant](./screenshots/article-illustrator-styles/elegant.webp) | ![warm](./screenshots/article-illustrator-styles/warm.webp) |
  469. | notion | elegant | warm |
  470. | ![minimal](./screenshots/article-illustrator-styles/minimal.webp) | ![blueprint](./screenshots/article-illustrator-styles/blueprint.webp) | ![watercolor](./screenshots/article-illustrator-styles/watercolor.webp) |
  471. | minimal | blueprint | watercolor |
  472. | ![editorial](./screenshots/article-illustrator-styles/editorial.webp) | ![scientific](./screenshots/article-illustrator-styles/scientific.webp) | |
  473. | editorial | scientific | |
  474. #### baoyu-post-to-x
  475. Post content and articles to X (Twitter). Supports regular posts with images and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation.
  476. Plain text input is treated as a regular post. Markdown files are treated as X Articles. Scripts fill content into the browser, and the user reviews and publishes manually.
  477. ```bash
  478. # Post with text
  479. /baoyu-post-to-x "Hello from AI Agent!"
  480. # Post with images
  481. /baoyu-post-to-x "Check this out" --image photo.png
  482. # Post X Article
  483. /baoyu-post-to-x --article path/to/article.md
  484. ```
  485. #### baoyu-post-to-wechat
  486. Post content to WeChat Official Account (微信公众号). Two modes available:
  487. **Image-Text (贴图)** - Multiple images with short title/content:
  488. ```bash
  489. /baoyu-post-to-wechat 贴图 --markdown article.md --images ./photos/
  490. /baoyu-post-to-wechat 贴图 --markdown article.md --image img1.png --image img2.png --image img3.png
  491. /baoyu-post-to-wechat 贴图 --title "标题" --content "内容" --image img1.png --submit
  492. ```
  493. **Article (文章)** - Full markdown/HTML with rich formatting:
  494. ```bash
  495. /baoyu-post-to-wechat 文章 --markdown article.md
  496. /baoyu-post-to-wechat 文章 --markdown article.md --theme grace
  497. /baoyu-post-to-wechat 文章 --html article.html
  498. ```
  499. **Publishing Methods**:
  500. | Method | Speed | Requirements |
  501. |--------|-------|--------------|
  502. | API (Recommended) | Fast | API credentials (local IP allowlisted in WeChat) |
  503. | Browser | Slow | Chrome, login session |
  504. | Remote API | Fast | API credentials + SSH-reachable server whose IP is on WeChat's allowlist |
  505. **API Configuration** (for faster publishing):
  506. ```bash
  507. # Add to .baoyu-skills/.env (project-level) or ~/.baoyu-skills/.env (user-level)
  508. WECHAT_APP_ID=your_app_id
  509. WECHAT_APP_SECRET=your_app_secret
  510. ```
  511. To obtain credentials:
  512. 1. Visit https://developers.weixin.qq.com/platform/
  513. 2. Go to: 我的业务 → 公众号 → 开发密钥
  514. 3. Create development key and copy AppID/AppSecret
  515. 4. Add your machine's IP to the whitelist
  516. **Browser Method** (no API setup needed): Requires Google Chrome. First run opens browser for QR code login (session preserved).
  517. **Remote API Method** (for when WeChat's IP allowlist excludes your local machine): tunnels WeChat API calls through an SSH SOCKS5 dynamic port forward to a server whose IP is on the allowlist. No files are written to the remote host and `AppSecret` never leaves the local process. Add to your EXTEND.md:
  518. ```yaml
  519. # Optional: only set when WeChat's IP allowlist excludes your local machine
  520. remote_publish_host: server.example.com
  521. remote_publish_user: deploy
  522. remote_publish_identity_file: ~/.ssh/id_ed25519
  523. ```
  524. Then publish with `--remote` (or set `default_publish_method: remote-api`). Authentication is SSH key only; only the typed `remote_publish_*` keys are honored.
  525. **Multi-Account Support**: Manage multiple WeChat Official Accounts via `EXTEND.md`:
  526. ```bash
  527. mkdir -p .baoyu-skills/baoyu-post-to-wechat
  528. ```
  529. Create `.baoyu-skills/baoyu-post-to-wechat/EXTEND.md`:
  530. ```yaml
  531. # Global settings (shared across all accounts)
  532. default_theme: default
  533. default_color: blue
  534. # Account list
  535. accounts:
  536. - name: My Tech Blog
  537. alias: tech-blog
  538. default: false
  539. default_publish_method: api
  540. default_author: Author Name
  541. need_open_comment: 1
  542. only_fans_can_comment: 0
  543. app_id: your_wechat_app_id
  544. app_secret: your_wechat_app_secret
  545. - name: AI Newsletter
  546. alias: ai-news
  547. default_publish_method: browser
  548. default_author: AI Newsletter
  549. need_open_comment: 1
  550. only_fans_can_comment: 0
  551. ```
  552. | Accounts configured | Behavior |
  553. |---------------------|----------|
  554. | No `accounts` block | Single-account mode (backward compatible) |
  555. | 1 account | Auto-select, no prompt |
  556. | 2+ accounts | Prompt to select, or use `--account <alias>` |
  557. | 1 account has `default: true` | Pre-selected as default |
  558. Each account gets an isolated Chrome profile for independent login sessions (browser method). API credentials can be set inline in EXTEND.md or via `.env` with alias-prefixed keys (e.g., `WECHAT_TECH_BLOG_APP_ID`).
  559. #### baoyu-post-to-weibo
  560. Post content to Weibo (微博). Supports regular posts with text, images, and videos, and headline articles (头条文章) with Markdown input. Uses real Chrome with CDP to bypass anti-automation.
  561. **Regular Posts** - Text + images/videos (max 18 files):
  562. ```bash
  563. # Post with text
  564. /baoyu-post-to-weibo "Hello Weibo!"
  565. # Post with images
  566. /baoyu-post-to-weibo "Check this out" --image photo.png
  567. # Post with video
  568. /baoyu-post-to-weibo "Watch this" --video clip.mp4
  569. ```
  570. **Headline Articles (头条文章)** - Long-form Markdown:
  571. ```bash
  572. # Publish article
  573. /baoyu-post-to-weibo --article article.md
  574. # With cover image
  575. /baoyu-post-to-weibo --article article.md --cover cover.jpg
  576. ```
  577. **Article Options**:
  578. | Option | Description |
  579. |--------|-------------|
  580. | `--cover <path>` | Cover image |
  581. | `--title <text>` | Override title (max 32 chars) |
  582. | `--summary <text>` | Override summary (max 44 chars) |
  583. **Note**: Scripts fill content into the browser. User reviews and publishes manually. First run requires manual Weibo login (session persists).
  584. ### AI Generation Skills
  585. AI-powered generation backends.
  586. #### baoyu-image-gen
  587. AI SDK-based image generation using OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope (Aliyun Tongyi Wanxiang), MiniMax, Jimeng (即梦), Seedream (豆包), and Replicate APIs. Supports text-to-image, reference images, aspect ratios, custom sizes, batch generation, and quality presets.
  588. ```bash
  589. # Basic generation (auto-detect provider)
  590. /baoyu-image-gen --prompt "A cute cat" --image cat.png
  591. # With aspect ratio
  592. /baoyu-image-gen --prompt "A landscape" --image landscape.png --ar 16:9
  593. # High quality (2k)
  594. /baoyu-image-gen --prompt "A banner" --image banner.png --quality 2k
  595. # Specific provider
  596. /baoyu-image-gen --prompt "A cat" --image cat.png --provider openai --model gpt-image-2
  597. # Azure OpenAI (model = deployment name)
  598. /baoyu-image-gen --prompt "A cat" --image cat.png --provider azure --model gpt-image-2
  599. # OpenRouter
  600. /baoyu-image-gen --prompt "A cat" --image cat.png --provider openrouter
  601. # OpenRouter with reference images
  602. /baoyu-image-gen --prompt "Make it blue" --image out.png --provider openrouter --model google/gemini-3.1-flash-image --ref source.png
  603. # DashScope (Aliyun Tongyi Wanxiang)
  604. /baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
  605. # DashScope with custom size
  606. /baoyu-image-gen --prompt "为咖啡品牌设计一张 21:9 横幅海报,包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
  607. # Z.AI GLM-Image
  608. /baoyu-image-gen --prompt "一张带清晰中文标题的科技海报" --image out.png --provider zai
  609. # MiniMax
  610. /baoyu-image-gen --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
  611. # MiniMax with subject reference
  612. /baoyu-image-gen --prompt "A girl stands by the library window, cinematic lighting" --image out.jpg --provider minimax --model image-01 --ref portrait.png --ar 16:9
  613. # Replicate (default: google/nano-banana-2)
  614. /baoyu-image-gen --prompt "A cat" --image cat.png --provider replicate
  615. # Replicate Seedream 4.5
  616. /baoyu-image-gen --prompt "A studio portrait" --image portrait.png --provider replicate --model bytedance/seedream-4.5 --ar 3:2
  617. # Replicate Wan 2.7 Image Pro
  618. /baoyu-image-gen --prompt "A concept frame" --image frame.png --provider replicate --model wan-video/wan-2.7-image-pro --size 2048x1152
  619. # Jimeng (即梦)
  620. /baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider jimeng
  621. # Seedream (豆包)
  622. /baoyu-image-gen --prompt "一只可爱的猫" --image cat.png --provider seedream
  623. # With reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate, MiniMax, or Seedream 5.0/4.5/4.0)
  624. /baoyu-image-gen --prompt "Make it blue" --image out.png --ref source.png
  625. # Batch mode
  626. /baoyu-image-gen --batchfile batch.json --jobs 4 --json
  627. ```
  628. **Options**:
  629. | Option | Description |
  630. |--------|-------------|
  631. | `--prompt`, `-p` | Prompt text |
  632. | `--promptfiles` | Read prompt from files (concatenated) |
  633. | `--image` | Output image path (required) |
  634. | `--batchfile` | JSON batch file for multi-image generation |
  635. | `--jobs` | Worker count for batch mode |
  636. | `--provider` | `google`, `openai`, `azure`, `openrouter`, `dashscope`, `zai`, `minimax`, `jimeng`, `seedream`, `replicate`, or `agnes` |
  637. | `--model`, `-m` | Model ID or deployment name. Azure uses deployment name; OpenRouter uses full model IDs; Z.AI uses `glm-image`; MiniMax uses `image-01` / `image-01-live` |
  638. | `--ar` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
  639. | `--size` | Size (e.g., `1024x1024`; `gpt-image-2` accepts valid custom sizes up to 3840px max edge) |
  640. | `--quality` | `normal` or `2k` (default: `2k`) |
  641. | `--imageSize` | `1K`, `2K`, or `4K` for Google/OpenRouter |
  642. | `--imageApiDialect` | `openai-native` or `ratio-metadata` for OpenAI-compatible gateways |
  643. | `--ref` | Reference images (Google, OpenAI, Azure OpenAI, OpenRouter, Replicate supported families, MiniMax, or Seedream 5.0/4.5/4.0) |
  644. | `--n` | Number of images per request (`replicate` currently requires `--n 1`) |
  645. | `--json` | JSON output |
  646. **Environment Variables** (see [Environment Configuration](#environment-configuration) for setup):
  647. | Variable | Description | Default |
  648. |----------|-------------|---------|
  649. | `OPENAI_API_KEY` | OpenAI API key | - |
  650. | `AZURE_OPENAI_API_KEY` | Azure OpenAI API key | - |
  651. | `OPENROUTER_API_KEY` | OpenRouter API key | - |
  652. | `GOOGLE_API_KEY` | Google API key | - |
  653. | `GEMINI_API_KEY` | Alias for `GOOGLE_API_KEY` | - |
  654. | `DASHSCOPE_API_KEY` | DashScope API key (Aliyun) | - |
  655. | `ZAI_API_KEY` | Z.AI API key | - |
  656. | `BIGMODEL_API_KEY` | Backward-compatible alias for Z.AI API key | - |
  657. | `MINIMAX_API_KEY` | MiniMax API key | - |
  658. | `REPLICATE_API_TOKEN` | Replicate API token | - |
  659. | `JIMENG_ACCESS_KEY_ID` | Jimeng Volcengine access key | - |
  660. | `JIMENG_SECRET_ACCESS_KEY` | Jimeng Volcengine secret key | - |
  661. | `ARK_API_KEY` | Seedream Volcengine ARK API key | - |
  662. | `OPENAI_IMAGE_MODEL` | OpenAI model | `gpt-image-2` |
  663. | `AZURE_OPENAI_DEPLOYMENT` | Azure default deployment name | - |
  664. | `AZURE_OPENAI_IMAGE_MODEL` | Backward-compatible Azure deployment/model alias | `gpt-image-2` |
  665. | `OPENROUTER_IMAGE_MODEL` | OpenRouter model | `google/gemini-3.1-flash-image` |
  666. | `GOOGLE_IMAGE_MODEL` | Google model | `gemini-3-pro-image` |
  667. | `DASHSCOPE_IMAGE_MODEL` | DashScope model | `qwen-image-2.0-pro` |
  668. | `ZAI_IMAGE_MODEL` | Z.AI model | `glm-image` |
  669. | `BIGMODEL_IMAGE_MODEL` | Backward-compatible alias for Z.AI model | `glm-image` |
  670. | `MINIMAX_IMAGE_MODEL` | MiniMax model | `image-01` |
  671. | `REPLICATE_IMAGE_MODEL` | Replicate model | `google/nano-banana-2` |
  672. | `JIMENG_IMAGE_MODEL` | Jimeng model | `jimeng_t2i_v40` |
  673. | `SEEDREAM_IMAGE_MODEL` | Seedream model | `doubao-seedream-5-0-260128` |
  674. | `OPENAI_BASE_URL` | Custom OpenAI endpoint | - |
  675. | `OPENAI_IMAGE_API_DIALECT` | OpenAI-compatible image API dialect (`openai-native` or `ratio-metadata`) | `openai-native` |
  676. | `OPENAI_IMAGE_USE_CHAT` | Use `/chat/completions` for OpenAI image generation | `false` |
  677. | `AZURE_OPENAI_BASE_URL` | Azure resource or deployment endpoint | - |
  678. | `AZURE_API_VERSION` | Azure image API version | `2025-04-01-preview` |
  679. | `OPENROUTER_BASE_URL` | Custom OpenRouter endpoint | `https://openrouter.ai/api/v1` |
  680. | `OPENROUTER_HTTP_REFERER` | Optional app/site URL for OpenRouter attribution | - |
  681. | `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution | - |
  682. | `GOOGLE_BASE_URL` | Custom Google endpoint | - |
  683. | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint | - |
  684. | `ZAI_BASE_URL` | Custom Z.AI endpoint | `https://api.z.ai/api/paas/v4` |
  685. | `BIGMODEL_BASE_URL` | Backward-compatible alias for Z.AI endpoint | - |
  686. | `MINIMAX_BASE_URL` | Custom MiniMax endpoint | `https://api.minimaxi.com` |
  687. | `REPLICATE_BASE_URL` | Custom Replicate endpoint | - |
  688. | `JIMENG_BASE_URL` | Custom Jimeng endpoint | `https://visual.volcengineapi.com` |
  689. | `JIMENG_REGION` | Jimeng region | `cn-north-1` |
  690. | `SEEDREAM_BASE_URL` | Custom Seedream endpoint | `https://ark.cn-beijing.volces.com/api/v3` |
  691. | `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap | `10` |
  692. | `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency | provider-specific |
  693. | `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider request start gap | provider-specific |
  694. **Provider Notes**:
  695. - Azure OpenAI: `--model` means Azure deployment name, not the underlying model family.
  696. - DashScope: `qwen-image-2.0-pro` is the recommended default for custom `--size`, `21:9`, and strong Chinese/English text rendering.
  697. - Z.AI: `glm-image` is recommended for posters, diagrams, and text-heavy Chinese/English images. Reference images are not supported.
  698. - MiniMax: `image-01` supports documented custom `width` / `height`; `image-01-live` is lower latency and works best with `--ar`.
  699. - MiniMax reference images are sent as `subject_reference`; the current API is specialized toward character / portrait consistency.
  700. - Jimeng does not support reference images.
  701. - Seedream reference images are supported by Seedream 5.0 / 4.5 / 4.0, not Seedream 3.0.
  702. - Replicate defaults to `google/nano-banana-2`. `baoyu-image-gen` only enables Replicate advanced options for `google/nano-banana*`, `bytedance/seedream-4.5`, `bytedance/seedream-5-lite`, `wan-video/wan-2.7-image`, and `wan-video/wan-2.7-image-pro`.
  703. - Replicate currently saves exactly one output image per request. `--n > 1` is blocked locally instead of silently dropping extra results.
  704. - Replicate model behavior is family-specific: nano-banana uses `--quality` / `--ar`, Seedream uses validated `--size` / `--ar`, and Wan uses validated `--size` (with `--ar` converted locally to a concrete size).
  705. **Provider Auto-Selection**:
  706. 1. If `--provider` is specified → use it
  707. 2. If `--ref` is provided and no provider is specified → try Google, then OpenAI, Azure, OpenRouter, Replicate, Seedream, MiniMax, and finally Agnes
  708. 3. If only one API key is available → use that provider
  709. 4. If multiple providers are available → default to Google, then OpenAI, Azure, OpenRouter, DashScope, Z.AI, MiniMax, Replicate, Jimeng, Seedream, Agnes
  710. #### baoyu-danger-gemini-web
  711. Interacts with Gemini Web to generate text and images.
  712. **Text Generation:**
  713. ```bash
  714. /baoyu-danger-gemini-web "Hello, Gemini"
  715. /baoyu-danger-gemini-web --prompt "Explain quantum computing"
  716. ```
  717. **Image Generation:**
  718. ```bash
  719. /baoyu-danger-gemini-web --prompt "A cute cat" --image cat.png
  720. /baoyu-danger-gemini-web --promptfiles system.md content.md --image out.png
  721. ```
  722. ### Utility Skills
  723. Utility tools for content processing.
  724. #### baoyu-youtube-transcript
  725. Download YouTube video transcripts/subtitles and cover images. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting.
  726. ```bash
  727. # Default: markdown with timestamps
  728. /baoyu-youtube-transcript https://www.youtube.com/watch?v=VIDEO_ID
  729. # Specify languages (priority order)
  730. /baoyu-youtube-transcript https://youtu.be/VIDEO_ID --languages zh,en,ja
  731. # With chapters and speaker identification
  732. /baoyu-youtube-transcript https://youtu.be/VIDEO_ID --chapters --speakers
  733. # SRT subtitle format
  734. /baoyu-youtube-transcript https://youtu.be/VIDEO_ID --format srt
  735. # List available transcripts
  736. /baoyu-youtube-transcript https://youtu.be/VIDEO_ID --list
  737. ```
  738. **Options**:
  739. | Option | Description | Default |
  740. |--------|-------------|---------|
  741. | `<url-or-id>` | YouTube URL or video ID | Required |
  742. | `--languages <codes>` | Language codes, comma-separated | `en` |
  743. | `--format <fmt>` | Output format: `text`, `srt` | `text` |
  744. | `--translate <code>` | Translate to specified language | |
  745. | `--chapters` | Chapter segmentation from video description | |
  746. | `--speakers` | Speaker identification (requires AI post-processing) | |
  747. | `--no-timestamps` | Disable timestamps | |
  748. | `--list` | List available transcripts | |
  749. | `--refresh` | Force re-fetch, ignore cache | |
  750. #### baoyu-url-to-markdown
  751. Fetch any URL via Chrome CDP and convert to clean markdown. Saves rendered HTML snapshot alongside the markdown, and automatically falls back to a legacy extractor when Defuddle fails.
  752. ```bash
  753. # Auto mode (default) - capture when page loads
  754. /baoyu-url-to-markdown https://example.com/article
  755. # Wait mode - for login-required pages
  756. /baoyu-url-to-markdown https://example.com/private --wait
  757. # Save to specific file
  758. /baoyu-url-to-markdown https://example.com/article -o output.md
  759. ```
  760. **Capture Modes**:
  761. | Mode | Description | Best For |
  762. |------|-------------|----------|
  763. | Auto (default) | Captures immediately after page load | Public pages, static content |
  764. | Wait (`--wait`) | Waits for user signal before capture | Login-required, dynamic content |
  765. **Options**:
  766. | Option | Description |
  767. |--------|-------------|
  768. | `<url>` | URL to fetch |
  769. | `-o <path>` | Output file path |
  770. | `--wait` | Wait for user signal before capturing |
  771. | `--timeout <ms>` | Page load timeout (default: 30000) |
  772. #### baoyu-danger-x-to-markdown
  773. Converts X (Twitter) content to markdown format. Supports tweet threads and X Articles.
  774. ```bash
  775. # Convert tweet to markdown
  776. /baoyu-danger-x-to-markdown https://x.com/username/status/123456
  777. # Save to specific file
  778. /baoyu-danger-x-to-markdown https://x.com/username/status/123456 -o output.md
  779. # JSON output
  780. /baoyu-danger-x-to-markdown https://x.com/username/status/123456 --json
  781. # Download media (images/videos) to local files
  782. /baoyu-danger-x-to-markdown https://x.com/username/status/123456 --download-media
  783. ```
  784. **Supported URLs:**
  785. - `https://x.com/<user>/status/<id>`
  786. - `https://twitter.com/<user>/status/<id>`
  787. - `https://x.com/i/article/<id>`
  788. **Authentication:** Uses environment variables (`X_AUTH_TOKEN`, `X_CT0`) or Chrome login for cookie-based auth.
  789. #### baoyu-compress-image
  790. Compress images to reduce file size while maintaining quality.
  791. ```bash
  792. /baoyu-compress-image path/to/image.png
  793. /baoyu-compress-image path/to/images/ --quality 80
  794. ```
  795. #### baoyu-format-markdown
  796. Format plain text or markdown files with proper frontmatter, titles, summaries, headings, bold, lists, and code blocks.
  797. ```bash
  798. # Format a markdown file
  799. /baoyu-format-markdown path/to/article.md
  800. # Format with specific output
  801. /baoyu-format-markdown path/to/draft.md
  802. ```
  803. **Workflow**:
  804. 1. Read source file and analyze content structure
  805. 2. Check/create YAML frontmatter (title, slug, summary, coverImage)
  806. 3. Handle title: use existing, extract from H1, or generate candidates
  807. 4. Apply formatting: headings, bold, lists, code blocks, quotes
  808. 5. Save to `{filename}-formatted.md`
  809. 6. Run typography script: ASCII→fullwidth quotes, CJK spacing, autocorrect
  810. **Frontmatter Fields**:
  811. | Field | Processing |
  812. |-------|------------|
  813. | `title` | Use existing, extract H1, or generate candidates |
  814. | `slug` | Infer from file path or generate from title |
  815. | `summary` | Generate engaging summary (100-150 chars) |
  816. | `coverImage` | Check for `imgs/cover.png` in same directory |
  817. **Formatting Rules**:
  818. | Element | Format |
  819. |---------|--------|
  820. | Titles | `#`, `##`, `###` hierarchy |
  821. | Key points | `**bold**` |
  822. | Parallel items | `-` unordered or `1.` ordered lists |
  823. | Code/commands | `` `inline` `` or ` ```block``` ` |
  824. | Quotes | `>` blockquote |
  825. #### baoyu-markdown-to-html
  826. Convert markdown files into styled HTML with WeChat-compatible themes, syntax highlighting, and optional bottom citations for external links.
  827. ```bash
  828. # Basic conversion
  829. /baoyu-markdown-to-html article.md
  830. # Theme + color
  831. /baoyu-markdown-to-html article.md --theme grace --color red
  832. # Convert ordinary external links to bottom citations
  833. /baoyu-markdown-to-html article.md --cite
  834. ```
  835. #### baoyu-translate
  836. Translate articles and documents between languages with three modes: quick (direct), normal (analysis-informed), and refined (full publication-quality workflow with review and polish).
  837. ```bash
  838. # Normal mode (default) - analyze then translate
  839. /translate article.md --to zh-CN
  840. # Quick mode - direct translation
  841. /translate article.md --mode quick --to ja
  842. # Refined mode - full workflow with review and polish
  843. /translate article.md --mode refined --to zh-CN
  844. # Translate a URL
  845. /translate https://example.com/article --to zh-CN
  846. # Specify audience
  847. /translate article.md --to zh-CN --audience technical
  848. # Specify style
  849. /translate article.md --to zh-CN --style humorous
  850. # With additional glossary
  851. /translate article.md --to zh-CN --glossary my-terms.md
  852. ```
  853. **Options**:
  854. | Option | Description |
  855. |--------|-------------|
  856. | `<source>` | File path, URL, or inline text |
  857. | `--mode <mode>` | `quick`, `normal` (default), `refined` |
  858. | `--from <lang>` | Source language (auto-detect if omitted) |
  859. | `--to <lang>` | Target language (default: `zh-CN`) |
  860. | `--audience <type>` | Target reader profile (default: `general`) |
  861. | `--style <style>` | Translation style (default: `storytelling`) |
  862. | `--glossary <file>` | Additional glossary file |
  863. **Modes**:
  864. | Mode | Steps | Use Case |
  865. |------|-------|----------|
  866. | Quick | Translate | Short texts, informal content |
  867. | Normal | Analyze → Translate | Articles, blog posts |
  868. | Refined | Analyze → Translate → Review → Polish | Publication-quality documents |
  869. After normal mode completes, you can reply "继续润色" or "refine" to continue with review and polish steps.
  870. **Audience Presets**:
  871. | Value | Description |
  872. |-------|-------------|
  873. | `general` | General readers (default) — plain language, more translator's notes |
  874. | `technical` | Developers / engineers — less annotation on common tech terms |
  875. | `academic` | Researchers / scholars — formal register, precise terminology |
  876. | `business` | Business professionals — business-friendly tone |
  877. Custom audience descriptions are also accepted, e.g., `--audience "AI-interested general readers"`.
  878. **Style Presets**:
  879. | Value | Description |
  880. |-------|-------------|
  881. | `storytelling` | Engaging narrative flow (default) — smooth transitions, vivid phrasing |
  882. | `formal` | Professional, structured — neutral tone, no colloquialisms |
  883. | `technical` | Precise, documentation-style — concise, terminology-heavy |
  884. | `literal` | Close to original structure — minimal restructuring |
  885. | `academic` | Scholarly, rigorous — formal register, complex clauses OK |
  886. | `business` | Concise, results-focused — action-oriented, executive-friendly |
  887. | `humorous` | Preserves and adapts humor — witty, recreates comedic effect |
  888. | `conversational` | Casual, spoken-like — friendly, as if explaining to a friend |
  889. | `elegant` | Literary, polished prose — aesthetically refined, carefully crafted |
  890. Custom style descriptions are also accepted, e.g., `--style "poetic and lyrical"`.
  891. **Features**:
  892. - Custom glossaries via EXTEND.md with built-in EN→ZH glossary
  893. - Audience-aware translation with adjustable annotation depth
  894. - Automatic chunking for long documents (4000+ words) with parallel subagent translation
  895. - Figurative language interpreted by meaning, not word-for-word
  896. - Translator's notes for cultural/domain-specific references
  897. - Output directory with all intermediate files preserved
  898. #### baoyu-wechat-summary
  899. Summarize WeChat group chat highlights into a structured digest. Extracts topics, quotes, and stats from group messages using [wx-cli](https://github.com/jackwener/wx-cli). Maintains per-group history, per-user profiles, and per-group fact memory across runs. Supports normal and roast (毒舌) versions, and answers `@bot` questions raised in the chat.
  900. ```bash
  901. # Summarize a group's recent messages
  902. /baoyu-wechat-summary 相亲相爱一家人 最近 1 天
  903. # Weekly summary
  904. /baoyu-wechat-summary AI 技术群 最近 7 天
  905. # Incremental (since last digest)
  906. /baoyu-wechat-summary 相亲相爱一家人
  907. # Roast version
  908. /baoyu-wechat-summary 相亲相爱一家人 最近 3 天 毒舌版
  909. ```
  910. **Requirements**:
  911. - [wx-cli](https://github.com/jackwener/wx-cli) installed (`npm install -g @jackwener/wx-cli`)
  912. - WeChat 4.x running and logged in on macOS
  913. **Features**:
  914. - Topic extraction with attribution and quotes
  915. - Message leaderboard and per-user profiles
  916. - Per-group fact memory: corrections confirmed in chat persist across digests (with injection guardrails)
  917. - Incremental mode (picks up where last digest left off)
  918. - Multi-day range splitting for large batches
  919. - Normal and roast (毒舌) digest versions
  920. - Profile backfill from historical digests
  921. #### baoyu-electron-extract
  922. Extract resources and JavaScript from any installed Electron app's `app.asar`. When `.js.map` files embed `sourcesContent`, restores the original source tree (TypeScript/JSX included); otherwise formats the minified JS/CSS with Prettier in place. Always skips `node_modules`. Works on macOS and Windows; pass `--asar <path>` on other platforms.
  923. ```bash
  924. # Extract by app name (default output: ~/Downloads/Codex-electron-extract/)
  925. /baoyu-electron-extract Codex
  926. # Extract by absolute path (.app bundle, install dir, or .asar file)
  927. /baoyu-electron-extract "/Applications/Visual Studio Code.app"
  928. /baoyu-electron-extract --asar /Applications/Codex.app/Contents/Resources/app.asar Codex
  929. # Custom output directory
  930. /baoyu-electron-extract Codex --output ~/work/codex-source
  931. # Preview discovery without writing anything
  932. /baoyu-electron-extract Codex --dry-run
  933. # Overwrite an existing output directory
  934. /baoyu-electron-extract Codex --force
  935. ```
  936. **Options**:
  937. | Option | Description | Default |
  938. |--------|-------------|---------|
  939. | `<app>` | App name or absolute path (required unless `--asar`) | — |
  940. | `--output`, `-o` | Output directory | `~/Downloads/<AppName>-electron-extract` |
  941. | `--asar` | Override the resolved `.asar` path | auto-discovered |
  942. | `--force`, `-f` | Allow writing into a non-empty existing output dir | false |
  943. | `--skip-format` | Skip Prettier formatting | false |
  944. | `--skip-restore` | Skip source-map restoration | false |
  945. | `--no-unpacked` | Don't copy `app.asar.unpacked/` alongside | false |
  946. | `--dry-run` | Print resolved paths and exit without writing | false |
  947. | `--json` | Emit one JSON-line summary on stdout | false |
  948. **Output layout**: `extract-report.json` (counts, warnings, paths), `extracted/` (raw asar, formatted in place when no map), `extracted.unpacked/` (native modules if present), and `restored/` (rebuilt source tree from `.js.map` files).
  949. ## Environment Configuration
  950. Some skills require API keys or custom configuration. Environment variables can be set in `.env` files:
  951. **Load Priority** (higher priority overrides lower):
  952. 1. CLI environment variables (e.g., `OPENAI_API_KEY=xxx /baoyu-image-gen ...`)
  953. 2. `process.env` (system environment)
  954. 3. `<cwd>/.baoyu-skills/.env` (project-level)
  955. 4. `~/.baoyu-skills/.env` (user-level)
  956. **Setup**:
  957. ```bash
  958. # Create user-level config directory
  959. mkdir -p ~/.baoyu-skills
  960. # Create .env file
  961. cat > ~/.baoyu-skills/.env << 'EOF'
  962. # OpenAI
  963. OPENAI_API_KEY=sk-xxx
  964. OPENAI_IMAGE_MODEL=gpt-image-2
  965. # OPENAI_BASE_URL=https://api.openai.com/v1
  966. # OPENAI_IMAGE_USE_CHAT=false
  967. # Azure OpenAI
  968. AZURE_OPENAI_API_KEY=xxx
  969. AZURE_OPENAI_BASE_URL=https://your-resource.openai.azure.com
  970. AZURE_OPENAI_DEPLOYMENT=gpt-image-2
  971. # AZURE_API_VERSION=2025-04-01-preview
  972. # OpenRouter
  973. OPENROUTER_API_KEY=sk-or-xxx
  974. OPENROUTER_IMAGE_MODEL=google/gemini-3.1-flash-image
  975. # OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
  976. # OPENROUTER_HTTP_REFERER=https://your-app.example.com
  977. # OPENROUTER_TITLE=Your App Name
  978. # Google
  979. GOOGLE_API_KEY=xxx
  980. GOOGLE_IMAGE_MODEL=gemini-3-pro-image
  981. # GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta
  982. # DashScope (Aliyun Tongyi Wanxiang)
  983. DASHSCOPE_API_KEY=sk-xxx
  984. DASHSCOPE_IMAGE_MODEL=qwen-image-2.0-pro
  985. # DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
  986. # Z.AI
  987. ZAI_API_KEY=xxx
  988. ZAI_IMAGE_MODEL=glm-image
  989. # ZAI_BASE_URL=https://api.z.ai/api/paas/v4
  990. # MiniMax
  991. MINIMAX_API_KEY=xxx
  992. MINIMAX_IMAGE_MODEL=image-01
  993. # MINIMAX_BASE_URL=https://api.minimaxi.com
  994. # Replicate
  995. REPLICATE_API_TOKEN=r8_xxx
  996. REPLICATE_IMAGE_MODEL=google/nano-banana-2
  997. # REPLICATE_BASE_URL=https://api.replicate.com
  998. # Jimeng (即梦)
  999. JIMENG_ACCESS_KEY_ID=xxx
  1000. JIMENG_SECRET_ACCESS_KEY=xxx
  1001. JIMENG_IMAGE_MODEL=jimeng_t2i_v40
  1002. # JIMENG_BASE_URL=https://visual.volcengineapi.com
  1003. # JIMENG_REGION=cn-north-1
  1004. # Seedream (豆包)
  1005. ARK_API_KEY=xxx
  1006. SEEDREAM_IMAGE_MODEL=doubao-seedream-5-0-260128
  1007. # SEEDREAM_BASE_URL=https://ark.cn-beijing.volces.com/api/v3
  1008. EOF
  1009. ```
  1010. **Project-level config** (for team sharing):
  1011. ```bash
  1012. mkdir -p .baoyu-skills
  1013. # Add .baoyu-skills/.env to .gitignore to avoid committing secrets
  1014. echo ".baoyu-skills/.env" >> .gitignore
  1015. ```
  1016. ## Customization
  1017. All skills support customization via `EXTEND.md` files. Create an extension file to override default styles, add custom configurations, or define your own presets.
  1018. **Extension paths** (checked in priority order):
  1019. 1. `.baoyu-skills/<skill-name>/EXTEND.md` - Project-level (for team/project-specific settings)
  1020. 2. `~/.baoyu-skills/<skill-name>/EXTEND.md` - User-level (for personal preferences)
  1021. **Example**: To customize `baoyu-cover-image` with your brand colors:
  1022. ```bash
  1023. mkdir -p .baoyu-skills/baoyu-cover-image
  1024. ```
  1025. Then create `.baoyu-skills/baoyu-cover-image/EXTEND.md`:
  1026. ```markdown
  1027. ## Custom Palettes
  1028. ### corporate-tech
  1029. - Primary colors: #1a73e8, #4A90D9
  1030. - Background: #F5F7FA
  1031. - Accent colors: #00B4D8, #48CAE4
  1032. - Decorative hints: Clean lines, subtle gradients
  1033. - Best for: SaaS, enterprise, technical
  1034. ```
  1035. The extension content will be loaded before skill execution and override defaults.
  1036. ## Disclaimer
  1037. ### baoyu-danger-gemini-web
  1038. This skill uses the Gemini Web API (reverse-engineered).
  1039. **Warning:** This project uses unofficial API access via browser cookies. Use at your own risk.
  1040. - First run opens a browser to authenticate with Google
  1041. - Cookies are cached for subsequent runs
  1042. - No guarantees on API stability or availability
  1043. **Supported browsers** (auto-detected): Google Chrome, Chrome Canary/Beta, Chromium, Microsoft Edge
  1044. **Proxy configuration**: If you need a proxy to access Google services (e.g., in China), set environment variables inline:
  1045. ```bash
  1046. HTTP_PROXY=http://127.0.0.1:7890 HTTPS_PROXY=http://127.0.0.1:7890 /baoyu-danger-gemini-web "Hello"
  1047. ```
  1048. On Windows PowerShell, inline assignment doesn't work. Set the variables in the session first, then start your agent from that same session:
  1049. ```powershell
  1050. $env:HTTP_PROXY = 'http://127.0.0.1:7890'
  1051. $env:HTTPS_PROXY = 'http://127.0.0.1:7890'
  1052. # Start your agent from this PowerShell session, then run the skill inside it
  1053. ```
  1054. These variables apply to the current PowerShell session and processes started from it. An agent that is already running must be restarted to pick them up.
  1055. ### baoyu-danger-x-to-markdown
  1056. This skill uses a reverse-engineered X (Twitter) API.
  1057. **Warning:** This is NOT an official API. Use at your own risk.
  1058. - May break without notice if X changes their API
  1059. - Account restrictions possible if API usage detected
  1060. - First use requires consent acknowledgment
  1061. - Authentication via environment variables or Chrome login
  1062. ## Credits
  1063. This project was inspired by and builds upon the following open source projects:
  1064. - [x-article-publisher-skill](https://github.com/wshuyi/x-article-publisher-skill) by [@wshuyi](https://github.com/wshuyi) — Inspiration for the X article publishing skill
  1065. - [doocs/md](https://github.com/doocs/md) by [@doocs](https://github.com/doocs) — Core implementation logic for Markdown to HTML conversion
  1066. - [High-density Infographic Prompt](https://waytoagi.feishu.cn/wiki/YG0zwalijihRREkgmPzcWRInnUg) by AJ@WaytoAGI — Inspiration for the infographic skill
  1067. - [qiaomu-mondo-poster-design](https://github.com/joeseesun/qiaomu-mondo-poster-design) by [@joeseesun](https://github.com/joeseesun)(乔木) — Inspiration for the Mondo style
  1068. - [architecture-diagram-generator](https://github.com/Cocoon-AI/architecture-diagram-generator) by [@Cocoon-AI](https://github.com/Cocoon-AI) — Inspiration for the diagram skill's design system
  1069. ## License
  1070. Unless otherwise noted, this repository is licensed under the [MIT License](./LICENSE).
  1071. Published ClawHub skills follow ClawHub registry rules and are distributed under `MIT-0`. Third-party code and assets retain their original licenses where noted.
  1072. ## Star History
  1073. [![Star History Chart](https://api.star-history.com/svg?repos=JimLiu/baoyu-skills&type=Date)](https://www.star-history.com/#JimLiu/baoyu-skills&Date)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.