Skip to content
Back to search

canghe-skills

MarketplaceWorks with Claude CodeGitHub

苍何的技能skills仓库,搜集好用的 skills,辅助提效

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/freestylefly--canghe-skills/badge.svg)](/listings/freestylefly--canghe-skills)

HTML

<a href="/listings/freestylefly--canghe-skills"><img src="/api/listings/freestylefly--canghe-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.

Quick Install (Recommended)

npx skills add freestylefly/canghe-skills

Register as Plugin Marketplace

Run the following command in Claude Code:

/plugin marketplace add freestylefly/canghe-skills

Install Skills

**Option 1: Via Browse UI**

1. Select **Browse and install plugins** 2. Select **canghe-skills** 3. Select the plugin(s) you want to install 4. Select **Install now**

**Option 2: Direct Install**

# Install specific plugin
/plugin install content-skills@canghe-skills
/plugin install ai-generation-skills@canghe-skills
/plugin install business-intelligence-skills@canghe-skills
/plugin install utility-skills@canghe-skills

**Option 3: Ask the Agent**

Simply tell Claude Code:

> Please install Skills from github.com/freestylefly/canghe-skills

Available Plugins

| Plugin | Description | Skills | |--------|-------------|--------| | **content-skills** | Content generation and publishing | [xhs-images](#canghe-xhs-images), [infographic](#canghe-infographic), [cover-image](#canghe-cover-image), [slide-deck](#canghe-slide-deck), [comic](#canghe-comic), [article-illustrator](#canghe-article-illustrator), [post-to-x](#canghe-post-to-x), [post-to-wechat](#canghe-post-to-wechat), [manga-drama](#canghe-manga-drama), [manga-style-video](#canghe-manga-style-video) | | **ai-generation-skills** | AI-powered generation backends | [image-gen](#canghe-image-gen), [danger-gemini-web](#canghe-danger-gemini-web), [seedance-video](#canghe-seedance-video), [flyworks-avatar-video](#flyworks-avatar-video) | | **business-intelligence-skills** | Business research and company intelligence | [tianyancha](#canghe-tianyancha) | | **utility-skills** | Utility tools for content processing | [url-to-markdown](#canghe-url-to-markdown), [danger-x-to-markdown](#canghe-danger-x-to-markdown), [compress-image](#canghe-compress-image), [format-markdown](#canghe-format-markdown), [wechat-article-extractor](#canghe-wechat-article-extractor), [markdown-to-html](#canghe-markdown-to-html), [find-skills](#find-skills), [obsidian-skills](#obsidian-skills), [obsidian-bases](#obsidian-bases), [obsidian-markdown](#obsidian-markdown), [remotion-best-practices](#remotion-best-practices), [skill-creator](#skill-creator), [volcengine-video-understanding](#canghe-volcengine-video-understanding), [douyin-downloader](#canghe-douyin-downloader), [paddleocr-doc-parsing](#paddleocr-doc-parsing) |

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 · 69 lines

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

  1. {
  2. "name": "canghe-skills",
  3. "owner": {
  4. "name": "freestylefly (苍何)",
  5. "email": "canghe0818@gmail.com"
  6. },
  7. "metadata": {
  8. "description": "Skills shared by canghe for improving daily work efficiency",
  9. "version": "1.37.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "content-skills",
  14. "description": "Content generation and publishing skills",
  15. "source": "./",
  16. "strict": false,
  17. "skills": [
  18. "./skills/canghe-xhs-images",
  19. "./skills/canghe-post-to-x",
  20. "./skills/canghe-post-to-wechat",
  21. "./skills/canghe-article-illustrator",
  22. "./skills/canghe-cover-image",
  23. "./skills/canghe-slide-deck",
  24. "./skills/canghe-comic",
  25. "./skills/canghe-infographic",
  26. "./skills/canghe-manga-drama",
  27. "./skills/canghe-manga-style-video"
  28. ]
  29. },
  30. {
  31. "name": "ai-generation-skills",
  32. "description": "AI-powered generation backends",
  33. "source": "./",
  34. "strict": false,
  35. "skills": [
  36. "./skills/canghe-danger-gemini-web",
  37. "./skills/canghe-image-gen",
  38. "./skills/canghe-seedance-video",
  39. "./skills/flyworks-avatar-video-1.0.0"
  40. ]
  41. },
  42. {
  43. "name": "business-intelligence-skills",
  44. "description": "Business research, company intelligence, and dashboard skills",
  45. "source": "./",
  46. "strict": false,
  47. "skills": [
  48. "./skills/canghe-tianyancha"
  49. ]
  50. },
  51. {
  52. "name": "utility-skills",
  53. "description": "Utility tools for content processing",
  54. "source": "./",
  55. "strict": false,
  56. "skills": [
  57. "./skills/canghe-danger-x-to-markdown",
  58. "./skills/canghe-compress-image",
  59. "./skills/canghe-url-to-markdown",
  60. "./skills/canghe-format-markdown",
  61. "./skills/canghe-markdown-to-html",
  62. "./skills/canghe-wechat-article-extractor",
  63. "./skills/canghe-volcengine-video-understanding",
  64. "./skills/canghe-douyin-downloader",
  65. "./skills/paddleocr-doc-parsing"
  66. ]
  67. }
  68. ]
  69. }
README.md · README · 1,084 lines

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

  1. # canghe-skills
  2. English | [中文](./README.zh.md)
  3. Skills shared by Canghe for improving daily work efficiency with Claude Code.
  4. ## Prerequisites
  5. - Node.js environment installed
  6. - Ability to run `npx bun` commands
  7. ## Installation
  8. ### Quick Install (Recommended)
  9. ```bash
  10. npx skills add freestylefly/canghe-skills
  11. ```
  12. ### Register as Plugin Marketplace
  13. Run the following command in Claude Code:
  14. ```bash
  15. /plugin marketplace add freestylefly/canghe-skills
  16. ```
  17. ### Install Skills
  18. **Option 1: Via Browse UI**
  19. 1. Select **Browse and install plugins**
  20. 2. Select **canghe-skills**
  21. 3. Select the plugin(s) you want to install
  22. 4. Select **Install now**
  23. **Option 2: Direct Install**
  24. ```bash
  25. # Install specific plugin
  26. /plugin install content-skills@canghe-skills
  27. /plugin install ai-generation-skills@canghe-skills
  28. /plugin install business-intelligence-skills@canghe-skills
  29. /plugin install utility-skills@canghe-skills
  30. ```
  31. **Option 3: Ask the Agent**
  32. Simply tell Claude Code:
  33. > Please install Skills from github.com/freestylefly/canghe-skills
  34. ### Available Plugins
  35. | Plugin | Description | Skills |
  36. |--------|-------------|--------|
  37. | **content-skills** | Content generation and publishing | [xhs-images](#canghe-xhs-images), [infographic](#canghe-infographic), [cover-image](#canghe-cover-image), [slide-deck](#canghe-slide-deck), [comic](#canghe-comic), [article-illustrator](#canghe-article-illustrator), [post-to-x](#canghe-post-to-x), [post-to-wechat](#canghe-post-to-wechat), [manga-drama](#canghe-manga-drama), [manga-style-video](#canghe-manga-style-video) |
  38. | **ai-generation-skills** | AI-powered generation backends | [image-gen](#canghe-image-gen), [danger-gemini-web](#canghe-danger-gemini-web), [seedance-video](#canghe-seedance-video), [flyworks-avatar-video](#flyworks-avatar-video) |
  39. | **business-intelligence-skills** | Business research and company intelligence | [tianyancha](#canghe-tianyancha) |
  40. | **utility-skills** | Utility tools for content processing | [url-to-markdown](#canghe-url-to-markdown), [danger-x-to-markdown](#canghe-danger-x-to-markdown), [compress-image](#canghe-compress-image), [format-markdown](#canghe-format-markdown), [wechat-article-extractor](#canghe-wechat-article-extractor), [markdown-to-html](#canghe-markdown-to-html), [find-skills](#find-skills), [obsidian-skills](#obsidian-skills), [obsidian-bases](#obsidian-bases), [obsidian-markdown](#obsidian-markdown), [remotion-best-practices](#remotion-best-practices), [skill-creator](#skill-creator), [volcengine-video-understanding](#canghe-volcengine-video-understanding), [douyin-downloader](#canghe-douyin-downloader), [paddleocr-doc-parsing](#paddleocr-doc-parsing) |
  41. ## Update Skills
  42. To update skills to the latest version:
  43. 1. Run `/plugin` in Claude Code
  44. 2. Switch to **Marketplaces** tab (use arrow keys or Tab)
  45. 3. Select **canghe-skills**
  46. 4. Choose **Update marketplace**
  47. You can also **Enable auto-update** to get the latest versions automatically.
  48. ![Update Skills](./screenshots/update-plugins.png)
  49. ## Available Skills
  50. Skills are organized into three categories:
  51. ### Content Skills
  52. Content generation and publishing skills.
  53. #### canghe-manga-drama
  54. Manga drama generator - creates comic-style short dramas based on Seedance. Supports automatic storyboard script generation with a character image as the base.
  55. ```bash
  56. # Generate manga drama with character image
  57. /canghe-manga-drama generate --image /path/to/character.png --theme "campus life" --scenes 3
  58. # From custom script
  59. /canghe-manga-drama from-script --script my_drama.json --image /path/to/character.png
  60. ```
  61. **Built-in Scene Types**: `introduction` (character entry), `action` (action scene), `emotion` (emotion expression), `interaction` (interaction scene), `ending` (closing shot)
  62. #### canghe-manga-style-video
  63. Manga-style video generator - specialized in generating anime-style animated videos. 8 built-in manga style templates, supports image-to-video.
  64. ```bash
  65. # Basic generation with Japanese style
  66. /canghe-manga-style-video "A girl reading under cherry blossoms"
  67. # Specify style
  68. /canghe-manga-style-video "Landscape painting" --style chinese
  69. /canghe-manga-style-video "Cute animals" --style cartoon
  70. /canghe-manga-style-video "Rural scenery" --style ghibli
  71. # With reference image
  72. /canghe-manga-style-video "Grandma making dumplings" --style japanese --image ~/Desktop/character.png
  73. ```
  74. **8 Manga Styles**:
  75. - `japanese` - Japanese healing style (default)
  76. - `ghibli` - Studio Ghibli style
  77. - `chinese` - Chinese ink wash style
  78. - `cartoon` - American cartoon style
  79. - `sketch` - Pencil sketch
  80. - `watercolor` - Watercolor hand-drawn
  81. - `manga_comic` - Japanese manga
  82. - `chibi` - Q-style cute
  83. #### canghe-xhs-images
  84. Xiaohongshu (RedNote) infographic series generator. Breaks down content into 1-10 cartoon-style infographics with **Style × Layout** two-dimensional system.
  85. ```bash
  86. # Auto-select style and layout
  87. /canghe-xhs-images posts/ai-future/article.md
  88. # Specify style
  89. /canghe-xhs-images posts/ai-future/article.md --style notion
  90. # Specify layout
  91. /canghe-xhs-images posts/ai-future/article.md --layout dense
  92. # Combine style and layout
  93. /canghe-xhs-images posts/ai-future/article.md --style tech --layout list
  94. # Direct content input
  95. /canghe-xhs-images 今日星座运势
  96. ```
  97. **Styles** (visual aesthetics): `cute` (default), `fresh`, `warm`, `bold`, `minimal`, `retro`, `pop`, `notion`, `chalkboard`
  98. **Style Previews**:
  99. | | | |
  100. |:---:|:---:|:---:|
  101. | ![cute](./screenshots/xhs-images-styles/cute.webp) | ![fresh](./screenshots/xhs-images-styles/fresh.webp) | ![warm](./screenshots/xhs-images-styles/warm.webp) |
  102. | cute | fresh | warm |
  103. | ![bold](./screenshots/xhs-images-styles/bold.webp) | ![minimal](./screenshots/xhs-images-styles/minimal.webp) | ![retro](./screenshots/xhs-images-styles/retro.webp) |
  104. | bold | minimal | retro |
  105. | ![pop](./screenshots/xhs-images-styles/pop.webp) | ![notion](./screenshots/xhs-images-styles/notion.webp) | ![chalkboard](./screenshots/xhs-images-styles/chalkboard.webp) |
  106. | pop | notion | chalkboard |
  107. **Layouts** (information density):
  108. | Layout | Density | Best for |
  109. |--------|---------|----------|
  110. | `sparse` | 1-2 pts | Covers, quotes |
  111. | `balanced` | 3-4 pts | Regular content |
  112. | `dense` | 5-8 pts | Knowledge cards, cheat sheets |
  113. | `list` | 4-7 items | Checklists, rankings |
  114. | `comparison` | 2 sides | Before/after, pros/cons |
  115. | `flow` | 3-6 steps | Processes, timelines |
  116. **Layout Previews**:
  117. | | | |
  118. |:---:|:---:|:---:|
  119. | ![sparse](./screenshots/xhs-images-layouts/sparse.webp) | ![balanced](./screenshots/xhs-images-layouts/balanced.webp) | ![dense](./screenshots/xhs-images-layouts/dense.webp) |
  120. | sparse | balanced | dense |
  121. | ![list](./screenshots/xhs-images-layouts/list.webp) | ![comparison](./screenshots/xhs-images-layouts/comparison.webp) | ![flow](./screenshots/xhs-images-layouts/flow.webp) |
  122. | list | comparison | flow |
  123. #### canghe-infographic
  124. Generate professional infographics with 20 layout types and 17 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics.
  125. ```bash
  126. # Auto-recommend combinations based on content
  127. /canghe-infographic path/to/content.md
  128. # Specify layout
  129. /canghe-infographic path/to/content.md --layout pyramid
  130. # Specify style (default: craft-handmade)
  131. /canghe-infographic path/to/content.md --style technical-schematic
  132. # Specify both
  133. /canghe-infographic path/to/content.md --layout funnel --style corporate-memphis
  134. # With aspect ratio
  135. /canghe-infographic path/to/content.md --aspect portrait
  136. ```
  137. **Options**:
  138. | Option | Description |
  139. |--------|-------------|
  140. | `--layout <name>` | Information layout (20 options) |
  141. | `--style <name>` | Visual style (17 options, default: craft-handmade) |
  142. | `--aspect <ratio>` | landscape (16:9), portrait (9:16), square (1:1) |
  143. | `--lang <code>` | Output language (en, zh, ja, etc.) |
  144. **Layouts** (information structure):
  145. | Layout | Best For |
  146. |--------|----------|
  147. | `bridge` | Problem-solution, gap-crossing |
  148. | `circular-flow` | Cycles, recurring processes |
  149. | `comparison-table` | Multi-factor comparisons |
  150. | `do-dont` | Correct vs incorrect practices |
  151. | `equation` | Formula breakdown, input-output |
  152. | `feature-list` | Product features, bullet points |
  153. | `fishbone` | Root cause analysis |
  154. | `funnel` | Conversion processes, filtering |
  155. | `grid-cards` | Multiple topics, overview |
  156. | `iceberg` | Surface vs hidden aspects |
  157. | `journey-path` | Customer journey, milestones |
  158. | `layers-stack` | Technology stack, layers |
  159. | `mind-map` | Brainstorming, idea mapping |
  160. | `nested-circles` | Levels of influence, scope |
  161. | `priority-quadrants` | Eisenhower matrix, 2x2 |
  162. | `pyramid` | Hierarchy, Maslow's needs |
  163. | `scale-balance` | Pros vs cons, weighing |
  164. | `timeline-horizontal` | History, chronological events |
  165. | `tree-hierarchy` | Org charts, taxonomy |
  166. | `venn` | Overlapping concepts |
  167. **Layout Previews**:
  168. | | | |
  169. |:---:|:---:|:---:|
  170. | ![bridge](./screenshots/infographic-layouts/bridge.webp) | ![circular-flow](./screenshots/infographic-layouts/circular-flow.webp) | ![comparison-table](./screenshots/infographic-layouts/comparison-table.webp) |
  171. | bridge | circular-flow | comparison-table |
  172. | ![do-dont](./screenshots/infographic-layouts/do-dont.webp) | ![equation](./screenshots/infographic-layouts/equation.webp) | ![feature-list](./screenshots/infographic-layouts/feature-list.webp) |
  173. | do-dont | equation | feature-list |
  174. | ![fishbone](./screenshots/infographic-layouts/fishbone.webp) | ![funnel](./screenshots/infographic-layouts/funnel.webp) | ![grid-cards](./screenshots/infographic-layouts/grid-cards.webp) |
  175. | fishbone | funnel | grid-cards |
  176. | ![iceberg](./screenshots/infographic-layouts/iceberg.webp) | ![journey-path](./screenshots/infographic-layouts/journey-path.webp) | ![layers-stack](./screenshots/infographic-layouts/layers-stack.webp) |
  177. | iceberg | journey-path | layers-stack |
  178. | ![mind-map](./screenshots/infographic-layouts/mind-map.webp) | ![nested-circles](./screenshots/infographic-layouts/nested-circles.webp) | ![priority-quadrants](./screenshots/infographic-layouts/priority-quadrants.webp) |
  179. | mind-map | nested-circles | priority-quadrants |
  180. | ![pyramid](./screenshots/infographic-layouts/pyramid.webp) | ![scale-balance](./screenshots/infographic-layouts/scale-balance.webp) | ![timeline-horizontal](./screenshots/infographic-layouts/timeline-horizontal.webp) |
  181. | pyramid | scale-balance | timeline-horizontal |
  182. | ![tree-hierarchy](./screenshots/infographic-layouts/tree-hierarchy.webp) | ![venn](./screenshots/infographic-layouts/venn.webp) | |
  183. | tree-hierarchy | venn | |
  184. **Styles** (visual aesthetics):
  185. | Style | Description |
  186. |-------|-------------|
  187. | `craft-handmade` (Default) | Hand-drawn illustration, paper craft aesthetic |
  188. | `claymation` | 3D clay figures, playful stop-motion |
  189. | `kawaii` | Japanese cute, big eyes, pastel colors |
  190. | `storybook-watercolor` | Soft painted illustrations, whimsical |
  191. | `chalkboard` | Colorful chalk on black board |
  192. | `cyberpunk-neon` | Neon glow on dark, futuristic |
  193. | `bold-graphic` | Comic style, halftone dots, high contrast |
  194. | `aged-academia` | Vintage science, sepia sketches |
  195. | `corporate-memphis` | Flat vector people, vibrant fills |
  196. | `technical-schematic` | Blueprint, isometric 3D, engineering |
  197. | `origami` | Folded paper forms, geometric |
  198. | `pixel-art` | Retro 8-bit, nostalgic gaming |
  199. | `ui-wireframe` | Grayscale boxes, interface mockup |
  200. | `subway-map` | Transit diagram, colored lines |
  201. | `ikea-manual` | Minimal line art, assembly style |
  202. | `knolling` | Organized flat-lay, top-down |
  203. | `lego-brick` | Toy brick construction, playful |
  204. **Style Previews**:
  205. | | | |
  206. |:---:|:---:|:---:|
  207. | ![craft-handmade](./screenshots/infographic-styles/craft-handmade.webp) | ![claymation](./screenshots/infographic-styles/claymation.webp) | ![kawaii](./screenshots/infographic-styles/kawaii.webp) |
  208. | craft-handmade | claymation | kawaii |
  209. | ![storybook-watercolor](./screenshots/infographic-styles/storybook-watercolor.webp) | ![chalkboard](./screenshots/infographic-styles/chalkboard.webp) | ![cyberpunk-neon](./screenshots/infographic-styles/cyberpunk-neon.webp) |
  210. | storybook-watercolor | chalkboard | cyberpunk-neon |
  211. | ![bold-graphic](./screenshots/infographic-styles/bold-graphic.webp) | ![aged-academia](./screenshots/infographic-styles/aged-academia.webp) | ![corporate-memphis](./screenshots/infographic-styles/corporate-memphis.webp) |
  212. | bold-graphic | aged-academia | corporate-memphis |
  213. | ![technical-schematic](./screenshots/infographic-styles/technical-schematic.webp) | ![origami](./screenshots/infographic-styles/origami.webp) | ![pixel-art](./screenshots/infographic-styles/pixel-art.webp) |
  214. | technical-schematic | origami | pixel-art |
  215. | ![ui-wireframe](./screenshots/infographic-styles/ui-wireframe.webp) | ![subway-map](./screenshots/infographic-styles/subway-map.webp) | ![ikea-manual](./screenshots/infographic-styles/ikea-manual.webp) |
  216. | ui-wireframe | subway-map | ikea-manual |
  217. | ![knolling](./screenshots/infographic-styles/knolling.webp) | ![lego-brick](./screenshots/infographic-styles/lego-brick.webp) | |
  218. | knolling | lego-brick | |
  219. #### canghe-cover-image
  220. Generate cover images for articles with 5 dimensions: Type × Palette × Rendering × Text × Mood. Combines 9 color palettes with 6 rendering styles for 54 unique combinations.
  221. ```bash
  222. # Auto-select all dimensions based on content
  223. /canghe-cover-image path/to/article.md
  224. # Quick mode: skip confirmation, use auto-selection
  225. /canghe-cover-image path/to/article.md --quick
  226. # Specify dimensions (5D system)
  227. /canghe-cover-image path/to/article.md --type conceptual --palette cool --rendering digital
  228. /canghe-cover-image path/to/article.md --text title-subtitle --mood bold
  229. # Style presets (backward-compatible shorthand)
  230. /canghe-cover-image path/to/article.md --style blueprint
  231. # Specify aspect ratio (default: 16:9)
  232. /canghe-cover-image path/to/article.md --aspect 2.35:1
  233. # Visual only (no title text)
  234. /canghe-cover-image path/to/article.md --no-title
  235. ```
  236. **Five Dimensions**:
  237. - **Type**: `hero`, `conceptual`, `typography`, `metaphor`, `scene`, `minimal`
  238. - **Palette**: `warm`, `elegant`, `cool`, `dark`, `earth`, `vivid`, `pastel`, `mono`, `retro`
  239. - **Rendering**: `flat-vector`, `hand-drawn`, `painterly`, `digital`, `pixel`, `chalk`
  240. - **Text**: `none`, `title-only` (default), `title-subtitle`, `text-rich`
  241. - **Mood**: `subtle`, `balanced` (default), `bold`
  242. #### canghe-slide-deck
  243. Generate professional slide deck images from content. Creates comprehensive outlines with style instructions, then generates individual slide images.
  244. ```bash
  245. # From markdown file
  246. /canghe-slide-deck path/to/article.md
  247. # With style and audience
  248. /canghe-slide-deck path/to/article.md --style corporate
  249. /canghe-slide-deck path/to/article.md --audience executives
  250. # Target slide count
  251. /canghe-slide-deck path/to/article.md --slides 15
  252. # Outline only (no image generation)
  253. /canghe-slide-deck path/to/article.md --outline-only
  254. # With language
  255. /canghe-slide-deck path/to/article.md --lang zh
  256. ```
  257. **Options**:
  258. | Option | Description |
  259. |--------|-------------|
  260. | `--style <name>` | Visual style: preset name or `custom` |
  261. | `--audience <type>` | Target: beginners, intermediate, experts, executives, general |
  262. | `--lang <code>` | Output language (en, zh, ja, etc.) |
  263. | `--slides <number>` | Target slide count (8-25 recommended, max 30) |
  264. | `--outline-only` | Generate outline only, skip images |
  265. | `--prompts-only` | Generate outline + prompts, skip images |
  266. | `--images-only` | Generate images from existing prompts |
  267. | `--regenerate <N>` | Regenerate specific slide(s): `3` or `2,5,8` |
  268. **Style System**:
  269. Styles are built from 4 dimensions: **Texture** × **Mood** × **Typography** × **Density**
  270. | Dimension | Options |
  271. |-----------|---------|
  272. | Texture | clean, grid, organic, pixel, paper |
  273. | Mood | professional, warm, cool, vibrant, dark, neutral |
  274. | Typography | geometric, humanist, handwritten, editorial, technical |
  275. | Density | minimal, balanced, dense |
  276. **Presets** (pre-configured dimension combinations):
  277. | Preset | Dimensions | Best For |
  278. |--------|------------|----------|
  279. | `blueprint` (default) | grid + cool + technical + balanced | Architecture, system design |
  280. | `chalkboard` | organic + warm + handwritten + balanced | Education, tutorials |
  281. | `corporate` | clean + professional + geometric + balanced | Investor decks, proposals |
  282. | `minimal` | clean + neutral + geometric + minimal | Executive briefings |
  283. | `sketch-notes` | organic + warm + handwritten + balanced | Educational, tutorials |
  284. | `watercolor` | organic + warm + humanist + minimal | Lifestyle, wellness |
  285. | `dark-atmospheric` | clean + dark + editorial + balanced | Entertainment, gaming |
  286. | `notion` | clean + neutral + geometric + dense | Product demos, SaaS |
  287. | `bold-editorial` | clean + vibrant + editorial + balanced | Product launches, keynotes |
  288. | `editorial-infographic` | clean + cool + editorial + dense | Tech explainers, research |
  289. | `fantasy-animation` | organic + vibrant + handwritten + minimal | Educational storytelling |
  290. | `intuition-machine` | clean + cool + technical + dense | Technical docs, academic |
  291. | `pixel-art` | pixel + vibrant + technical + balanced | Gaming, developer talks |
  292. | `scientific` | clean + cool + technical + dense | Biology, chemistry, medical |
  293. | `vector-illustration` | clean + vibrant + humanist + balanced | Creative, children's content |
  294. | `vintage` | paper + warm + editorial + balanced | Historical, heritage |
  295. **Style Previews**:
  296. | | | |
  297. |:---:|:---:|:---:|
  298. | ![blueprint](./screenshots/slide-deck-styles/blueprint.webp) | ![chalkboard](./screenshots/slide-deck-styles/chalkboard.webp) | ![bold-editorial](./screenshots/slide-deck-styles/bold-editorial.webp) |
  299. | blueprint | chalkboard | bold-editorial |
  300. | ![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) |
  301. | corporate | dark-atmospheric | editorial-infographic |
  302. | ![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) |
  303. | fantasy-animation | intuition-machine | minimal |
  304. | ![notion](./screenshots/slide-deck-styles/notion.webp) | ![pixel-art](./screenshots/slide-deck-styles/pixel-art.webp) | ![scientific](./screenshots/slide-deck-styles/scientific.webp) |
  305. | notion | pixel-art | scientific |
  306. | ![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) |
  307. | sketch-notes | vector-illustration | vintage |
  308. | ![watercolor](./screenshots/slide-deck-styles/watercolor.webp) | | |
  309. | watercolor | | |
  310. After generation, slides are automatically merged into `.pptx` and `.pdf` files for easy sharing.
  311. #### canghe-comic
  312. Knowledge comic creator with flexible art style × tone combinations. Creates original educational comics with detailed panel layouts and sequential image generation.
  313. ```bash
  314. # From source material (auto-selects art + tone)
  315. /canghe-comic posts/turing-story/source.md
  316. # Specify art style and tone
  317. /canghe-comic posts/turing-story/source.md --art manga --tone warm
  318. /canghe-comic posts/turing-story/source.md --art ink-brush --tone dramatic
  319. # Use preset (includes special rules)
  320. /canghe-comic posts/turing-story/source.md --style ohmsha
  321. /canghe-comic posts/turing-story/source.md --style wuxia
  322. # Specify layout and aspect ratio
  323. /canghe-comic posts/turing-story/source.md --layout cinematic
  324. /canghe-comic posts/turing-story/source.md --aspect 16:9
  325. # Specify language
  326. /canghe-comic posts/turing-story/source.md --lang zh
  327. # Direct content input
  328. /canghe-comic "The story of Alan Turing and the birth of computer science"
  329. ```
  330. **Options**:
  331. | Option | Values |
  332. |--------|--------|
  333. | `--art` | `ligne-claire` (default), `manga`, `realistic`, `ink-brush`, `chalk` |
  334. | `--tone` | `neutral` (default), `warm`, `dramatic`, `romantic`, `energetic`, `vintage`, `action` |
  335. | `--style` | `ohmsha`, `wuxia`, `shoujo` (presets with special rules) |
  336. | `--layout` | `standard` (default), `cinematic`, `dense`, `splash`, `mixed`, `webtoon` |
  337. | `--aspect` | `3:4` (default, portrait), `4:3` (landscape), `16:9` (widescreen) |
  338. | `--lang` | `auto` (default), `zh`, `en`, `ja`, etc. |
  339. **Art Styles** (rendering technique):
  340. | Art Style | Description |
  341. |-----------|-------------|
  342. | `ligne-claire` | Uniform lines, flat colors, European comic tradition (Tintin, Logicomix) |
  343. | `manga` | Large eyes, manga conventions, expressive emotions |
  344. | `realistic` | Digital painting, realistic proportions, sophisticated |
  345. | `ink-brush` | Chinese brush strokes, ink wash effects |
  346. | `chalk` | Chalkboard aesthetic, hand-drawn warmth |
  347. **Tones** (mood/atmosphere):
  348. | Tone | Description |
  349. |------|-------------|
  350. | `neutral` | Balanced, rational, educational |
  351. | `warm` | Nostalgic, personal, comforting |
  352. | `dramatic` | High contrast, intense, powerful |
  353. | `romantic` | Soft, beautiful, decorative elements |
  354. | `energetic` | Bright, dynamic, exciting |
  355. | `vintage` | Historical, aged, period authenticity |
  356. | `action` | Speed lines, impact effects, combat |
  357. **Presets** (art + tone + special rules):
  358. | Preset | Equivalent | Special Rules |
  359. |--------|-----------|---------------|
  360. | `ohmsha` | manga + neutral | Visual metaphors, NO talking heads, gadget reveals |
  361. | `wuxia` | ink-brush + action | Qi effects, combat visuals, atmospheric elements |
  362. | `shoujo` | manga + romantic | Decorative elements, eye details, romantic beats |
  363. **Layouts** (panel arrangement):
  364. | Layout | Panels/Page | Best for |
  365. |--------|-------------|----------|
  366. | `standard` | 4-6 | Dialogue, narrative flow |
  367. | `cinematic` | 2-4 | Dramatic moments, establishing shots |
  368. | `dense` | 6-9 | Technical explanations, timelines |
  369. | `splash` | 1-2 large | Key moments, revelations |
  370. | `mixed` | 3-7 varies | Complex narratives, emotional arcs |
  371. | `webtoon` | 3-5 vertical | Ohmsha tutorials, mobile reading |
  372. **Layout Previews**:
  373. | | | |
  374. |:---:|:---:|:---:|
  375. | ![standard](./screenshots/comic-layouts/standard.webp) | ![cinematic](./screenshots/comic-layouts/cinematic.webp) | ![dense](./screenshots/comic-layouts/dense.webp) |
  376. | standard | cinematic | dense |
  377. | ![splash](./screenshots/comic-layouts/splash.webp) | ![mixed](./screenshots/comic-layouts/mixed.webp) | ![webtoon](./screenshots/comic-layouts/webtoon.webp) |
  378. | splash | mixed | webtoon |
  379. #### canghe-article-illustrator
  380. Smart article illustration skill with Type × Style two-dimension approach. Analyzes article structure, identifies positions requiring visual aids, and generates illustrations.
  381. ```bash
  382. # Auto-select type and style based on content
  383. /canghe-article-illustrator path/to/article.md
  384. # Specify type
  385. /canghe-article-illustrator path/to/article.md --type infographic
  386. # Specify style
  387. /canghe-article-illustrator path/to/article.md --style blueprint
  388. # Combine type and style
  389. /canghe-article-illustrator path/to/article.md --type flowchart --style notion
  390. ```
  391. **Types** (information structure):
  392. | Type | Description | Best For |
  393. |------|-------------|----------|
  394. | `infographic` | Data visualization, charts, metrics | Technical articles, data analysis |
  395. | `scene` | Atmospheric illustration, mood rendering | Narrative, personal stories |
  396. | `flowchart` | Process diagrams, step visualization | Tutorials, workflows |
  397. | `comparison` | Side-by-side, before/after contrast | Product comparisons |
  398. | `framework` | Concept maps, relationship diagrams | Methodologies, architecture |
  399. | `timeline` | Chronological progression | History, project progress |
  400. **Styles** (visual aesthetics):
  401. | Style | Description | Best For |
  402. |-------|-------------|----------|
  403. | `notion` (default) | Minimalist hand-drawn line art | Knowledge sharing, SaaS, productivity |
  404. | `elegant` | Refined, sophisticated | Business, thought leadership |
  405. | `warm` | Friendly, approachable | Personal growth, lifestyle |
  406. | `minimal` | Ultra-clean, zen-like | Philosophy, minimalism |
  407. | `blueprint` | Technical schematics | Architecture, system design |
  408. | `watercolor` | Soft artistic with natural warmth | Lifestyle, travel, creative |
  409. | `editorial` | Magazine-style infographic | Tech explainers, journalism |
  410. | `scientific` | Academic precise diagrams | Biology, chemistry, technical |
  411. **Style Previews**:
  412. | | | |
  413. |:---:|:---:|:---:|
  414. | ![notion](./screenshots/article-illustrator-styles/notion.webp) | ![elegant](./screenshots/article-illustrator-styles/elegant.webp) | ![warm](./screenshots/article-illustrator-styles/warm.webp) |
  415. | notion | elegant | warm |
  416. | ![minimal](./screenshots/article-illustrator-styles/minimal.webp) | ![blueprint](./screenshots/article-illustrator-styles/blueprint.webp) | ![watercolor](./screenshots/article-illustrator-styles/watercolor.webp) |
  417. | minimal | blueprint | watercolor |
  418. | ![editorial](./screenshots/article-illustrator-styles/editorial.webp) | ![scientific](./screenshots/article-illustrator-styles/scientific.webp) | |
  419. | editorial | scientific | |
  420. #### canghe-post-to-x
  421. 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.
  422. ```bash
  423. # Post with text
  424. /canghe-post-to-x "Hello from Claude Code!"
  425. # Post with images
  426. /canghe-post-to-x "Check this out" --image photo.png
  427. # Post X Article
  428. /canghe-post-to-x --article path/to/article.md
  429. ```
  430. #### canghe-post-to-wechat
  431. Post content to WeChat Official Account (微信公众号). Two modes available:
  432. **Image-Text (贴图)** - Multiple images with short title/content:
  433. ```bash
  434. /canghe-post-to-wechat 贴图 --markdown article.md --images ./photos/
  435. /canghe-post-to-wechat 贴图 --markdown article.md --image img1.png --image img2.png --image img3.png
  436. /canghe-post-to-wechat 贴图 --title "标题" --content "内容" --image img1.png --submit
  437. ```
  438. **Article (文章)** - Full markdown/HTML with rich formatting:
  439. ```bash
  440. /canghe-post-to-wechat 文章 --markdown article.md
  441. /canghe-post-to-wechat 文章 --markdown article.md --theme grace
  442. /canghe-post-to-wechat 文章 --html article.html
  443. ```
  444. **Publishing Methods**:
  445. | Method | Speed | Requirements |
  446. |--------|-------|--------------|
  447. | API (Recommended) | Fast | API credentials |
  448. | Browser | Slow | Chrome, login session |
  449. **API Configuration** (for faster publishing):
  450. ```bash
  451. # Add to .canghe-skills/.env (project-level) or ~/.canghe-skills/.env (user-level)
  452. WECHAT_APP_ID=your_app_id
  453. WECHAT_APP_SECRET=your_app_secret
  454. ```
  455. To obtain credentials:
  456. 1. Visit https://developers.weixin.qq.com/platform/
  457. 2. Go to: 我的业务 → 公众号 → 开发密钥
  458. 3. Create development key and copy AppID/AppSecret
  459. 4. Add your machine's IP to the whitelist
  460. **Browser Method** (no API setup needed): Requires Google Chrome. First run opens browser for QR code login (session preserved).
  461. ### AI Generation Skills
  462. AI-powered generation backends.
  463. #### canghe-image-gen
  464. AI SDK-based image generation using official OpenAI, Google and DashScope (Aliyun Tongyi Wanxiang) APIs. Supports text-to-image, reference images, aspect ratios, and quality presets.
  465. ```bash
  466. # Basic generation (auto-detect provider)
  467. /canghe-image-gen --prompt "A cute cat" --image cat.png
  468. # With aspect ratio
  469. /canghe-image-gen --prompt "A landscape" --image landscape.png --ar 16:9
  470. # High quality (2k)
  471. /canghe-image-gen --prompt "A banner" --image banner.png --quality 2k
  472. # Specific provider
  473. /canghe-image-gen --prompt "A cat" --image cat.png --provider openai
  474. # DashScope (Aliyun Tongyi Wanxiang)
  475. /canghe-image-gen --prompt "一只可爱的猫" --image cat.png --provider dashscope
  476. # With reference images (Google multimodal only)
  477. /canghe-image-gen --prompt "Make it blue" --image out.png --ref source.png
  478. ```
  479. **Options**:
  480. | Option | Description |
  481. |--------|-------------|
  482. | `--prompt`, `-p` | Prompt text |
  483. | `--promptfiles` | Read prompt from files (concatenated) |
  484. | `--image` | Output image path (required) |
  485. | `--provider` | `google`, `openai` or `dashscope` (default: google) |
  486. | `--model`, `-m` | Model ID |
  487. | `--ar` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
  488. | `--size` | Size (e.g., `1024x1024`) |
  489. | `--quality` | `normal` or `2k` (default: normal) |
  490. | `--ref` | Reference images (Google multimodal only) |
  491. **Environment Variables** (see [Environment Configuration](#environment-configuration) for setup):
  492. | Variable | Description | Default |
  493. |----------|-------------|---------|
  494. | `OPENAI_API_KEY` | OpenAI API key | - |
  495. | `GOOGLE_API_KEY` | Google API key | - |
  496. | `DASHSCOPE_API_KEY` | DashScope API key (Aliyun) | - |
  497. | `OPENAI_IMAGE_MODEL` | OpenAI model | `gpt-image-1.5` |
  498. | `GOOGLE_IMAGE_MODEL` | Google model | `gemini-3-pro-image-preview` |
  499. | `DASHSCOPE_IMAGE_MODEL` | DashScope model | `z-image-turbo` |
  500. | `OPENAI_BASE_URL` | Custom OpenAI endpoint | - |
  501. | `GOOGLE_BASE_URL` | Custom Google endpoint | - |
  502. | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint | - |
  503. **Provider Auto-Selection**:
  504. 1. If `--provider` specified → use it
  505. 2. If only one API key available → use that provider
  506. 3. If multiple available → default to Google
  507. #### canghe-danger-gemini-web
  508. Interacts with Gemini Web to generate text and images.
  509. **Text Generation:**
  510. ```bash
  511. /canghe-danger-gemini-web "Hello, Gemini"
  512. /canghe-danger-gemini-web --prompt "Explain quantum computing"
  513. ```
  514. **Image Generation:**
  515. ```bash
  516. /canghe-danger-gemini-web --prompt "A cute cat" --image cat.png
  517. /canghe-danger-gemini-web --promptfiles system.md content.md --image out.png
  518. ```
  519. #### canghe-seedance-video
  520. Generate AI videos using ByteDance Seedance. Supports text-to-video and image-to-video, with multiple model options.
  521. ```bash
  522. # Text-to-video
  523. /canghe-seedance-video create --prompt "A cute cat yawning at the camera" --wait --download ~/Desktop
  524. # Image-to-video from local file
  525. /canghe-seedance-video create --prompt "Character slowly turns head and smiles" --image /path/to/photo.jpg --wait --download ~/Desktop
  526. # First + last frame
  527. /canghe-seedance-video create --prompt "Flower blooms from bud to full blossom" --image first.jpg --last-frame last.jpg --wait --download ~/Desktop
  528. # Custom parameters
  529. /canghe-seedance-video create --prompt "City nightscape timelapse" --ratio 21:9 --duration 8 --resolution 1080p --wait --download ~/Desktop
  530. ```
  531. **Supported Models**:
  532. - `doubao-seedance-1-5-pro-251215` (default, with audio)
  533. - `doubao-seedance-1-0-pro-250428`
  534. - `doubao-seedance-1-0-pro-fast-250528`
  535. - `doubao-seedance-1-0-lite-t2v-250219` (text-to-video only)
  536. - `doubao-seedance-1-0-lite-i2v-250219` (image-to-video with reference images)
  537. #### flyworks-avatar-video
  538. Generate videos using Flyworks (HiFly) Digital Humans. Create talking photo videos from images, use public avatars with TTS, or clone voices.
  539. ```bash
  540. # Create video with public avatar (TTS)
  541. /flyworks-avatar-video create_video --type tts --text "Hello world" --avatar "avatar_id" --voice "voice_id"
  542. # Create talking photo video
  543. /flyworks-avatar-video create_talking_photo --image photo.png --title "My Avatar"
  544. # Clone a voice
  545. /flyworks-avatar-video clone_voice --audio audio.mp3 --title "My Voice"
  546. # List available avatars/voices
  547. /flyworks-avatar-video list_public_avatars
  548. /flyworks-avatar-video list_public_voices
  549. ```
  550. **API Token**: Default free-tier token included (with watermark, 30s limit). Set `HIFLY_API_TOKEN` for unlimited access.
  551. ### Business Intelligence Skills
  552. Business research, company intelligence, and dashboard skills.
  553. #### canghe-tianyancha
  554. Generate Tianyancha-style company and industry insight dashboards from researched enterprise data. It organizes company profiles, hiring analysis, legal risks, financing history, shareholders, intellectual property, investments, and key people into single-file HTML dashboards.
  555. ```bash
  556. # Company dashboard
  557. /canghe-tianyancha "Analyze Moonshot AI and generate a company dashboard"
  558. # Industry dashboard
  559. /canghe-tianyancha "Analyze leading AI model companies and generate an industry dashboard"
  560. ```
  561. **Outputs**: single-company dashboards, industry dashboards, or an industry dashboard linked to multiple company dashboards.
  562. ### Utility Skills
  563. Utility tools for content processing.
  564. #### canghe-wechat-article-extractor
  565. Extract metadata and content from WeChat Official Account articles. Parses WeChat article URLs (`mp.weixin.qq.com`) to extract title, author, description, publish time, and content.
  566. ```bash
  567. # Auto extract when providing a WeChat article URL
  568. /canghe-wechat-article-extractor https://mp.weixin.qq.com/s/...
  569. ```
  570. #### canghe-url-to-markdown
  571. Fetch any URL via Chrome CDP and convert to clean markdown. Supports two capture modes for different scenarios.
  572. ```bash
  573. # Auto mode (default) - capture when page loads
  574. /canghe-url-to-markdown https://example.com/article
  575. # Wait mode - for login-required pages
  576. /canghe-url-to-markdown https://example.com/private --wait
  577. # Save to specific file
  578. /canghe-url-to-markdown https://example.com/article -o output.md
  579. ```
  580. **Capture Modes**:
  581. | Mode | Description | Best For |
  582. |------|-------------|----------|
  583. | Auto (default) | Captures immediately after page load | Public pages, static content |
  584. | Wait (`--wait`) | Waits for user signal before capture | Login-required, dynamic content |
  585. **Options**:
  586. | Option | Description |
  587. |--------|-------------|
  588. | `<url>` | URL to fetch |
  589. | `-o <path>` | Output file path |
  590. | `--wait` | Wait for user signal before capturing |
  591. | `--timeout <ms>` | Page load timeout (default: 30000) |
  592. #### canghe-danger-x-to-markdown
  593. Converts X (Twitter) content to markdown format. Supports tweet threads and X Articles.
  594. ```bash
  595. # Convert tweet to markdown
  596. /canghe-danger-x-to-markdown https://x.com/username/status/123456
  597. # Save to specific file
  598. /canghe-danger-x-to-markdown https://x.com/username/status/123456 -o output.md
  599. # JSON output
  600. /canghe-danger-x-to-markdown https://x.com/username/status/123456 --json
  601. # Download media (images/videos) to local files
  602. /canghe-danger-x-to-markdown https://x.com/username/status/123456 --download-media
  603. ```
  604. **Supported URLs:**
  605. - `https://x.com/<user>/status/<id>`
  606. - `https://twitter.com/<user>/status/<id>`
  607. - `https://x.com/i/article/<id>`
  608. **Authentication:** Uses environment variables (`X_AUTH_TOKEN`, `X_CT0`) or Chrome login for cookie-based auth.
  609. #### canghe-compress-image
  610. Compress images to reduce file size while maintaining quality.
  611. ```bash
  612. /canghe-compress-image path/to/image.png
  613. /canghe-compress-image path/to/images/ --quality 80
  614. ```
  615. #### canghe-format-markdown
  616. Format plain text or markdown files with proper frontmatter, titles, summaries, headings, bold, lists, and code blocks.
  617. ```bash
  618. # Format a markdown file
  619. /canghe-format-markdown path/to/article.md
  620. # Format with specific output
  621. /canghe-format-markdown path/to/draft.md
  622. ```
  623. **Workflow**:
  624. 1. Read source file and analyze content structure
  625. 2. Check/create YAML frontmatter (title, slug, summary, coverImage)
  626. 3. Handle title: use existing, extract from H1, or generate candidates
  627. 4. Apply formatting: headings, bold, lists, code blocks, quotes
  628. 5. Save to `{filename}-formatted.md`
  629. 6. Run typography script: ASCII→fullwidth quotes, CJK spacing, autocorrect
  630. **Frontmatter Fields**:
  631. | Field | Processing |
  632. |-------|------------|
  633. | `title` | Use existing, extract H1, or generate candidates |
  634. | `slug` | Infer from file path or generate from title |
  635. | `summary` | Generate engaging summary (100-150 chars) |
  636. | `coverImage` | Check for `imgs/cover.png` in same directory |
  637. **Formatting Rules**:
  638. | Element | Format |
  639. |---------|--------|
  640. | Titles | `#`, `##`, `###` hierarchy |
  641. | Key points | `**bold**` |
  642. | Parallel items | `-` unordered or `1.` ordered lists |
  643. | Code/commands | `` `inline` `` or ` ```block``` ` |
  644. | Quotes | `>` blockquote |
  645. #### canghe-markdown-to-html
  646. Converts Markdown files to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, and infographics.
  647. ```bash
  648. # Basic conversion (uses default theme)
  649. /canghe-markdown-to-html article.md
  650. # With specific theme (default, grace, simple)
  651. /canghe-markdown-to-html article.md --theme grace
  652. ```
  653. #### find-skills
  654. A discovery helper for the agent-skills ecosystem. It maps user goals to searchable keywords, finds candidate skills with `npx skills`, and suggests concrete install commands.
  655. #### obsidian-skills
  656. An Obsidian-focused skill bundle for knowledge-work workflows, combining note authoring, structured views, and canvas-based organization in one package.
  657. #### obsidian-bases
  658. Build and maintain Obsidian Bases (`.base`) with reliable YAML structure, including multi-view setups, filter logic, computed formulas, and summary fields.
  659. #### obsidian-markdown
  660. Work with Obsidian Flavored Markdown safely: wikilinks, embeds, callouts, metadata/frontmatter, tags, and other vault-native syntax conventions.
  661. #### remotion-best-practices
  662. A rule-driven reference set for building Remotion videos in React, with patterns for timing, composition design, captions, transitions, assets, and rendering quality.
  663. #### skill-creator
  664. Methodology for designing and iterating skills: compact SKILL.md writing, progressive-loading structure, and clean separation of scripts, references, and assets.
  665. #### canghe-volcengine-video-understanding
  666. Volcengine video understanding - analyzes video content using Volcengine Ark video understanding API. Uploads videos via Files API (recommended, up to 512MB), supports video content analysis, object recognition, action understanding, etc.
  667. ```bash
  668. # Basic video analysis
  669. /canghe-volcengine-video-understanding /path/to/video.mp4 "Describe the content of this video"
  670. # Video Q&A
  671. /canghe-volcengine-video-understanding /path/to/video.mp4 "What characters appear in the video?"
  672. # Emotion analysis
  673. /canghe-volcengine-video-understanding /path/to/video.mp4 "Analyze the emotional changes of the characters in the video"
  674. # Specify model and FPS
  675. /canghe-volcengine-video-understanding /path/to/video.mp4 "Summarize the key points of the video" --model doubao-seed-2-0-pro-260215 --fps 2
  676. ```
  677. **Supported Models**:
  678. - `doubao-seed-2-0-pro-260215` (default)
  679. - `doubao-seed-2-0-lite-250728`
  680. - `doubao-seed-1-6-251015`
  681. **Key Features**:
  682. - Upload videos up to 512MB via Files API
  683. - Video content analysis, scene/character/action recognition
  684. - Video Q&A based on content
  685. - Automatic video description and summary generation
  686. - Files stored for 7 days for reuse
  687. #### canghe-douyin-downloader
  688. Douyin (TikTok China) video downloader and transcript extractor. Downloads watermark-free videos and extracts speech-to-text transcripts.
  689. ```bash
  690. # Get video info
  691. /canghe-douyin-downloader info "抖音分享链接"
  692. # Download video
  693. /canghe-douyin-downloader download "抖音链接" -o ./videos
  694. # Extract transcript (requires API Key)
  695. /canghe-douyin-downloader extract "抖音链接" -o ./output
  696. ```
  697. **Environment Variables**:
  698. | Variable | Description |
  699. |----------|-------------|
  700. | `DOUYIN_API_KEY` | SiliconFlow API key for speech-to-text |
  701. **Requirements**: `ffmpeg`
  702. #### paddleocr-doc-parsing
  703. Advanced document parsing with PaddleOCR. Extracts complete document structure including text, tables, formulas, charts, and layout information.
  704. ```bash
  705. # Parse from URL
  706. /paddleocr-doc-parsing --file-url "https://example.com/doc.pdf" --pretty
  707. # Parse local file
  708. /paddleocr-doc-parsing --file-path "document.pdf" --pretty
  709. # Specify file type
  710. /paddleocr-doc-parsing --file-url "URL" --file-type 0 --pretty
  711. ```
  712. **File Types**: `0` (PDF), `1` (image), or auto-detected
  713. **Environment Variables**:
  714. | Variable | Description |
  715. |----------|-------------|
  716. | `PADDLEOCR_DOC_PARSING_API_URL` | PaddleOCR API endpoint |
  717. | `PADDLEOCR_ACCESS_TOKEN` | API access token |
  718. **Requirements**: `python`
  719. #### Skill Provenance and Personal Repos
  720. Many skills in this repository are adapted from BaoYu's skill work and then refined for local workflows, tooling, and prompt styles. Source repository: [https://github.com/JimLiu/baoyu-skills](https://github.com/JimLiu/baoyu-skills).
  721. The practical recommendation is to keep a personal skills repository: each person can version their own conventions, templates, scripts, and domain-specific defaults instead of relying on one shared baseline forever.
  722. ## Environment Configuration
  723. Some skills require API keys or custom configuration. Environment variables can be set in `.env` files:
  724. **Load Priority** (higher priority overrides lower):
  725. 1. CLI environment variables (e.g., `OPENAI_API_KEY=xxx /canghe-image-gen ...`)
  726. 2. `process.env` (system environment)
  727. 3. `<cwd>/.canghe-skills/.env` (project-level)
  728. 4. `~/.canghe-skills/.env` (user-level)
  729. **Setup**:
  730. ```bash
  731. # Create user-level config directory
  732. mkdir -p ~/.canghe-skills
  733. # Create .env file
  734. cat > ~/.canghe-skills/.env << 'EOF'
  735. # OpenAI
  736. OPENAI_API_KEY=sk-xxx
  737. OPENAI_IMAGE_MODEL=gpt-image-1.5
  738. # OPENAI_BASE_URL=https://api.openai.com/v1
  739. # Google
  740. GOOGLE_API_KEY=xxx
  741. GOOGLE_IMAGE_MODEL=gemini-3-pro-image-preview
  742. # GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta
  743. # DashScope (Aliyun Tongyi Wanxiang)
  744. DASHSCOPE_API_KEY=sk-xxx
  745. DASHSCOPE_IMAGE_MODEL=z-image-turbo
  746. # DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
  747. EOF
  748. ```
  749. **Project-level config** (for team sharing):
  750. ```bash
  751. mkdir -p .canghe-skills
  752. # Add .canghe-skills/.env to .gitignore to avoid committing secrets
  753. echo ".canghe-skills/.env" >> .gitignore
  754. ```
  755. ## Customization
  756. All skills support customization via `EXTEND.md` files. Create an extension file to override default styles, add custom configurations, or define your own presets.
  757. **Extension paths** (checked in priority order):
  758. 1. `.canghe-skills/<skill-name>/EXTEND.md` - Project-level (for team/project-specific settings)
  759. 2. `~/.canghe-skills/<skill-name>/EXTEND.md` - User-level (for personal preferences)
  760. **Example**: To customize `canghe-cover-image` with your brand colors:
  761. ```bash
  762. mkdir -p .canghe-skills/canghe-cover-image
  763. ```
  764. Then create `.canghe-skills/canghe-cover-image/EXTEND.md`:
  765. ```markdown
  766. ## Custom Palettes
  767. ### corporate-tech
  768. - Primary colors: #1a73e8, #4A90D9
  769. - Background: #F5F7FA
  770. - Accent colors: #00B4D8, #48CAE4
  771. - Decorative hints: Clean lines, subtle gradients
  772. - Best for: SaaS, enterprise, technical
  773. ```
  774. The extension content will be loaded before skill execution and override defaults.
  775. ## Disclaimer
  776. ### canghe-danger-gemini-web
  777. This skill uses the Gemini Web API (reverse-engineered).
  778. **Warning:** This project uses unofficial API access via browser cookies. Use at your own risk.
  779. - First run opens a browser to authenticate with Google
  780. - Cookies are cached for subsequent runs
  781. - No guarantees on API stability or availability
  782. **Supported browsers** (auto-detected): Google Chrome, Chrome Canary/Beta, Chromium, Microsoft Edge
  783. **Proxy configuration**: If you need a proxy to access Google services (e.g., in China), set environment variables inline:
  784. ```bash
  785. HTTP_PROXY=http://127.0.0.1:7890 HTTPS_PROXY=http://127.0.0.1:7890 /canghe-danger-gemini-web "Hello"
  786. ```
  787. ### canghe-danger-x-to-markdown
  788. This skill uses a reverse-engineered X (Twitter) API.
  789. **Warning:** This is NOT an official API. Use at your own risk.
  790. - May break without notice if X changes their API
  791. - Account restrictions possible if API usage detected
  792. - First use requires consent acknowledgment
  793. - Authentication via environment variables or Chrome login
  794. ## License
  795. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

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