By rancheng
Generate or edit images by invoking OpenAI's gpt-image-2 ("image 2") through headless `codex exec`. Triggers on requests to create logos, icons, illustrations, banners, sprite sheets, or to transform a reference image.
Generate or edit images by invoking OpenAI's gpt-image-2 ("image 2") through headless `codex exec`. Trigger when the user asks to create, generate, draw, design, or edit an image, logo, icon, illustration, banner, sprite sheet, placeholder art, or any visual asset — and they have not specified a different generator (Stable Diffusion, Midjourney, DALL·E API directly, etc.). Also use when the user wants to transform or extend a reference image they have provided locally.
Generate short text-to-video clips via Aliyun DashScope's async video synthesis API (e.g. `happyhorse-1.0-t2v`, Wan series). Trigger when the user asks to create, generate, or make a video / animation / clip / 视频 from a text description — and they have not specified a different generator (Sora, Runway, Pika, Kling, Luma, etc.). Also trigger when the user mentions DashScope, 通义万相, 阿里视频生成, or `happyhorse` / Wan video models.
Export an HTML deck, slide page, or long web page to a faithful PDF by screenshotting each section with a real headless browser and stitching the frames into a one-slide-per-page PDF. Use this whenever a user wants a PDF of an HTML presentation/deck/slides/report and the page's own "Print to PDF" / @media print output is broken — wrong pagination, half-empty pages, missing video frames, or lost animated/interactive state. Especially for scroll-snap section decks, video-heavy pages, and canvas/JS-driven visuals.
A personal marketplace of Claude Code skills.
| Skill | What it does |
|---|---|
codex-imagegen | Generate or edit images via OpenAI's gpt-image-2 ("image 2") by invoking codex exec in headless mode. |
dashscope-videogen | Generate short text-to-video clips via Aliyun DashScope's async video synthesis API (happyhorse-1.0-t2v / Wan series). |
More to come.
In Claude Code:
/plugin marketplace add rancheng/my_claude_skills
/plugin install codex-imagegen@my-claude-skills
/plugin install dashscope-videogen@my-claude-skills
To pull updates later:
/plugin marketplace update my-claude-skills
/plugin)Each skill is a self-contained folder under skills/. You can drop one straight into your user-level skills directory:
git clone https://github.com/rancheng/my_claude_skills.git
cp -r my_claude_skills/skills/codex-imagegen ~/.claude/skills/
chmod +x ~/.claude/skills/codex-imagegen/*.sh
codex-imagegen — requires the Codex CLI on PATH and either codex login completed or OPENAI_API_KEY exported. Image generation consumes Codex usage credits (3–5× a normal turn).dashscope-videogen — requires a DashScope API key. On first use Claude will ask you for the key once and persist it to ~/.claude/skill-env/dashscope-videogen.env (chmod 600, outside any git repo). You can also export DASHSCOPE_API_KEY=sk-… in your shell. Video generation consumes Aliyun model credits..
├── .claude-plugin/
│ └── marketplace.json # plugin manifest consumed by Claude Code
├── skills/
│ └── <skill-name>/
│ ├── SKILL.md # frontmatter (name, description) + instructions
│ └── ... # any helper scripts the skill calls
├── scripts/
│ └── link-local.sh # symlink skills into ~/.claude/skills for live dev
├── DEVELOPMENT.md # how to add a new skill
└── README.md
See DEVELOPMENT.md.
MIT — see LICENSE.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub rancheng/my_claude_skills --plugin codex-imagegenUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.