// AI-generated greeting cards as PNG images. Triggers: greeting card, 贺卡, mofa card, mofa 贺卡, make a card, CNY card, New Year card, 新年贺卡, ink-wash card. Generates full-bleed AI artwork via Gemini in various Chinese art styles.
Shared CLI binary for all mofa skills (slides, cards, comic, infographic, video). Not a user-facing skill.
AI-generated comic strips and illustrations. Triggers: comic, manga, xkcd, 漫画, comic strip, 四格漫画, panel comic, illustration strip, snoopy. Generates multi-panel comics via Gemini with optional Qwen-Edit refinement, stitched into a single image.
AI-generated infographics and visual posters. Triggers: infographic, poster, 信息图, 海报, data poster, visual summary, mofa infographic. Generates multi-section infographic via Gemini with optional Qwen-Edit refinement, stitched into a single tall image.
AI-generated visual presentations with full-bleed Gemini images. Triggers: mofa, mofa ppt, mofa deck, slides, 幻灯片, generative slides, build a mofa ppt, 用mofa做PPT, AI deck, 做个PPT, make slides.
Deploy static sites to GitHub Pages or Mac Mini hosting. Triggers: mofa publish, deploy site, publish website, 发布网站, 部署网页, github pages, deploy to mini, host website, 上线, push to pages, mofa deploy, 发布到GitHub.
Multi-speaker podcast and dialogue generation with TTS voice cloning. Triggers: podcast, 播客, multi-speaker audio, 多人对话, 多人语音, radio show, talk show, 对话生成, 锵锵三人行, 两人对话, 三人对话, voice dialogue, 用XX的声音, 用XX和XX的风格, 声音模仿, 角色对话, 配音.
| name | mofa-cards |
| version | 0.4.5 |
| description | AI-generated greeting cards as PNG images. Triggers: greeting card, 贺卡, mofa card, mofa 贺卡, make a card, CNY card, New Year card, 新年贺卡, ink-wash card. Generates full-bleed AI artwork via Gemini in various Chinese art styles. |
| requires_bins | mofa |
| requires_env | GEMINI_API_KEY |
Generate AI-powered greeting / holiday cards as PNG images (full-bleed Gemini artwork in 8 Chinese art styles plus inline custom prompts).
mofa cardsstyles/*.toml (8 built-in + 7 t-shirt variants)mofa/config.jsonThe mofa_cards tool is spawn_only — generation runs in the background and
images are delivered when ready. Do NOT wait inside the agent loop.
ALWAYS use a relative path under skill-output/ with a unique per-request
subdirectory:
skill-output/mofa-cards-<YYYYMMDD-HHMMSS>/
NEVER use absolute paths like /tmp/cards/ or /Users/.../Desktop/. The
session scope rejects writes outside skill-output/.
Verify GEMINI_API_KEY is set before calling the tool. If unset, ask the user
to export it — the tool will fail otherwise.
Before generating, gather: occasion, style, card count (typically 1-3), aspect
ratio (default 9:16). On Telegram, use an inline keyboard for style picks.
Recommend a style based on occasion — see docs/styles.md.
You are NOT limited to built-in styles. Write a full style description directly
in the card's prompt field; pick any built-in --style as a layout base. See
docs/styles.md for trigger-phrase → snippet recipes.
Each card is ~15-30s; tool timeout is 600s. If generation times out, cached
cards are preserved — rerun and only missing cards regenerate. See
docs/examples.md for the timing table.
docs/styles.mddocs/examples.mdmofa/config.json keys → docs/cli-flags.mdstyles/*.toml