Menu
TTS and voice cloning. Triggers: voice, TTS, text to speech, 语音, 播报, read aloud.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
Build or scaffold websites from content using Quarto, Astro, Next.js, or React/Vite. Triggers: mofa site, build website, make a website, 建网站, 做个网站, generate site, mofa web, create website, 生成网页, build lesson site, build docs site, 做个教程网站.
Shared CLI binary for all mofa skills (slides, cards, comic, infographic, video). Not a user-facing skill.
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.
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.
| name | mofa-fm |
| description | TTS and voice cloning. Triggers: voice, TTS, text to speech, 语音, 播报, read aloud. |
One-line: synthesize speech (preset or cloned voices) via the local
ominix-api server. Background-spawning — call fm_tts directly with the
full text and the audio file is delivered automatically.
Do NOT call fm_voice_list as a precheck before fm_tts or before
podcast generation. fm_voice_list is a recovery and explicit-listing
tool, not a TTS prerequisite. If a user names a voice you do not
recognise, call fm_tts directly with that voice — the error path is
short and recoverable, and a preemptive catalog dump wastes a turn and
can prevent the actual TTS call from happening.
Call fm_voice_list only when:
fm_tts or podcast generation returns Unknown voice 'NAME',
Voice not found, or an equivalent unavailable-voice error.Do NOT use spawn, shell scripts, or manual text splitting around
fm_tts. The tool is spawn_only — call it once with the full text.
Do NOT use fm_tts for podcasts. Use podcast_generate from
mofa-podcast instead.
vivian. Other presets and custom-voice save / list /
delete behaviour are documented in docs/full-guide.md.prompt argument): leave empty for natural
content-aware tone; set it to override with a consistent style — see
the table in docs/full-guide.md.fm_voice_save (3-10s clear-speech clip),
then pass the same name as fm_tts's voice argument. Local-only
save — no server round-trip at save time.