SkillCDN Pack
Your marketer, designer and developer in the AI you already use, making the short ad, the card news, the deck, the web app and the meeting minutes itself, checked before you see them. docs/pack/finding-a-skill.md says how to find a skill.
https://skillcdn.ai/gh/skillcdn/skillsConnect this address to your AI to use these skills. How to connect
- Repository
skillcdn/skills - Default branch
main - Commit
9e3fd2c - License
MIT - Searchwords and meaning
Explore this repository
Searches the original text of skills and documents by words and by meaning; display translations are not searched.
The skills that drive Higgsfield (higgsfield-…, in any area) share how the tools behave, how credits are quoted, how models and images are found, how a take is decoded, and what the video models do w…
Documents
- Higgsfield: what its skills shareThe skills that drive Higgsfield (higgsfield-…, in any area) share how the tools behave, how credits are quoted, how models and images are found, how a take is decoded, and what the video models do w…docs/higgsfield/README.md
- Portraits and first framesEvery person in a Higgsfield video has an approved portrait, and every generated shot an approved still first frame. The portrait keeps a face the same from shot to shot and from run to run; the fram…docs/higgsfield/cast.md
- Decoding a takeWhat a take says is settled by machine before anyone asks whether it matters: two plain speech-to-text decodes, a third to break a tie, word probabilities, a loudness envelope and a contact sheet. Th…docs/higgsfield/decodes.md
- Models, tiers and creditsHow a Higgsfield skill finds the models it needs in the catalog at run time, locks the lowest tier, quotes every credit before spending it, and handles what the server answers instead of a job. A ski…docs/higgsfield/models.md
- Pronunciation: what the video models do with soundsVideo models with native dialogue have no pronunciation dictionary, and a transcript often cannot show the fault. This file is the knowledge, per language, gathered from real runs of every Higgsfield…docs/higgsfield/pronunciation.md
- The sandboxsandbox_exec is a Linux box with ffmpeg, sox, ImageMagick, Pillow, faster-whisper, Playwright with headless Chromium, curl and two Latin caption fonts, where a Higgsfield skill reads frames, decodes…docs/higgsfield/sandbox.md