powertokens-prompting
Write and fix prompts for PowerTokens video, image and voice models (Wan 3.0, Seedance 2.0/2.5, Kling v3, Seedream, MiniMax speech) — shot structure, camera language, timing, dialogue and audio cues, reference-image wording, and common failure fixes. Use whenever you write a prompt for any PowerTokens generation, when a result looks wrong (morphing, extra fingers, garbled text, wrong motion, drifting faces), or when the user asks for a cinematic, ad, UGC or short-drama look.
- Version
- 0.2.2
- License
- MIT
Pinned to revision b47b6c8917ff, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/powertokens-prompting/SKILL.md
- skills/powertokens-prompting/references/camera-language.md
- skills/powertokens-prompting/references/kling.md
- skills/powertokens-prompting/references/pitfalls.md
- skills/powertokens-prompting/references/seedance.md
- skills/powertokens-prompting/references/seedream.md
- skills/powertokens-prompting/references/speech.md
- skills/powertokens-prompting/references/timing-and-shots.md
- skills/powertokens-prompting/references/wan.md
Every link opens the file at its source, pinned to the revision this page describes.