seedance-antislop
This skill strips hollow superlatives and bloated adjectives from Seedance 2.0 prompts, replacing them with concrete production language—camera moves, light sources, motion, and sound cues that a crew can actually execute. It classifies filler into six patterns (empty evaluators, borrowed tokens, tag salad, negation slop, adjective stacking, and feel-suffix words) and rewrites each class with observable details that preserve the user's intent without the padding.
seedance-antislop removes generic filler and vague language from video production prompts by replacing empty words with observable, production-specific details.
AI-generated summary based on this skill's SKILL.md
Install
Emily2040/seedance-2.0/seedance-antislop · repository language: Python
git clone https://github.com/Emily2040/seedance-2.0
cp -r seedance-2.0/skills/seedance-antislop ~/.claude/skills/seedance-antislopFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does seedance-antislop remove filler from video prompts?
seedance-antislop strips hollow superlatives and bloated adjectives from Seedance 2.0 prompts by replacing them with concrete production language—camera moves, light sources, motion, and sound cues that a crew can actually execute. The skill identifies six patterns of prompt slop (empty evaluators, borrowed tokens, tag salad, negation slop, adjective stacking, and feel-suffix words) and rewrites each class with observable details while preserving your creative intent.
What types of prompt slop does seedance-antislop classify and repair?
seedance-antislop systematically handles six types of prompt slop: empty evaluators (vague praise words), borrowed tokens (generic AI phrases), tag salad (unstructured keyword dumps), negation slop (what to avoid rather than what to do), adjective stacking (piled-on descriptors), and feel-suffix words (abstract emotional language). Each type gets converted to production-specific, visually concrete language.
Can seedance-antislop convert bloated adjectives to camera language?
Yes. seedance-antislop converts bloated adjectives to observable camera, light, and motion details. Instead of 'epic' or 'beautiful,' it rewrites prompts with specifics: lens choice, depth of field, lighting angle, camera speed, or texture. This makes prompts production-ready and executable by crews who need to know exactly what to shoot, not how it should feel.
How does seedance-antislop improve Seedance 2.0 prompt quality?
seedance-antislop tightens Seedance 2.0 prompt quality by eliminating generic filler and vague language that wastes tokens and confuses AI models. It replaces tag salad, empty evaluators, and negation slop with concrete production terms. The result: sharper prompts that preserve creative intent while using language a video crew can actually execute.
Does seedance-antislop preserve creative intent while editing?
Yes. seedance-antislop preserves your creative intent while tightening production-ready language. It doesn't strip meaning—it translates it. Vague emotional language becomes specific visual and technical direction. Your vision stays intact; only the padding disappears.
What license does seedance-antislop use?
seedance-antislop is released under the MIT license, allowing free use, modification, and distribution in both open-source and commercial projects.
SKILL.md
rendered from the published skill — quoted content, verbatim
seedance-antislop
Remove filler that hides missing visual decisions. A strong Seedance prompt uses observable nouns, verbs, camera moves, light sources, sound cues, and constraints. A weak prompt asks for excellence without saying what excellence looks or sounds like.
Intent
Users reach for giant empty words precisely because they care intensely and don't know where to put it. The soul of de-slopping is conservation: every deleted "epic" must come back as a visible choice that holds the same caring. Strip a prompt without honoring the feeling that bloated it, and the user hears
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/seedance-antislop/SKILL.md