agentleFS
Sign inStart free
381487190381487190/opengod/skills/seedance/seedance-antislop/SKILL.md

seedance-antislop

Skill0 starsChanged 3 months agoMITView on GitHub

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Remove filler that hides missing visual decisions.

    line 23
  2. Distinctive:

    Every major phrase should be visible to a camera, measurable by a light meter, audible in the mix, or observable as motion.

    line 31
  3. Very specific:

    Do not remove useful genre language when it is paired with concrete direction.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 that their excitement was wrong.

Visibility Test

Every major phrase should be visible to a camera, measurable by a light meter, audible in the mix, or observable as motion. If a phrase cannot pass that test, replace it with production language.

FillerAsk what it meansStrong replacement pattern
cinematicWhat camera and light make it cinematic?locked close-up, warm practical key, cool rim light
epicWhat is the scale or stake?wide low-angle shot, tiny figure against storm wall
beautifulWhat color, texture, or light behavior?pearl highlights on wet ceramic, soft window bounce
dynamicWhat moves, how fast, and where does it end?fast lateral track ending on the hero label
professionalWhat production setup?clean commercial tabletop, controlled reflection, no clutter

The Six Slop Classes

Classify before rewriting - each class has a different repair:

  1. Empty evaluators (cinematic, epic, stunning) - convert each to the one observable detail that earns it.
  2. Borrowed image-model tokens (8K, masterpiece, trending on ArtStation) - delete; quality and resolution are settings, not prose.
  3. Tag salad (comma keyword dumps ported from image prompting) - rewrite as shooting-brief prose: one sentence per element, with an action and a time axis.
  4. Negation slop (no blur, no artifacts, no extra fingers) - negation summons; describe what IS there instead, and keep negation only in the constraint slot.
  5. Adjective stacking (three synonyms for one quality) - pick the single detail that matters.
  6. Feel-suffix words (电影感, 雰囲気のある, 감성적인, atmosférico, атмосферный, vibey) - name the physical cause of the feeling; every language file in references/vocab/ has a Slop Traps table for its own community's empty words.

Rewrite Pass

First, underline all superlatives and vague style labels and classify each by slop class. Second, decide whether each word should become camera, light, motion, material, sound, or constraint language. Third, reduce duplicates. Fourth, keep the prompt within the character budget and preserve reference tags.

Do Not Over-Correct

Do not remove useful genre language when it is paired with concrete direction. Noir hallway with hard venetian-blind shadows is useful; dramatic cinematic noir vibes is not. Keep terms that communicate medium, era, palette, or lens behavior.

Load [ref:anti-slop-lexicon] for the slop-class taxonomy and extended replacement table, and [skill:seedance-vocab-en] with references/vocab/en.md for the full function-organized English precision vocabulary. For non-English prompts, load the matching vocab file's Slop Traps table (references/vocab/zh.md, ja.md, ko.md, es.md, ru.md) - each language community has its own empty-quality words and decompositions.

Output Contract

Return removed words, replacements grouped by camera/light/motion/sound/constraint, and the tightened prompt.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free