About

Imported from emily2040/seedance-2.0 (skills/seedance-vocab-en/SKILL.md). Install upstream with npx skills add emily2040/seedance-2.0 --skill seedance-vocab-en. Copyright stays with the author (MIT).

seedance-vocab-en

Name: seedance-vocab-en
Author: emily2040

Before producing prompt text, a prompt-ready block, a rewrite, an example, or a compiled clip, load the Director's Read, classify the brief, and complete its canonical narrative or non-narrative record. Translate that record into visible or audible carriers and keep its internal labels out of final generation prose.

English is the default prompting language and fails in two ways at once: slop (empty evaluation words that add tokens and no signal) and false positives (vague threat-adjacent wording that trips the heaviest moderation surface). The cure for both is the same: concrete production English. Preserve reference tags exactly: @Image1, @Video1, @Audio1 must never be reworded.

Intent

English is where most users think, and where most prompts quietly rot. The soul of this vocabulary is precision as kindness: give people exact words so their excitement survives contact with the model, and so honest prompts stop being mistaken for dangerous ones.

Usage Rule

If a camera, microphone, light meter, or stopwatch cannot detect it, rewrite it. Every sentence should name something visible, audible, or measurable: subject, visible action, camera, light source, sound, constraint.

Function	English wording
Camera	`slow push-in`, `locked medium shot`, `stable lateral tracking`, `pull back to reveal`, `macro close-up`
Lighting	`soft backlight`, `warm practical light from the left`, `cool moonlight rim`, `wet asphalt reflecting neon`
Motion	`a slow head turn that stops`, `droplets merge and slide down`, `fabric settles after the gesture`
Audio	`quiet room tone`, `one clear spoken line in quotes`, `no music until after the line`
Constraints	`keep the logo, label, and shape unchanged`, `one action, one camera move`, `nothing else moves`

De-Slop Pass

Strip quality adjectives before adding anything: cinematic, epic, stunning, masterpiece, 8K, ultra-realistic, award-winning, hyper-detailed all delete or convert to one observable detail each. A prompt that earns "epic" names the crowd size, the lens distance, or the structure height instead of the word.

Filter-Aware Wording

English homonyms read as threats to filters: shoot the scene, kill the lights, gun it, dead silence, blow up the image. Use the production synonym (film the take, cut the lights to black, accelerate hard, held silence, enlarge to full frame). This is clarity for safe prompts only — never evasion. Anything genuinely risky (minors, real-person likeness, sexual or graphic content) routes to seedance-filter for its boundary rule, not to a rewording.

Compact Pattern

@Image1 is the reference; keep identity, color, and shape unchanged. Only [motion/light/camera] changes. Camera: [one move]. Sound: [one cue]. Constraints: [lock].

Load English vocabulary for the full function-organized vocabulary, slop traps, and filter-trip repairs. Load anti-slop-lexicon for the core replacement rule and filter-vocab for the full false-positive repair table.

Output Contract

Return the de-slopped English prompt, each replacement made (slop → observable detail), any filter-trip repair applied, and unchanged reference tags.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/emily2040-seedance-2-0-seedance-vocab-en/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

emily2040-seedance-2-0-seedance-vocab-en.ocm.jsonjson

{
  "ocm": "1",
  "id": "emily2040-seedance-2-0-seedance-vocab-en",
  "kind": "skill",
  "name": "seedance-vocab-en",
  "description": "This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.",
  "publisher": "emily2040",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "english",
      "vocabulary",
      "anti-slop",
      "seedance-20",
      "skills-sh"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "skills.sh",
      "repository": "https://github.com/emily2040/seedance-2.0",
      "path": "skills/seedance-vocab-en/SKILL.md",
      "ref": "HEAD",
      "url": "https://github.com/emily2040/seedance-2.0/blob/HEAD/skills/seedance-vocab-en/SKILL.md",
      "key": "emily2040/seedance-2.0/skills/seedance-vocab-en/SKILL.md"
    },
    "license": "MIT"
  },
  "instructions": "# seedance-vocab-en\n\nBefore producing prompt text, a prompt-ready block, a rewrite, an example, or a compiled clip, load the [Director's Read](../../references/directors-read.md), classify the brief, and complete its canonical narrative or non-narrative record. Translate that record into visible or audible carriers and keep its internal labels out of final generation prose.\n\nEnglish is the default prompting language and fails in two ways at once: slop (empty evaluation words that add tokens and no signal) and false positives (vague threat-adjacent wording that trips the heaviest moderation sur",
  "cost": {
    "context_tokens": 856
  }
}

Fetch it by URL: GET /api/v1/registry/emily2040-seedance-2-0-seedance-vocab-en/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.