seedance-vocab-en

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.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean and highly actionable, with concrete wording tables, slop-strip lists, and filter-trip repair pairs plus a compact output template. Its main weakness is mild philosophical padding in the Intent section and implicit rather than explicit validation checkpoints.

Suggestions

Tighten the Intent section: replace editorializing like "the soul of this vocabulary is precision as kindness" and "where most prompts quietly rot" with a one-line purpose statement.

Add an explicit validation/verification checkpoint in the workflow (e.g., before the Output Contract, confirm each slop term was replaced with an observable detail and reference tags are unchanged).

Confirm the referenced files (directors-read.md, vocab/en.md, anti-slop-lexicon.md, filter-vocab.md) resolve in the deployed bundle, since no references/ directory is present here.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with a compact wording table, de-slop list, and copy-ready pattern template, but the philosophical Intent framing ("the soul of this vocabulary is precision as kindness", "where most prompts quietly rot") adds editorializing that could be trimmed.	4 / 5
Actionability	Highly actionable: a concrete function-to-wording table, an explicit slop-word strip list with replacement guidance, before/after filter-trip synonym pairs, and a fill-in compact pattern template — all copy-paste ready and covering common cases.	5 / 5
Workflow Clarity	A clear sequence is given up front (load Director's Read, classify, complete record, translate to carriers) followed by de-slop, filter-aware, compact pattern, and an Output Contract that functions as a checklist; validation is implicit rather than an explicit checkpoint, leaving a minor gap.	4 / 5
Progressive Disclosure	The body is a well-sectioned overview that keeps core rules inline and clearly signals one-level-deep references (Director's Read, vocab/en.md, anti-slop-lexicon.md, filter-vocab.md, seedance-filter), with content appropriately split; no bundle files are present in this review directory to verify against.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it explicitly states both when to use the skill and what it provides, with concrete vocabulary domains and natural trigger phrasing. It uses appropriate third-person voice and stays specific rather than vague.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas — "precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints" — alongside specific trigger conditions (slop-heavy, padded with empty quality words, tripping false-positive filters), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both: the "when" via "This skill should be used when an English Seedance 2.0 prompt is slop-heavy..." and the "what" via the enumerated vocabulary domains, with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with natural domain phrasing like "slop-heavy", "padded with empty quality words", and "tripping false-positive filters", though some terms lean toward jargon and a few common user phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	A clear, narrow niche (English Seedance 2.0 prompt vocabulary, anti-slop, filter-aware wording) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	13 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-vocab-en/SKILL.md
Commit: 44b5149

Reviewed: 29 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.