seedance-vocab-zh

This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/seedance-vocab-zh/SKILL.md

Quality

Content

71%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 body is lean, well-sectioned, and actionable, with a strong inlined vocabulary table and a compact pattern template. Its main weakness is progressive disclosure: multiple rules depend on reference files that are not present in the bundle.

Suggestions

Bundle the referenced files (references/directors-read.md and references/vocab/zh.md), or inline the Script Variant and Slop Traps tables, so the 'load …' rules are executable without external files.

Fix the reference paths: ../../references/ escapes the skill bundle; use a sibling references/ directory so navigation works from SKILL.md.

Move the 'shipped independent review artifact is empty' note out of the Intent section — it is review-process meta-commentary, not prompt-production guidance.

Dimension	Reasoning	Score
Conciseness	Lean and dense with a high-value vocabulary table and concrete rules, but the aside 'The shipped independent review artifact is empty, so treat these choices as working production wording pending locale-specialist review' is tangential meta-commentary that could be trimmed.	4 / 5
Actionability	Provides directly usable Chinese phrases, a fill-in compact pattern template, and concrete rules (preserve @Image1/@Video1/@Audio1; 头发 → 頭髮, not 頭發), but several rules depend on loading referenced files (vocab/zh.md) that are not present in the bundle.	4 / 5
Workflow Clarity	A coherent sequence is present in prose ('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' → Output Contract), but it is not a clean numbered list and has no checkpoints; acceptable for a simple single-purpose wording skill.	4 / 5
Progressive Disclosure	Sections are well-organized and references are clearly signaled as one-level-deep markdown links, but the referenced files (../../references/directors-read.md, ../../references/vocab/zh.md) are absent from the bundle and use unusual ../../ paths that escape the skill folder, breaking actual navigation.	3 / 5
	Total	15 / 20 Passed

Description

78%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 targets a clear, distinctive niche with strong natural trigger phrases and an explicit use-when clause. Its main weakness is that the 'what' is implicit within the trigger list rather than stated declaratively.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities ('Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese') but frames them as triggers ('asks for') rather than crisp performed actions, leaving minor gaps.	4 / 5
Completeness	The 'when' is explicit and strong ('This skill should be used when the user asks for...'), but the 'what' is only implicit, folded into the trigger list rather than a distinct declarative statement as in the 5 anchor.	4 / 5
Trigger Term Quality	Natural keywords like 'Chinese Seedance 2.0 prompt wording', 'Mandarin cinematic vocabulary', and the production-term list match what a user would say, and synonyms are present (Chinese/Mandarin), though a few natural phrasings (e.g. 'subtitles', 'bilingual prompt') are missing.	4 / 5
Distinctiveness Conflict Risk	A clear narrow niche (Chinese/Mandarin Seedance 2.0 cinematic prompts) with highly specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: 4 suspicious	Warning

	Total	13 / 16 Passed

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

Reviewed: 27 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.