seedance-vocab-ja

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

Quality

76%

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-ja/SKILL.md

Quality

Content

75%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.

A lean, well-structured instruction-only skill with concrete Japanese wording guidance, a usable compact template, and clear conditional rules. The main weaknesses are the absence of a final validation/verification step and external references that are not bundled within the skill.

Suggestions

Add an explicit verification step in the Output Contract (e.g., confirm reference tags @Image1/@Video1/@Audio1 are intact and a register was declared when dialogue is present) to close the workflow with a validation checkpoint.

Move the mora-cost aside and the 'shipped independent review artifact is empty' commentary out of the core flow or into the referenced vocabulary file to tighten conciseness toward a 5.

Either bundle the referenced files (directors-read.md, vocab/ja.md) one level deep inside the skill's references/ directory, or note explicitly that they live in the parent bundle, so the references resolve within the skill.

Dimension	Reasoning	Score
Conciseness	The ~37-line body is dense and assumes Claude's intelligence with no concept padding, but minor asides (the mora-cost example 'ありがとう 5 → ありがとうございます 10' and the 'shipped independent review artifact is empty' note) keep it just below a pristine 5.	4 / 5
Actionability	Provides a ready-to-fill Compact Pattern template, concrete Japanese vocabulary per function, explicit register options, and specific de-slop decomposition rules, but the template uses bracketed placeholders requiring substitution rather than being fully literal/copy-paste-ready.	4 / 5
Workflow Clarity	A clear sequence (load Director's Read → classify → complete record → translate → strip labels) with explicit conditional checkpoints in the Register and De-Slop rules, though no explicit final validation or error-recovery feedback loop is present.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled references to specific anchors (文体 table, Slop Traps table), but no bundle files exist under references/scripts/assets and the referenced '../../references/...' paths resolve outside the skill bundle rather than to bundled one-level-deep files.	4 / 5
	Total	16 / 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.

A strong, specific description that explicitly answers both what the skill does and when to use it, with a clear niche that minimizes conflict risk. The only gap is that the 'what' relies on a single action verb across many term categories rather than multiple distinct actions.

Suggestions

Lead with one or two additional distinct action verbs (e.g., 'compose', 'rewrite', 'localize') so the 'what' reads as multiple concrete actions rather than one verb over a noun list.

Add a couple of natural synonyms a user might actually say (e.g., 'Japanese prompts', '映像用語', 'video-generation wording') to broaden trigger coverage.

Tighten the term list by grouping (e.g., 'camera, lighting, motion, VFX, and audio production terms') to reduce repetition of 'Japanese' without losing specificity.

Dimension	Reasoning	Score
Specificity	Names the Japanese Seedance 2.0 domain and enumerates several concrete term categories (camera, lighting, action, VFX, audio, production), though 'translation' is the single action verb applied across noun categories rather than multiple distinct actions.	4 / 5
Completeness	Explicitly states both what (Japanese prompt wording / cinematic vocabulary / translation of production terms) and when ('This skill should be used when the user asks for…') with concrete trigger phrases, sitting just below the 5 anchor whose 'what' lists multiple distinct actions.	4 / 5
Trigger Term Quality	Uses natural phrasing ('when the user asks for…') with good keyword coverage including the product name and many production-domain terms, but lacks common synonyms or simpler variations a user might say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Japanese + Seedance 2.0 + cinematic/production vocabulary) with distinct, 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: 3 suspicious	Warning

	Total	13 / 16 Passed

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

Reviewed: 28 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.