seedance-examples-ja

This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/seedance-examples-ja/SKILL.md

Quality

Content

82%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 compact, highly actionable instruction skill with concrete Japanese prompt templates, a clear rewrite/labeling workflow, and well-signaled external references. Minor room to tighten the Intent paragraph and make workflow checkpoints explicit rather than implicit.

Suggestions

Tighten or remove the 'Intent' paragraph; its guidance is already implied by the concrete patterns that follow.

Restate the production workflow as a short numbered list with an explicit validation checkpoint (e.g., 'run multilingual-native-review before emitting the final prompt') so the sequence and feedback loop are unambiguous.

Confirm the ../../references/ paths resolve from the skill's installed location, or move the referenced material into a local references/ directory so the links are verifiable within the bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with dense concrete example patterns earning their tokens; the only trimming candidate is the slightly atmospheric 'Intent' paragraph ('should feel like production notes a Japanese creator could actually use: polite where helpful...').	4 / 5
Actionability	It provides six copy-paste-ready Japanese prompt templates (product I2V, portrait, sequence, continuation, dialogue, textless localization) plus a concrete before/after rewrite pattern and a label taxonomy, covering the common cases with executable guidance.	5 / 5
Workflow Clarity	A clear sequence is given in the intro (load the Director's Read, classify the brief, complete the canonical record, translate to carriers, keep labels out) with a conditional rewrite branch and an output contract; checkpoints are present but mostly implicit rather than enumerated as numbered validation steps.	4 / 5
Progressive Disclosure	The body is a well-organized overview with clearly signaled one-level references ([Director's Read], [multilingual language review]) for deeper supporting material, and the examples correctly live inline; the references resolve outside the bundle (../../references/) and cannot be verified against this skill's files, keeping it just short of a 5.	4 / 5
	Total	17 / 20 Passed

Description

73%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 tightly scoped, well-triggered description for a niche skill, with explicit 'when' guidance and low conflict risk. Its main weakness is that the capability is expressed as deliverable nouns rather than concrete action verbs, leaving the 'what' implicit.

Suggestions

Lead with an explicit action verb for the 'what' (e.g., 'Generates Japanese Seedance 2.0 prompt examples, rewrites, and safe variants...') before the 'Use when' clause.

Add a couple of natural synonym variants users might say (e.g., 'Japanese video prompts', 'Seedance prompts in Japanese') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Japanese Seedance 2.0 video-generation prompts) and concrete deliverables ('examples, Japanese prompt patterns, example rewrites, or safe versions'), but frames them as nouns under a trigger clause rather than as explicit action verbs, leaving the 'what' only weakly stated.	3 / 5
Completeness	The 'when' is explicit and concrete ('This skill should be used when the user asks for...'), satisfying the Use-when requirement; the 'what' is only implied (provide those deliverables) rather than stated as a clear action, so it stops short of a 5.	4 / 5
Trigger Term Quality	It surfaces natural phrases a user would say ('Japanese Seedance 2.0 examples', 'Japanese prompt patterns', 'example rewrites', 'safe versions', 'Japanese video-generation prompts'), with good synonym coverage, though a few natural variants are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a narrow, distinct niche (Japanese Seedance 2.0 prompt examples/rewrites) with triggers unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	16 / 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: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-examples-ja/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.