seedance-examples-ko

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

Quality

75%

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-ko/SKILL.md

Quality

Content

72%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 concise and highly actionable, with copy-paste Korean prompt templates and concrete rewrite guidance. Its weaknesses are implicit rather than explicit validation checkpoints in the workflow, and two referenced files that are not present in the bundle.

Suggestions

Make the workflow's validation checkpoint explicit, e.g. add a step that says 'label the example (safe / rewrite-required) and attach a risk note before returning output, then provide a safer variant if needed'.

Add the missing referenced files (references/directors-read.md and references/multilingual-native-review.md) to the bundle, or remove the links and inline the essential guidance so no reference is broken.

Optionally surface a one-line 'steps' summary (load reference -> classify brief -> write labeled example -> return with risk note) so the sequence is scannable before the prose.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned with no padding or explanation of basic concepts, and it assumes Claude's competence; the dense opening paragraph could be tightened slightly, so it sits just below the top anchor.	4 / 5
Actionability	It provides copy-paste-ready Korean prompt blocks across six common cases (Product I2V, Melodrama, Sequence, Continuation, Dialogue, Textless) plus concrete before/after rewrite pairs and an explicit output contract, fully covering the common cases.	5 / 5
Workflow Clarity	The opening paragraph lays out a sequence (load the Director's Read, classify the brief, complete the record, translate to carriers), but validation checkpoints are only implicit via the labeling scheme rather than explicit 'validate then proceed' steps.	3 / 5
Progressive Disclosure	Sections are well-organized and references are clearly signaled and one level deep, but both referenced files (directors-read.md, multilingual-native-review.md) do not exist in the bundle, so the navigation structure is incomplete.	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 is specific, well-triggered, and clearly occupies a distinct niche, with concrete deliverables and natural user-facing trigger phrases. Its only weakness is that the 'what' is expressed as a noun list rather than an explicit action statement, keeping it just below the top anchor on completeness and specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete deliverables ('Korean Seedance 2.0 examples, Korean prompt patterns, example rewrites, or safe versions of working Korean video-generation prompts'), but they are nouns rather than explicit action verbs, leaving a minor gap versus a fully comprehensive action list.	4 / 5
Completeness	It explicitly answers 'when' ('This skill should be used when the user asks for...') and conveys 'what' through the deliverable list, but the 'what' is implied rather than stated as a distinct action, so it falls just short of a fully explicit what-and-when pair.	4 / 5
Trigger Term Quality	The triggers ('Korean Seedance 2.0 examples', 'Korean prompt patterns', 'example rewrites', 'safe versions of working Korean video-generation prompts') are natural phrases a user would say with good synonym coverage; a few common variations are missing.	4 / 5
Distinctiveness Conflict Risk	The narrow niche (Korean + Seedance 2.0 + video-generation prompts) with distinct, specific triggers gives it 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: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-examples-ko/SKILL.md
Commit: 44b5149

Reviewed: 19 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.