CtrlK
BlogDocsLog inGet started
Tessl Logo

seedance-examples-zh

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

65

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/seedance-examples-zh/SKILL.md
SKILL.md
Quality
Evals
Security

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 content is highly actionable with concrete Chinese prompt examples and a clear output contract, but workflow clarity lacks explicit validation checkpoints and progressive disclosure relies on reference files that are not present in the bundle.

Suggestions

Add an explicit validation/review checkpoint (e.g., verify the canonical record is complete and labels are stripped before emitting final prose) with a fix-and-retry loop, since generation and rewriting are batch-like operations.

Either include the referenced references/directors-read.md and references/multilingual-native-review.md files in the bundle or inline the minimal content they require so navigation is not broken.

Tighten the 'Intent' section and framing sentences to reduce token overhead without losing the recognition-by-example guidance.

DimensionReasoningScore

Conciseness

The body is mostly lean with compact, production-oriented examples and little concept explanation, but the 'Intent' section and a few framing sentences could be trimmed; it is efficient rather than fully lean.

4 / 5

Actionability

It provides concrete, copy-paste-ready Chinese prompt examples across the common Seedance cases (product I2V, character drama, action, dialogue, first/last frame, R2V) plus explicit rewrite and output contracts, fully covering the common cases.

5 / 5

Workflow Clarity

A rough sequence exists (load Director's Read -> classify brief -> complete record -> translate -> review), but validation checkpoints are only implicit and there is no explicit verify/fix feedback loop for the rewrite and batch-generation operations.

3 / 5

Progressive Disclosure

Two references (directors-read.md, multilingual-native-review.md) are clearly signaled via inline links, but the referenced files do not exist in any references/ bundle, so the navigation is broken and structure is incomplete.

3 / 5

Total

15

/

20

Passed

Description

87%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 cleanly answers what the skill does and when to use it with concrete, natural trigger terms and a distinctive niche. Minor gaps in action enumeration and synonym coverage keep specificity and trigger quality just below maximum.

DimensionReasoningScore

Specificity

Quotes 'Chinese Seedance 2.0 examples, Chinese prompt patterns, example rewrites, or safe versions of working Chinese video-generation prompts' name the domain plus several concrete action types, with only minor coverage gaps; not a 5 because the actions overlap rather than enumerating distinct capabilities.

4 / 5

Completeness

It explicitly states both the 'what' (examples, prompt patterns, rewrites, safe versions) and the 'when' via 'This skill should be used when the user asks for...', matching the top anchor for concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like 'Chinese Seedance 2.0 examples', 'example rewrites', and 'safe versions of working Chinese video-generation prompts' map well to what a user would say, but synonyms and file/extension variations are absent, so it falls just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The narrow Chinese-language Seedance 2.0 example niche with distinct triggers gives it a clear, low-conflict scope unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.