CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

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

76%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 strong examples-focused body: highly concrete, production-ready Chinese prompt examples and a clear labeling and output contract. The weakest area is workflow clarity — the process delegates its core steps and validation to reference files that are not present, leaving checkpoints implicit.

Suggestions

Add an explicit validation checklist before returning output (e.g., confirm internal record labels are absent from final prose, reference tags @Image1/@Video1/@Audio1 unchanged, protected-identity terms replaced), instead of relying on the referenced Director's Read process.

State what the multilingual language review step concretely checks and what to do when it fails, so it functions as a checkpoint rather than a load-and-hope reference.

Inline the minimal critical steps from the Director's Read workflow so the skill remains actionable if the '../../references/' files are unavailable, and fix the reference paths to live inside the skill's own bundle.

DimensionReasoningScore

Conciseness

The body is dense and operational — a compact labels table, ten inline example prompts, a one-line rewrite mapping, and a short output contract. It falls short of the 5-anchor only because of the motivational 'Intent' section ('An example that teaches is worth ten instructions') and two intro paragraphs that could be tightened.

4 / 5

Actionability

Ten complete, copy-paste-ready Chinese example prompts spanning I2V, character drama, action, animation, first/last-frame, sequence, continuation, camera-reference R2V, and dialogue, plus a concrete rewrite mapping ('知名IP角色' becomes '原创蒙面屋顶信使') and an explicit output contract. This matches the 5-anchor: fully usable examples covering the common cases.

5 / 5

Workflow Clarity

A sequence is present (load the Director's Read → classify the brief → complete the canonical record → translate into carriers → apply multilingual review → return example, label, risk note), but validation checkpoints are implicit: the 'multilingual language review' step is never defined as a pass/fail check, and the core process is delegated to a referenced file that is not part of the bundle. This matches the 3-anchor (sequence present, checkpoints missing or implicit), not 4 which requires most checkpoints to be explicit.

3 / 5

Progressive Disclosure

Sections are well organized (Intent, Example Labels, Safe Example Patterns, Rewrite Pattern, Output Contract) with the example content appropriately inline for an examples skill, and the two external files are clearly signaled as one-level links. It falls short of 5 because no bundle files are provided in the skill's directory while both references use '../../' paths pointing outside the skill, leaving navigation partially unverifiable.

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 description: third-person voice, explicit and concrete 'use when' triggers, and a well-scoped niche. The main weakness is that the 'what' is expressed as noun deliverables rather than explicit actions, and a few natural trigger variations are missing.

Suggestions

State the capability as an explicit action, e.g., 'Provides Chinese Seedance 2.0 example prompts, pattern rewrites, and safe variants of working video-generation prompts' so the 'what' is as concrete as the 'when'.

Add the natural synonyms users are likely to say, such as 'Seedance prompts', 'Chinese video prompts', or '中文提示词', to broaden trigger coverage.

Clarify what 'safe versions' means operationally (e.g., 'removing protected identity, brand, or celebrity references') to sharpen the what.

DimensionReasoningScore

Specificity

The description lists several concrete deliverables — 'Chinese Seedance 2.0 examples', 'Chinese prompt patterns', 'example rewrites', 'safe versions of working Chinese video-generation prompts' — in a clearly named domain. It sits between the 4-anchor (several specific actions, minor gaps) and 5, because the actions are stated as noun deliverables rather than explicit capabilities, leaving minor coverage gaps.

4 / 5

Completeness

It has an explicit trigger clause ('This skill should be used when the user asks for...') with concrete trigger phrases, satisfying the 'when' fully; the 'what' is present but only implied by the enumerated deliverables rather than stated as an action. Not 5 because the what could be more explicit ('Provides...'); not 3 because the when is explicit and concrete.

4 / 5

Trigger Term Quality

Triggers like 'Chinese Seedance 2.0 examples', 'prompt patterns', 'rewrites', and 'safe versions' are natural phrasings a user would say for this niche. It falls short of the 5-anchor because common synonyms and variations (e.g., 'Seedance prompts', 'Chinese video prompts', Chinese-language request terms) are missing.

4 / 5

Distinctiveness Conflict Risk

'Chinese Seedance 2.0 examples' is a clear niche with distinct triggers (Seedance 2.0, Chinese prompt patterns, example rewrites, safe versions) that are unlikely to fire for unrelated skills, matching the 5-anchor.

5 / 5

Total

17

/

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.

Validation — 13 / 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

Path

skills/seedance-examples-zh/SKILL.md

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.