CtrlK
BlogDocsLog inGet started
Tessl Logo

seedance-prompt

This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.

71

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill with a clear build workflow and validation checklist. Its main weaknesses are philosophical prose in the Intent section and reference placeholders that do not resolve to real bundle files.

Suggestions

Trim the Intent section to its actionable principle (revisions inherit prior decisions and change only the requested element) and drop the metaphorical padding to improve conciseness.

Provide the referenced bundle files (quick-ref, directing-engine, i2v-guide, etc.) under a references/ directory, or replace the [ref:...] placeholders with verifiable paths, so the progressive-disclosure navigation actually resolves.

Add an explicit length-budget figure or self-check threshold for the 'verified active-surface prompt budget' so the compression and budget steps are concretely measurable rather than implied.

DimensionReasoningScore

Conciseness

Most of the body is dense and assumes Claude's competence (it never explains what T2V, a dolly-in, or rim lighting are), but the "Intent" section is philosophical padding ("a draft is a conversation, not a restart") that could be tightened, so it does not meet the "every token earns its place" bar for 3.

2 / 3

Actionability

Provides concrete, copy-paste-ready guidance: the Subject+Action+Scene+Camera+Lighting/Style+Audio+Constraints formula with a slot table of prompt-ready patterns, per-mode drafting priorities and repairs, an ordered compression cut list, and a numbered output contract.

3 / 3

Workflow Clarity

The Prompt Build Process is an explicit First→Next→Then→Finally sequence ending in a validation checkpoint (the inlined directing coherence test: "one main subject, one main action, one motivated main camera move..."), plus a final anti-slop pass, giving clear steps with an explicit checklist.

3 / 3

Progressive Disclosure

The body is a lean overview that clearly signals one-level-deep conditional references ("Load [ref:quick-ref] for the checklist..."), but no references/ directory exists in the bundle, so the [ref:...] materials cannot be verified to resolve and navigation cannot actually be completed, preventing a 3.

2 / 3

Total

10

/

12

Passed

Description

100%

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, third-person description that states concrete capabilities and pairs them with explicit, domain-natural trigger terms. It clearly communicates both what the skill does and when to invoke it with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "write, improve, translate, compress, or debug a Seedance 2.0 video prompt" — matching the anchor for enumerating several specific actions rather than a single vague domain mention.

3 / 3

Completeness

Explicitly answers both what (write/improve/translate/compress/debug a production-ready prompt) and when via an explicit "This skill should be used when..." trigger clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Natural domain terms a Seedance user would actually say are well covered ("Seedance 2.0 video prompt", "T2V, I2V, V2V, R2V", "camera direction", "prompt quality"); the mode abbreviations are exactly the vocabulary of the target audience.

3 / 3

Distinctiveness Conflict Risk

Scoped to a named model ("Seedance 2.0") and distinctive mode triggers (T2V/I2V/V2V/R2V), giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 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

Total

14

/

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.