CtrlK
BlogDocsLog inGet started
Tessl Logo

seedance-sequence

This skill should be used when a Seedance 2.0 request is a long story, connected set of clips, multi-generation scene, campaign sequence, dense storyboard, continuation-ready plan, or any idea that must be divided into stateful clips.

56

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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 a well-structured, actionable orchestrator with a clear sequenced workflow and validation gate, but it is dense with run-on steps and inlined field specs, and its many references point outside the skill bundle rather than to bundled files.

Suggestions

Break the run-on Build Process steps (especially 2 and 7) into shorter sub-steps or move the per-field authoring_state rules into a dedicated reference file.

Move the full Sequence Map Fields and scene-card field enumerations into a reference file, keeping only the essential fields inline in SKILL.md.

Resolve the reference paths: either bundle the referenced files under ./references/ within the skill, or document that they live in a shared plugin-level references directory so the navigation is verifiable.

DimensionReasoningScore

Conciseness

The body does not pad with concepts Claude already knows, but several Build Process steps (notably 2 and 7) are long run-on sentences and the Sequence Map Fields section enumerates ~25 fields inline, which could be tightened or moved to a reference.

3 / 5

Actionability

It provides concrete taxonomies (generation modes, sequence relations, shot structures), an 11-step Build Process, and an explicit 11-item Output Contract; the main gap is that prompt-compilation mechanics are delegated to reference files not present in the bundle.

4 / 5

Workflow Clarity

The Build Process is a clearly numbered sequence with an explicit validation gate in step 11 ('require the clip or final frame... and only then compile the next prompt') and field checklists, though the dense prose slightly reduces clarity.

4 / 5

Progressive Disclosure

References are well-signaled with conditional load guidance, but the skill bundle contains no reference files (paths point to ../../references/ outside the bundle) and a large amount of detailed spec is inlined in SKILL.md rather than split out.

3 / 5

Total

14

/

20

Passed

Description

70%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 a strong, explicit trigger clause with a clear niche, but it reads as a 'when' list and only weakly states what the skill actually does. Adding an active third-person statement of the skill's action would raise specificity and completeness.

Suggestions

Lead with an active third-person action statement (e.g., 'Plans and compiles stateful multi-clip Seedance sequences') before the trigger clause, so the 'what' is explicit rather than implied.

Add the most natural everyday trigger phrases ('continue', 'extend', 'next part', 'make it longer') to the description, since they currently appear only in the body.

DimensionReasoningScore

Specificity

The description names the domain ('Seedance 2.0 request') and one implied action ('divided into stateful clips'), but it is mostly a trigger scenario list rather than a list of concrete skill actions, so it is not comprehensive.

3 / 5

Completeness

It has an explicit and comprehensive 'when' clause ('should be used when...'), and a 'what' ('divided into stateful clips') is present, though the 'what' is passive and could be stated more explicitly as the skill's own action.

4 / 5

Trigger Term Quality

It covers several natural domain trigger terms ('long story', 'connected set of clips', 'multi-generation scene', 'campaign sequence', 'dense storyboard'), but the simplest everyday phrases ('continue', 'make it longer') are absent from the description.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (Seedance 2.0 multi-clip sequence planning) with distinct triggers, with only minor overlap risk against the parent seedance-20 skill.

4 / 5

Total

15

/

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: 14 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.