seedance-characters

This skill should be used when the user asks for character consistency, character tags, identity lock, multi-character blocking, wardrobe continuity, hand safety, expression control, or likeness-sensitive character guidance.

Quality

53%

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-characters/SKILL.md

Quality

Content

50%

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

The skill is well-structured and packed with non-obvious, domain-specific guidance, but it mixes concrete examples with abstract direction, lacks an explicitly sequenced workflow, and references bundle files that are not present.

Suggestions

Provide a minimal character-card/tag-map output template in the Output Contract so the deliverable is directly usable rather than only described.

Either add the referenced [ref:shot-list-continuity] and [ref:directing-engine] files to the bundle or remove the load instructions, since the references currently point to non-existent files.

Tighten the Intent section to its design principle ('treat recurring characters as continuing cast members with memory and a contract') and drop the emotive framing to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, specialized instruction Claude would not already know, but the Intent section carries emotive framing ('a person they love', 'feels it as betrayal, not as a rendering artifact') that is not strictly instructional and could be tightened.	2 / 3
Actionability	It gives concrete specifics (tag assignment, a character-contract table, example actions like 'Character A lowers the envelope; Character B remains in the doorway', and tiered-motion examples), but several directives remain abstract ('keep hands visible but simple', 'use props to show emotion when facial precision is fragile') without directly usable templates.	2 / 3
Workflow Clarity	Sections flow logically into a clear Output Contract ('Return a character card, tag map, action assignments, continuity constraints, and any safety or authorization note'), but the guidance is presented as parallel principles rather than an explicitly sequenced workflow, and there are no validation checkpoints.	2 / 3
Progressive Disclosure	The body is well-organized into clear sections and signals when to load deeper references ('Load [ref:shot-list-continuity] when...'), but the referenced files do not exist in the bundle, so the disclosure is signposted yet broken.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 has an explicit trigger clause and a clear, distinctive niche, but it states when-to-use far more concretely than what the skill actually does, and several trigger terms are specialized jargon rather than natural user phrasing.

Suggestions

Add a brief what-it-does clause naming concrete actions, e.g. 'Assigns stable character tags, locks identity and wardrobe across shots, blocks multi-character action, and surfaces likeness/authorization notes.'

Soften jargon trigger terms with natural equivalents users would actually say, e.g. 'keep the character looking the same across clips' alongside 'identity lock'.

Lead with the capability summary and follow with the 'Use when...' trigger clause so both what and when are explicit.

Dimension	Reasoning	Score
Specificity	The description lists domain-specific capability terms ('character tags, identity lock, multi-character blocking, wardrobe continuity, hand safety, expression control') but frames them as trigger topics rather than concrete verb-actions the skill performs, so it names the domain without fully enumerating actions.	2 / 3
Completeness	It explicitly answers 'when' via 'should be used when the user asks for...', but the 'what' is only implied through the trigger noun list rather than stated as the concrete actions the skill performs, so it does not clearly answer both what and when.	2 / 3
Trigger Term Quality	It offers broad coverage of the niche ('character consistency', 'wardrobe continuity', 'hand safety') but leans heavily on technical jargon ('identity lock', 'multi-character blocking', 'likeness-sensitive character guidance') rather than the simpler phrasings a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	The triggers are highly specific to identity/character consistency in generative video, forming a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-characters/SKILL.md
Commit: 6c51262

Reviewed: 1 day 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.