seedance-copyright

This skill should be used when a Seedance 2.0 prompt mentions named characters, franchises, studios, celebrities, public figures, private people, brand logos, copyrighted scenes, songs, voices, or real-person likeness workflows and needs an IP-safe rewrite.

Quality

80%

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

Quality

Content

71%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 well-structured, mostly actionable instruction skill with a clear rewrite workflow and concrete examples. Its main weakness is progressive disclosure: it depends on a Director's Read reference file that is not bundled, leaving the core record template unreachable.

Suggestions

Bundle the referenced '../../references/directors-read.md' (or inline the canonical narrative/non-narrative record template) so the dangling reference resolves.

Convert the opening procedure into explicit numbered steps with validation checkpoints (e.g., 'after classifying, confirm the risk category before rewriting') to lift workflow clarity to a 5.

Tighten or relocate the 'Intent' framing so the body stays purely operational, or fold it into the Rewrite Principle section.

Dimension	Reasoning	Score
Conciseness	Mostly lean with tight, assumption-respecting sections, but the 'Intent' paragraph ('The user pointing at protected work is not trying to steal...') is motivational framing rather than operational guidance — a minor trim candidate. Not a 5 because not every token is strictly operational.	4 / 5
Actionability	Provides a concrete Risk→Replace table, a full worked example sentence, an authorization-gate decision rule, and an output contract — mostly executable guidance. Not a 5 because the core 'canonical record' template lives in the referenced Director's Read file rather than inline, leaving a gap if that file is unavailable.	4 / 5
Workflow Clarity	The opening sentence gives a clear ordered procedure (load the Director's Read → classify → complete the record → translate to carriers → keep internal labels out), and the Authorization Gate and Output Contract act as verification checkpoints. Not a 5 because checkpoints are implicit in prose rather than explicit numbered validation steps.	4 / 5
Progressive Disclosure	The body has clear section structure and signals one one-level-deep reference inline, but that referenced file ('../../references/directors-read.md') does not exist — no references/ bundle directory is present, so the single navigation pointer is broken. A dangling reference is more than a minor organization gap, so it does not reach 4.	3 / 5
	Total	15 / 20 Passed

Description

90%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, well-targeted description that explicitly states what it does (IP-safe rewrite) and when to use it, with rich natural trigger terms. Its only limitation is that it names a single action rather than enumerating several capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('Seedance 2.0 prompt', IP/likeness) and one concrete action ('IP-safe rewrite'), matching the anchor that lists domain plus 1-2 concrete actions without being comprehensive. It does not enumerate several distinct actions, so it is not a 4.	3 / 5
Completeness	Explicitly answers both 'what' ('needs an IP-safe rewrite') and 'when' ('should be used when a Seedance 2.0 prompt mentions...') with concrete trigger phrases, matching the top anchor exactly. Voice is third person, so no penalty applies.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers users would actually say — 'named characters, franchises, studios, celebrities, public figures, private people, brand logos, copyrighted scenes, songs, voices' — covering many synonyms for the IP/likeness surface, matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Scoped narrowly to 'Seedance 2.0' prompts with a distinct IP/likeness niche and specific triggers, giving a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-copyright/SKILL.md
Commit: 9ea203f

Reviewed: 5 days 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.