seedance-style

This skill should be used when the user asks for visual style, art direction, render feel, period aesthetic, texture, animation style, realism level, or style-safe alternatives to studio or franchise references.

Quality

68%

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-style/SKILL.md

Quality

Content

65%

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

The content is highly actionable with concrete descriptor examples and a clear output contract, but it is held back by narrative padding, the absence of an explicit verification step for the safety rule, and a referenced bundle file that does not exist.

Suggestions

Tighten or cut the "Intent" paragraph and the "Field-observed from Chinese practice" framing so every line carries instruction.

Add an explicit verification checkpoint, e.g. after drafting the descriptor, confirm no studio/franchise/artist/living-creator names remain before returning it.

Either ship the referenced `2d-anime-grammar` file under references/ or remove the `[ref:2d-anime-grammar]` load instruction so signaled references actually resolve.

Dimension	Reasoning	Score
Conciseness	The tables and layered method are tight and earn their tokens, but the philosophical "Intent" paragraph ("the soul of this skill is honoring the love while refusing the theft") and the "Field-observed from Chinese practice" narrative add evocative padding that could be trimmed.	2 / 3
Actionability	Copy-paste-ready descriptor strings in both mapping tables (e.g. "hand-painted 2D animation, soft watercolor backgrounds…"), a concrete five-layer framework, and a precise Output Contract give fully specific, executable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	The Output Contract makes the deliverable unambiguous and the layered method acts as a checklist, but the body presents rules and a framework rather than a sequenced workflow, and the name-safety check is only an implicit checkpoint with no explicit verify step.	2 / 3
Progressive Disclosure	Sections are well organized and the conditional load of `[ref:2d-anime-grammar]` is clearly signaled and one level deep, but no bundle directories exist in the review scope, so the referenced file does not resolve and the navigation chain is broken.	2 / 3
	Total	9 / 12 Passed

Description

72%

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 strong, natural trigger terms and a distinctive niche, but it omits the skill's actual function, leaving completeness and specificity below their top anchors. Adding a concrete action clause (e.g., what it translates style requests into) would raise both.

Suggestions

State explicitly what the skill does, e.g. "Translates style requests into production descriptors (medium, texture, palette, lens/render, period, composition) and rewrites protected-name references into safe descriptions."

Keep the strong "Use when the user asks for…" trigger list but pair it with the action so both what and when are explicit.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ("visual style, art direction, render feel, period aesthetic, texture, animation style, realism level") but never states a concrete action the skill performs, so it sits above the vague anchor 1 yet below the multi-action anchor 3.	2 / 3
Completeness	It has an explicit "when" clause ("This skill should be used when the user asks for…") but never states what the skill does, so it answers only half of the what/when pair and is capped at 2.	2 / 3
Trigger Term Quality	Phrases like "visual style", "art direction", "texture", "animation style", and "realism level" are natural terms a user would actually say, giving good coverage of trigger keywords.	3 / 3
Distinctiveness Conflict Risk	The IP-safe art-direction framing ("style-safe alternatives to studio or franchise references") carves a clear niche with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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-style/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.