skin-creator

Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skin_pack workflow marker; do not use for ordinary theme or image requests.

Quality

83%

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

92%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 content is a highly actionable, well-sequenced workflow with complete tool payloads, explicit validation checkpoints, and a properly externalized asset contract. Its only real weakness is redundancy between the non-negotiable rules list and the workflow steps, which could be consolidated.

Dimension	Reasoning	Score
Conciseness	The body is dense, imperative, and free of concept over-explanation, but the "Non-negotiable rules" section restates serial ordering, registration gating, and theme rules that the numbered workflow steps repeat (e.g. "Run strictly serially" vs "Never run image generations in parallel"), leaving minor trims available.	4 / 5
Actionability	Complete JSON payloads for create_draft, register_asset, and apply are copy-paste ready, reinforced by concrete numeric constraints (4.5:1 and 3:1 contrast ratios, #RRGGBB format, 16:9/2K output, particleDensity values, stable filename hints) and exact-slot registration examples.	5 / 5
Workflow Clarity	The six-step sequence has explicit validation checkpoints ("Preserve the returned skinId", "Proceed only after registration succeeds", "Apply only when both required slots are registered and ready") and a dedicated failure-handling section with explicit stop/retry loops covering each failure mode.	5 / 5
Progressive Disclosure	The SKILL.md body stays an actionable workflow overview while the detailed asset contract is externalized to a real one-level-deep reference, clearly signaled by "Read [references/asset-contract.md] before the first image generation call", with well-organized sections throughout.	5 / 5
	Total	19 / 20 Passed

Description

75%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 clearly and explicitly states both what the skill does and when to use it, with strong boundary guidance that minimizes conflict with generic theme/image skills. Trigger term quality is the weaker area: the gating language leans on system jargon ("skin_pack workflow marker") rather than phrases users would naturally say.

Dimension	Reasoning	Score
Specificity	"Create and apply a two-asset LobsterAI visual skin from the user's style description" names the domain and two concrete actions (create, apply) with the two-asset shape, but does not enumerate the assets or mention registration/validation, so coverage is not comprehensive.	3 / 5
Completeness	It explicitly answers what ("Create and apply a two-asset LobsterAI visual skin from the user's style description") and when ("Use only when the AI Skin Designer kit supplies the structured skin_pack workflow marker") with a concrete trigger plus a negative boundary ("do not use for ordinary theme or image requests").	5 / 5
Trigger Term Quality	Relevant terms ("skin", "style description", "theme", "image requests") are present, but the gating phrase "structured skin_pack workflow marker" is system jargon rather than natural user phrasing, and common variations users would say (look, appearance, design) are missing.	3 / 5
Distinctiveness Conflict Risk	The marker-gated trigger and the explicit exclusion of ordinary theme or image requests carve out a clear niche with minimal overlap risk against generic theming or image-generation skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/skin-creator/SKILL.md
Commit: 791a352

Reviewed: 2 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.