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.

A well-engineered, executable skill body: copy-paste-ready tool calls, a clearly sequenced workflow with explicit validation gates and failure handling, and a clean one-level reference split. The only nit is minor redundancy between the rules block and the workflow steps.

Suggestions

Trim redundancy between the 'Non-negotiable rules' section and the workflow steps (e.g., serial ordering and 'only lobsterai_skin_manage may register' are restated) to push conciseness from efficient to fully lean.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — it explains only LobsterAI-specific host behaviors (corner radius, theme inference) rather than general concepts — but the 'Non-negotiable rules' list repeats constraints already enforced in the workflow steps (serial ordering, no direct file writes), which keeps it just short of fully lean.	4 / 5
Actionability	Each tool interaction ships a copy-paste-ready JSON block (create_draft, register_asset, apply) with concrete palette values, focus coordinates, explicit contrast ratios (4.5:1, 3:1), and filename hints, plus clear 'replace every example value' guidance.	5 / 5
Workflow Clarity	A six-step numbered sequence runs build-art-direction through validate-and-apply, with explicit validation gates ('Proceed only after registration succeeds', 'Apply only when both required slots are registered and ready') and a dedicated failure-handling section providing error-recovery feedback loops for this batch operation.	5 / 5
Progressive Disclosure	The SKILL.md is a focused overview that offloads the per-slot composition contracts and prompt-suffix templates to a single, clearly signaled, one-level-deep reference (references/asset-contract.md), which exists and is directly relevant; navigation is unambiguous.	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.

A tight, well-gated description that clearly states both what it does and when to use it, with strong distinctiveness and boundary guidance. Its main weakness is that the action set is minimal and the trigger phrasing leans on kit-specific jargon rather than natural user language.

Suggestions

Name a few more concrete actions (e.g., 'generate a workspace backdrop and home emblem, register them, and apply the skin') to lift specificity from 1-2 actions to several.

Add at least one natural-language trigger phrase a user might actually say (e.g., 'Use when the user asks for a custom LobsterAI skin or visual theme pack') alongside the kit-marker gating.

Dimension	Reasoning	Score
Specificity	The description names the domain ('LobsterAI visual skin') and two concrete actions ('Create and apply'), matching the anchor for naming a domain with 1-2 concrete actions; it stops short of the several-specific-actions coverage needed for a 4.	3 / 5
Completeness	It explicitly answers both halves — the 'what' ('Create and apply a two-asset LobsterAI visual skin from the user's style description') and a concrete 'when' ('Use only when the AI Skin Designer kit supplies the structured skin_pack workflow marker; do not use for ordinary theme or image requests').	5 / 5
Trigger Term Quality	It surfaces relevant keywords ('LobsterAI visual skin', 'style description', 'skin_pack workflow marker') and negative triggers ('ordinary theme or image requests'), but the triggers are specialized kit jargon rather than natural phrases a user would say, leaving common variations uncovered.	3 / 5
Distinctiveness Conflict Risk	The niche is tightly scoped to the skin_pack workflow marker with an explicit negative boundary ('do not use for ordinary theme or image requests'), giving it distinct triggers and minimal overlap with other 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: 100d3f7

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.