visual-asset-design

visual-asset-design is an Image generation & prompting skill for AI agents, published by agentscope-ai in the QwenPaw repository on GitHub. Skillspace rates visual-asset-design D (59/100) and it passed the safety scan; the rating is based on static analysis only.

为角色/场景/道具设计视觉资产、编写或修复 VisualVariant 与阵容图的生成 Prompt 时使用。涵盖参考图布局（艺术身份板/序列关键帧/场景锚点/道具英雄 视图）、构图与镜头语言、图片审核误判规避、实体 continuity 与跨 Variant 身份稳定性。不用于视频 Prompt 编译（见 professional-media-prompts）、 纯素材剪辑或只评价已生成产物。

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
34,887

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubagentscope-ai/QwenPaw

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Image generation & prompting

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.