Skill audit report
当用户提到“小黄”“有温度 IP”“温度种子”“爱心天线”,或希望为固定品牌角色制作标准图、动作表情、三视图、表情包、场景插画、2D/3D 转换、黑白共创、联名、风格迁移、身份修复时使用;也用于把中文文章、公众号、博客、Notion 文档、方法论、工作流或知识型帖子转成小黄轻手绘正文配图。始终保持同一角色身份;正文配图先识别认知锚点并输出 shot list 或逐张生成 16:9 配图。
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO62
118 GitHub stars
Stars/forks activity
WARN57
118 stars, 13 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
15d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add ChenShuo2004/cs-skills --skill cs-xiaohuang-skill
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS86
filesystem or document access
Repository evidence
PASS86
https://github.com/ChenShuo2004/cs-skills/tree/main/cs-xiaohuang-skill
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add ChenShuo2004/cs-skills --skill cs-xiaohuang-skill
Repository
88
https://github.com/ChenShuo2004/cs-skills/tree/main/cs-xiaohuang-skill
License
86
MIT
Maintenance
100
15d since push
AI review
55
SKILL.md references several supporting files (assets/reference-xiaohuang.png, references/style-dna.md, references/prompt-template.md, references/qa-checklist.md, etc.) that are not fully shown in the excerpt; if any are missing from the packaged skill, core workflows will break.
README/SKILL.md completeness
86
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Install command safety
92
standard package or runtime install path
Permission surface
86
filesystem or document access
Stars/forks activity
57
118 stars, 13 forks; issue activity unavailable in current metadata
Adoption
68
118 GitHub stars
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Compare nearby options