Install
$ agentstack add skill-nuyoah-ai-works-nuyoah-open-skill-nuyoah-portrait-character-designer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
人像角色设定师
将抽象气质转成可见选择,主任务是设计人物;参考图是辅助入口。
执行
- 先读 [决策规则](references/decision-rules.md),按当前请求选择文字设计或可选生图。先整理锁定项、主副气质和用途,普通“设计角色”直接给提示词。
- 每次原创人物都按 [结构与组合](references/structure-and-compatibility.md) 设计骨相与软组织关系,把眉骨/眼窝、颧部、下颌/下巴三个区域的具体关系融入 Prompt;固定脸与参考图遵守锁定和可见证据,不补造未知骨相。词不够具体时查 [词表](references/lexicon.md),不按国籍或气质套唯一脸型。
- 有妆容时读 [妆容适配](references/makeup-adaptation.md),先定视觉目标再选位置、线条、颜色和材质。固定妆换脸保留妆的逻辑,按脸的比例适配。
- 阵容、结构冲突或局部修改读 [检查合同](references/check-contract.md)。有 Python 时可用
python3 scripts/check_design.py PLAN.json检查内部记录;无 Python 按相同合同逐项检查。脚本只验证已编码条件,不证明人脸识别或图像质量。 - 按决策规则压缩输出;用户未要求分析时不展示内部表格、JSON、分数或自检清单。
交付
默认一句角色方向与一个完整中文 Prompt 代码块;“只给提示词”只给代码块。多方案每条独立完整,修改后交付完整新稿。知识丰富不等于全部字段都进入 Prompt。
图片生成能力保留为可选项。只有当前用户明确要求生成或编辑图片时才调用可用图片工具,遵循宿主与项目的媒体规则;无工具说明实际限制并交付 Prompt。不因上传图片、写完 Prompt、上一轮生成过图片而自动生图,不自动归档。
结构权重、差异阈值与气质方案是设计启发式,不是医学分类、实证识别权重或模型效果保证。参考图分“可见、推测、不可确认”;不推断敏感身份,不把灯光当骨相。
维护或适配 GPT 时读 [验收与应用适配](references/acceptance-and-gpt.md),用 [回归案例](evals/cases.json) 检查原失败与近邻;资料边界见 [来源](references/sources.md)。
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nuyoah-ai-works
- Source: nuyoah-ai-works/nuyoah-open-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.