设计哲学顾问,从20种风格中推荐3个方向并生成视觉Demo和AI提示词。当用户提到"设计风格"、"设计方向"、"配色方案"、"视觉风格"、"设计评审"、"推荐风格"时使用。
70
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Skill.md 的 Phase 1-4 会读取用户在“深度理解需求”中输入的目标受众/核心信息/情感基调等自由文本,并在 Phase 3.5 用这些“用户实际内容”驱动并行 agent 生成 HTML Demo,再在 Phase 5 把“内容描述”拼入提示词传给模型,从而构成对外部用户自由文本的运行时摄取。
35e7cf3
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.