对任意代码项目生成一套面向新人的循序渐进文档集,输出到 docs/ 目录。包含架构、设计思想、代码导读、运行时模型、构建系统、对接指南、调试指南、语言特性、设计规范共 9 篇。当用户提到"生成项目文档"、"写文档"、"新人文档"、"项目理解"、"深入理解项目"时使用。
67
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The prompt instructs the agent to "read all source files" and to include real project code examples, which could force the LLM to reproduce any embedded secrets (API keys, tokens, passwords) verbatim and therefore creates an exfiltration risk.
fd28854
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.