github.com/microsoft/data-formulator
| Skill | Added | Review |
|---|---|---|
report py-src/data_formulator/analyst/skills/report/SKILL.md Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts. | 68 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5d4f7b3 | |
core py-src/data_formulator/analyst/skills/core/SKILL.md The analyst's built-in capabilities: data-inspection tools and the always-available actions (visualize, ask_user, delegate). | 59 59 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5d4f7b3 | |
path-safety .cursor/skills/path-safety/SKILL.md 服务端路径安全与文件访问编码规范。在编写文件下载路由、Agent 工具(文件读取/目录列出)、数据连接器/Loader、Workspace 路径操作、沙箱配置时使用。 | 80 80 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5d4f7b3 | |
language-injection .cursor/skills/language-injection/SKILL.md LLM Agent 多语言注入规范。在修改 Agent 提示词、添加新的 Agent 端点、处理用户可见的后端消息(message_code)时使用。 | 71 71 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 5d4f7b3 | |
error-handling .cursor/skills/error-handling/SKILL.md 统一错误处理系统。在添加 API 端点、修改错误处理、添加前端 API 调用、编写错误相关测试时使用。 | 69 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 5d4f7b3 |