通过 GitHub MCP 管理仓库协作时使用,例如检索仓库、提 Issue、起草或创建 PR、查看评论、回复评审和做合并前检查。当用户要操作 GitHub 仓库协作流程而不是修改本地代码实现时优先使用。
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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.
该 skill 的“必需工作流”是通过 GitHub MCP 读取远端 Issue/PR/评论/check runs 等协作事实(`pull_request_read` / `search_issues` / 远端文件读取 `get_file_contents`),这些内容属于外部作者的免费文本,且会在运行时作为 LLM 上下文输入用于起草与回复。
TencentBlueKing/bk-ci
3ae1b3b
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.