The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown templates and instructions designed to help an agent write concise and informative pull request bodies. It does not include any scripts or executable code.
[EXTERNAL_DOWNLOADS]: The skill includes links to GitHub repositories and user profiles for attribution and reference purposes. These target well-known developer platforms and pose no security risk.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions on how to process user code and logic to generate summaries. While it ingests external data (user code and diffs), it has no dangerous capabilities—such as network access, file system modifications, or shell execution—that could be leveraged by a malicious payload embedded in the user's code.

pr