The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the official GitHub CLI (gh repo view, gh issue create, gh api) to perform repository reconnaissance and issue management. This is consistent with the skill's stated purpose of managing GitHub issues.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (braindumps, specs, conversation logs) to generate issue content.
Ingestion points: Raw text provided by the user in the form of braindumps, documents, or conversation history.
Boundary markers: None explicitly defined in the instructions to separate user data from instruction context.
Capability inventory: Employs gh issue create and gh api to write content to remote GitHub repositories.
Sanitization: No explicit sanitization or filtering of the user-provided content is mentioned before it is processed by the model to draft issues.
[EXTERNAL_DOWNLOADS]: The README provides installation instructions using npx skills add thatjuan/agent-skills, which refers to the author's own repository and follows standard installation patterns for the platform.

capture-issues