The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) and its API interface to retrieve pull request information and comment history for the PrefectHQ/fastmcp repository.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources that may contain untrusted instructions.
Ingestion points: Processes pull request reviews, maintainer comments, automated feedback (from CodeRabbit, Copilot, or Codex), and CI job logs via gh pr view and gh api calls defined in SKILL.md.
Boundary markers: Absent; there are no explicit instructions or delimiters provided to isolate external content from the agent's core instruction set.
Capability inventory: The skill possesses the ability to modify the local codebase to "fix real defects" and perform network operations via git push or GitHub CLI tools.
Sanitization: No sanitization, filtering, or validation logic is specified for the fetched PR content or CI logs before they are evaluated by the agent.

review-pr