The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard command-line tools to manage repository state and pull requests.\n
Evidence: SKILL.md includes instructions to run gh pr view, gh pr edit, git status, git commit, and git push.\n
Evidence: A shell pipeline involving printf and shasum is used in Step 6 to calculate URL fragments for diff links.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which could contain malicious instructions designed to influence the agent's actions.\n
Ingestion points: Step 3 of SKILL.md directs the agent to read ticket artifacts and the complete diff of the pull request.\n
Boundary markers: The instructions do not specify any delimiters or safety prompts to distinguish between data and instructions within these external sources.\n
Capability inventory: The skill enables the agent to perform write operations like git commit, git push, and gh pr edit.\n
Sanitization: No sanitization process is defined for the content extracted from tickets or code diffs.

to-pr