The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and execute instructions found in external sources to automate code fixes. Ingestion points: Instructions are loaded from a local AGENTS.md file (Step 0) and extracted from GitHub PR comments marked as 'Prompt for AI Agents' (Step 4). Boundary markers: The skill does not use specific delimiters or 'ignore' instructions, instead explicitly directing the agent to 'follow agent prompts literally'. Capability inventory: The skill has access to the Edit tool for file system modifications, and use of git and gh for repository updates. Sanitization: The skill identifies and filters comments to ensure they only originate from verified CodeRabbit bot accounts before processing them.
[COMMAND_EXECUTION]: The skill executes standard git and gh (GitHub CLI) commands to fetch PR metadata, list threads, commit changes, and push updates. These operations are essential to the skill's stated purpose of providing an automated workflow for code review remediation.

autofix