The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from potentially untrusted sources such as issue comments, review comments, tickets, and external files (PRD/TDD) as described in Step 2.
[COMMAND_EXECUTION]: The skill involves executing shell commands, primarily for repository management and verification. Evidence: Usage of git rev-parse, ls -La, and repository-prescribed formatting, lint, type, build, and test commands in Step 6. Context: These are standard operations for a development-focused agent and are scoped to the current repository/worktree.

iterate-implementation