The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external sources such as an issue tracker and associated markdown files to drive automated development workflows.
Ingestion points: The skill reads metadata and requirements from docs/agents/issue-tracker.md, requirements.md, design.md, and tasks.md in SKILL.md Section 1.
Boundary markers: The instructions do not define delimiters or isolation techniques for the data ingested from these files.
Capability inventory: The skill has the capability to generate and execute code via the build-in-waves and test-first sub-skills, and perform repository changes using git.
Sanitization: There is no evidence of sanitization or validation of the input data before it is processed by downstream execution sub-skills.
[COMMAND_EXECUTION]: The skill instructions and testing documentation reference the execution of Git and GitHub CLI commands to manage code branches and pull requests.
Evidence: Explicit mentions of git branch, git worktree, and gh CLI operations are found in SKILL.md Section 2 and TESTS.md log entries.

deliver-issues