The Agent Skills Directory

[COMMAND_EXECUTION]: Executes the bd (Beads) command-line tool to retrieve status and details for child issues within the repository.
[PROMPT_INJECTION]: Ingests documentation, tracker files, and external CLI output which could theoretically contain malicious instructions.
Ingestion points: Reads docs/agents/issue-tracker.md, .scratch tracker files, git commit messages, and output from the bd CLI tool.
Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' warnings for the data being processed.
Capability inventory: Invokes MCP tools qa-to-do.run_to_qa_parent and qa-to-do.qa_session_create, and executes local shell commands via the bd tool.
Sanitization: Data from external sources is used directly to generate checklist items without explicit sanitization or content validation.

to-qa