The Agent Skills Directory

[SAFE]: The skill automates the creation of QA documentation by reading local markdown and YAML files within the project repository.
[SAFE]: File writing is restricted to the specific project path production/qa/ and requires an explicit human-in-the-loop approval step in Phase 5.
[PROMPT_INJECTION]: The skill reads and processes external content from story files and design documents, which creates a surface for indirect prompt injection.
Ingestion points: Phase 2 reads story-*.md files and Game Design Documents (GDDs) to extract acceptance criteria and formulas.
Boundary markers: The skill instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the ingested files.
Capability inventory: The skill uses Read, Glob, Grep, Write, and AskUserQuestion tools. It has the capability to write the processed (and potentially poisoned) content back to the filesystem.
Sanitization: The skill does not perform sanitization or escaping on the ingested text before interpolating it into the final markdown report.

qa-plan