The Agent Skills Directory

[COMMAND_EXECUTION]: The skill employs local shell commands including ls, mkdir, cp, and touch to manage the lifecycle and directory structure of BDD artifacts within the docs/ directory. These operations are confined to the local filesystem.
[COMMAND_EXECUTION]: It invokes a local validation script python3 scripts/validate_bdd_suite.py to verify the syntax and structure of generated feature files, which is a common developer tool pattern.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from upstream artifacts (BRD, PRD, EARS) to generate test scenarios, which represents an indirect prompt injection surface if the source artifacts are untrusted. * Ingestion points: Reads documents from docs/01_BRD/, docs/02_PRD/, and docs/03_EARS/. * Boundary markers: No explicit delimiters or boundary markers are defined in the instructions for the ingested data. * Capability inventory: Includes the ability to create directories, copy files, and execute a Python validation script. * Sanitization: No explicit sanitization or input validation of the content from upstream artifacts is defined before processing.

doc-bdd