The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent in SKILL.md to execute local Python scripts (scripts/resolve_style_guides.py and scripts/validate_trigger_matrix_sync.py) for logic related to skill activation and validation. It also provides a mapping in references/quality-gate-command-matrix.md of quality gate commands for various languages (e.g., prettier, eslint, tsc, ruff, cargo, terraform) to be executed within the repository environment.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted code and configuration files which are then processed by the agent using various CLI tools.
Ingestion points: TypeScript source files and configuration files specified in the SKILL.md description (.ts, .tsx, .d.ts, tsconfig*.json).
Boundary markers: None identified.
Capability inventory: Shell command execution across SKILL.md and references/quality-gate-command-matrix.md, including Python script runners, linters, and test suites.
Sanitization: No sanitization or validation of the ingested file content is specified before it is passed to execution tools.

typescript-style-guide