The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides Python scripts including scripts/init_skill.py and scripts/package_skill.py that automate the creation of directory structures and ZIP archives on the local filesystem.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it reads and processes external configuration and metadata files to perform validation and packaging.
Ingestion points: scripts/quick_validate.py and scripts/package_skill.py read the SKILL.md file and other directory contents.
Boundary markers: Absent; the content is parsed without specific delimiters to ignore embedded instructions.
Capability inventory: scripts/init_skill.py performs file and directory creation; scripts/package_skill.py reads local files and writes ZIP archives.
Sanitization: scripts/quick_validate.py enforces constraints on the 'name' and 'description' metadata fields using regular expressions.
[SAFE]: Documentation in references/script-quality-criteria.md provides guidance for managing API keys and secrets using .env files and environment variables, following industry best practices.
[SAFE]: The skill recommends using well-known package managers such as npm, npx, and pipx for tool integration, as outlined in references/creation-process.md and references/script-quality-criteria.md.

skill-creator