The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using subprocess.run to interact with system utilities.\n
scripts/check_dependencies.py: Executes ruby to verify environmental requirements.\n
scripts/insert_frontmatter.py: Executes git commands to retrieve file metadata and commit history.\n
scripts/okf_yaml.py: Executes an embedded Ruby script to ensure high-fidelity, strict YAML parsing of document frontmatter, passing data via standard input to avoid shell injection.\n- [PROMPT_INJECTION]: The skill processes Markdown and YAML content from the repository, which serves as an indirect prompt injection surface.\n
Ingestion points: Reads .md files within the workspace to extract and update metadata fields (scripts/insert_frontmatter.py, scripts/validate_okf.py).\n
Boundary markers: Uses --- delimiters and performs structural validation of the YAML block.\n
Capability inventory: Includes file read/write operations and execution of git and ruby binaries.\n
Sanitization: Employs YAML.safe_load within the Ruby parser and validates specific metadata fields against a strict schema to prevent malicious data from influencing agent behavior.

x9-okf-docs