The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard Unix utilities including find, ls, and grep to locate and analyze SKILL.md files within the project and the local .claude/skills/ directory.
[COMMAND_EXECUTION]: The skill executes a local script python3 scripts/validate_skill.py to ensure that refactored skills meet defined quality standards.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and processes content from external SKILL.md files.
Ingestion points: Reads SKILL.md files discovered in the project and user home directories during Task 1.
Boundary markers: None identified; the skill does not explicitly use delimiters to isolate untrusted skill content from its own instructions.
Capability inventory: The skill has the capability to search the file system, read file contents, delete directories (Task 3), and execute local Python scripts.
Sanitization: No specific sanitization or validation of the text content within the analyzed skills is described before the agent processes them.

refactoring-skills