The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to perform administrative tasks such as listing directory contents (ls) and calculating file line counts (wc). It also manages the lifecycle of scripts found within the target skills being audited.
[EXTERNAL_DOWNLOADS]: The skill employs WebSearch and WebFetch to research domain-specific information. It fetches external content to ensure that the refined skills incorporate current industry standards and best practices.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks (Category 8) because it processes untrusted content from the skills it audits.
Ingestion points: The agent reads the SKILL.md and all associated reference files of the target skill being refined (Phase 1).
Boundary markers: Absent. The skill does not explicitly instruct the agent to use delimiters or ignore instructions found within the target files.
Capability inventory: The skill has access to Bash, Write, Edit, WebSearch, and WebFetch (SKILL.md).
Sanitization: Absent. There is no mechanism described to sanitize or validate the content of the target skill before it is used to drive research or file edits.

skill-refine