The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches skill updates and new installations from the vendor's official GitHub repository (apocohq/skills).
[COMMAND_EXECUTION]: Executes npx skills commands to manage installation, status checks, and updates of agent skills.
[DYNAMIC_EXECUTION]: Uses a skill management utility to dynamically load and update executable logic from the vendor's repository at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from local repository files, which represents a potential attack surface if those files contain malicious instructions.
Ingestion points: Reads .claude/settings.json, CLAUDE.md, and .gitignore from the current project directory in Step 1.
Boundary markers: No explicit boundary markers or instruction-ignoring warnings are defined for the ingested file content.
Capability inventory: The skill can execute npx commands for skill management and perform file write operations to align repo conventions.
Sanitization: No explicit sanitization or content validation is performed on the ingested repository data.

align-repo