The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions specify using the Bash tool to execute apple-docs commands, which is the primary method for the agent to retrieve documentation (SKILL.md).
[EXTERNAL_DOWNLOADS]: The project depends on the @kimsungwhee/apple-docs-mcp package from the NPM registry to perform its core functionality (package.json).
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its interaction with external web content.
Ingestion points: External documentation content is retrieved from developer.apple.com via commands such as doc, search, and wwdc-video (SKILL.md, .claude/commands/apple-docs.md).
Boundary markers: There are no explicit markers or instructions provided in the skill prompt to separate fetched data from the agent's core instructions or to prevent the agent from following instructions embedded in the documentation (SKILL.md).
Capability inventory: The skill relies on the Bash tool to execute all of its operations (SKILL.md).
Sanitization: No sanitization or filtering of the retrieved documentation content is performed before it is presented to the agent (src/cli.ts).

apple-docs