The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform quality assurance checks and verify documentation integrity. Specific commands include pnpm lint:md, pnpm build, pnpm start, and vale. These are standard tools in a documentation-as-code workflow.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes untrusted data.
Ingestion points: The skill processes user-supplied "topics" via the argument-hint and reads "related docs" (referenced in SKILL.md step 2) to research tutorial content.
Boundary markers: There are no explicit instructions or delimiters defined to isolate external documentation content or user input from the agent's core instructions.
Capability inventory: The skill has Write and Edit permissions to create and modify files, and Bash permissions to execute project build and linting scripts as documented in process.md.
Sanitization: The skill lacks instructions for sanitizing or validating external content before it is interpolated into the generated tutorial files or processed by local build tools.

tutorial