The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is entirely focused on generating instructional text and copy-pasteable code examples for developer documentation.
[COMMAND_EXECUTION]: The skill contains example shell commands (e.g., npm install) and React/CSS code snippets. These are static placeholders within documentation templates and are not intended for execution by the agent or on the host system.
[INDIRECT_PROMPT_INJECTION]: The skill defines a process where the agent gathers configuration details from a user to populate a guide. This is a standard documentation workflow and does not introduce risk as the agent's capabilities are limited to text generation in this context.
Ingestion points: User-provided inputs in Step 1 (Framework, Package manager, Token consumption, etc.).
Boundary markers: The skill uses strict templates (Steps 3-13) to constrain how the agent incorporates user data into the output.
Capability inventory: The skill is limited to text generation; it contains no subprocess, network, or file-writing operations.
Sanitization: The skill does not explicitly sanitize the text labels provided by the user, but the output is intended for human-readable documentation.

engineering-onboarding