The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill retrieves design guidelines and output schemas from the author's GitHub repository (raw.githubusercontent.com/csark0812/...). These resources serve as static references for the agent's diagnostic process.- [PROMPT_INJECTION]: The skill ingests untrusted user data, including reproduction steps and environment artifacts, to construct diagnostic shell commands. This introduces a surface for indirect prompt injection. * Ingestion points: User-provided bug reports, environment logs, and captured artifacts (e.g., HAR files). * Boundary markers: No specific delimiters or safety warnings are defined to isolate untrusted user data from agent instructions. * Capability inventory: The skill instructs the agent to perform command execution, network operations (curl), and browser automation (Playwright/Puppeteer). * Sanitization: There is no requirement or mention of sanitizing or validating external artifacts before they are processed.- [NO_CODE]: The skill consists entirely of markdown documentation and instructions, without any accompanying scripts, executables, or binaries.

diagnose