The Agent Skills Directory

[SAFE]: The skill is designed for software maintenance tasks such as reproducing bugs and verifying resolutions. It provides structured templates for documentation and does not contain any instructions that attempt to bypass AI safety guidelines or override system prompts.
[COMMAND_EXECUTION]: The skill utilizes common development commands including pnpm test, pnpm build, pnpm lint, and gh run view to inspect local environment state and CI logs. These commands are standard for project management and are executed within the scope of the user's repository.
[DATA_EXFILTRATION]: The skill employs network-capable tools (WebFetch and Playwright MCP) for the legitimate purpose of verifying API endpoints and UI states. No hardcoded credentials or attempts to access sensitive system files (e.g., SSH keys, environment variables) were found.

reality-verification