Walk this project's own personas through its real user-facing surface before a human does — a browser for a web app, the binary for a CLI, a client for an API or a tool server — and report the friction and breakage as candidate tickets. Use when a branch is functionally complete and somebody is about to say "ship it", or when the user asks to dogfood a branch, run an end-to-end pass, or test the changed flows as a user.
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is dogfood in agranado2k/google-books-clojure
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow has the agent drive the product's own UI, API, or CLI and read the output it returns (page text, response bodies, CLI output), which can include user-generated content, but the agent selects each journey and entry point and no outsider can push text into a feed the workflow monitors, so this is low exposure.
agranado2k/tic-tac-toe-with-agentic-sdlc
931d5f3
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.