Opt-in workflow for triaging one GitHub issue without fixing it. Invoked only via `/triage <github-issue-url>` (`$triage` in Codex). Establishes live state, reproduces with our own fixtures, probes real Next.js for parity, classifies the issue, and drafts the issue reply and next action. Hands valid bugs off to the fix step.
92%
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 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 reads the target GitHub issue's body, every comment, linked PRs and cross-references via `gh`, which is outsider-authored text that any GitHub user can submit into the ingested source, so this is medium under the "ANY GitHub issue/PR reading" rule.
cloudflare/vinext
b0587b3
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.