github-triage-findings

You have a findings.json (from github-extract-findings). Filing every row blindly creates a noisy, unprioritized backlog. This skill is the human-in-the-loop gate: show the shape of the findings, agree on a scope and order, emit a smaller set, then hand off to classify-github-issues. The win is an auditable wave structure.

This is a reasoning/filtering step — there is no script to run. You read JSON, summarize, and write a smaller JSON.

1. Read and profile the findings

Show counts before asking anything:

• by severity: Critical / High / Medium / Low (and how many have none)
• by status: confirmed vs needs-review (bucket what you see)
• by section: which areas the findings cluster in
• by kind (optional): rename / disambiguation / missing / other