multi-reviewer-patterns

multi-reviewer-patterns · tier mission · source repo · MIT

verified

Coordinates parallel code reviews across multiple dimensions, deduplicates findings, calibrates severity, and generates consolidated report…

Test results

0.93 jury mean

quality
0.90
specificity
1.00
maintenance
0.90
Jury agreement
80%
Scored
2026-10-04
Score expires
2026-11-03

Scores are valid for 30 days (the same TTL as the pipeline's expensive scoring layer). After that this page marks them expired until the catalog is rebuilt.

Jury models

  • nvidia/nemotron-3-super-120b-a12b
  • google/gemma-4-31b-it
  • openai/gpt-oss-20b

Security scan

Level
verified
Scanned at
2026-10-03
Findings
0
Upstream commit
156b7a5e7a8b
Description length
268 chars
Files fingerprinted
2

Capabilities

  • code-review

Stacks

  • *

Pairs with

  • github-workflow

Community experiences

What actually happened when you used this skill. No stars, no ratings — just experience reports.

Local prototype: your comment is stored in this browser only — other visitors cannot see it. The queue below is a moderation simulation (try it with ?demo=moderation in the URL); in production a human moderator approves via signed entries shipped with the site build.

Loading…

Share your experience

Prototype: stored in this browser only, pending moderation. See the moderation design.

Moderation queue (local prototype)

Empty.