eval-layer

OtherGitHubActivePython

A skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, test cases, judge prompt, and harness. Returns a weighted score plus a judge-leniency signal.

Description provenance: Original source

Open canonical source

Measured: Oct 21, 2026 · 69 observations

Domains & Uses

Domains: Agents, skills and MCP
Uses: Observability, Code assistants

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/erezweinstein5/eval-layer

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

14stars · Oct 21, 2026

+1 (+7.7 %)since Sep 22, 2026

Exact values · 30 readings

Measured	stars	Change
Oct 21, 2026	14	0
Oct 20, 2026	14	0
Oct 19, 2026	14	0
Oct 18, 2026	14	0
Oct 17, 2026	14	0
Oct 16, 2026	14	0
Oct 15, 2026	14	+1
Oct 14, 2026	13	0
Oct 13, 2026	13	0
Oct 12, 2026	13	0
Oct 11, 2026	13	0
Oct 10, 2026	13	0
Oct 9, 2026	13	0
Oct 8, 2026	13	0
Oct 7, 2026	13	0
Oct 6, 2026	13	0
Oct 5, 2026	13	0
Oct 4, 2026	13	0
Oct 3, 2026	13	0
Oct 2, 2026	13	0
Oct 1, 2026	13	0
Sep 30, 2026	13	0
Sep 29, 2026	13	0
Sep 28, 2026	13	0
Sep 27, 2026	13	0
Sep 26, 2026	13	0
Sep 25, 2026	13	0
Sep 24, 2026	13	0
Sep 23, 2026	13	0
Sep 22, 2026	13	·