A Claude Code 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.
Last commit April 29, 2026, 196 days ago.
12 GitHub stars and 0 Honeystax upvotes. Copy the install, test the workflow, then decide if it earns a permanent slot.
You can test this quickly and remove it cleanly if it misses.
Starts at 6. Added: last commit 196 days ago +22, GitHub health 28/100 +22, no security policy +8, no contributing guide +4, no code of conduct +3.
AI Agent
Claude Code
Model
Multiple
Fastest way to find out if eval-layer belongs in your setup.
Copy the install command, run a real test, and back it out cleanly if it slows you down.
git clone https://github.com/erezweinstein5/eval-layer ~/.claude/skills/eval-layerRun this first. You will know quickly if the workflow earns a permanent slot.
rm -rf ~/.claude/skills/eval-layerNo messy cleanup loop. If it misses, remove it and keep moving.
Install Location
~/ └─ .claude/ ├─ commands/ ├─ skills/ │ └─ eval-layer/ ← installs here ├─ agents/ └─ settings.json
eval-layer is listed on Honeystax as a Skill for Claude Code, since April 29, 2026. Its code is at github.com/erezweinstein5/eval-layer, with 12 GitHub stars and 0 open issues. Last commit April 29, 2026, 196 days ago. GitHub's community health check gives it 28 out of 100.
Source: GitHub repository
Source check: July 18, 2026
Upstream commit: April 29, 2026
Repository state: Not marked archived
Honeystax upvotes are community interest signals, not star ratings. GitHub stars and repository health are source measurements; editorial risk and trial-cost notes are Honeystax analysis.