Individual skill
asset-judge-loop
The build→judge→rebuild loop for MULTI-asset 3D work — whenever a scene, environment, village, level, diorama or any batch of more than ~3 assets is being built (in Blender, via MCP, procedurally, or by generation), and especially when builder subagents are doing the work. The parent orchestrates; builders never self-certify; every "done" claim triggers a FRESH independent judge subagent that sees only renders, manifest and references, and the loop repeats until the judge passes or the operator stops. Exists to defeat effort dilution — the measured failure where 3 assets get real craft and 6 ship as boxes — and score-gaming via shaders/lighting while geometry rots. Load it at task start, alongside 3d-asset-quality, whenever the work is bigger than one object.
skills/asset-judge-loop/SKILL.md
Source commit d907ca964dd2b86b973eadb165f7413a971bb131
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 12
- Repository last updated
- Sep 1, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- 3d Repository topic
- agent-skills Repository topic
- ai-agents Repository topic
- blender Repository topic
- claude-code Repository topic
- game-development Repository topic
- remakebench Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 16,762 bytesSKILL.mdcore · 16,762 bytesSKILL.mdcore · 16,762 bytesreferences/judge-prompt.mddoc · 4,431 bytes
Read excerpt
# The judge loop: nobody passes their own work
Companion to `3d-asset-quality`, which defines the bar for ONE asset. This skill defines how a
BATCH of assets actually reaches that bar. Load both.
## The two failure modes this exists to kill
Both were observed, repeatedly, on real runs:
1. **Effort dilution.** Told to build nine assets to the same bar, a model spends real craft on
three and ships six as textured boxes. The wider the scope, the worse the spread. No prompt
wording fixes this — the builder's own "done" is the broken instrument, so done must be a
verdict someone else issues.
2. **Score gaming by global levers.** When a score exists, models drift to shaders, lighting and