Menu

Individual skill

reference-pack-authority

0upvotes

How to structure, audit and use a GENERATED reference/concept-art pack before building a 3D world from it — the art-direction stage's exit gate. Load this whenever generating target images (Claude with an image tool, Meshy, or any image model), whenever receiving a reference pack for an environment/level/world build, and BEFORE the first geometry is authored against images. Covers the two-tier authority split (technical plates govern geometry, cinematics govern fidelity), the congruence pass that catches a pack contradicting itself, printed-figures-over-drawn-geometry, spec-as-text, and the circularity and prompt-reuse traps. Exists because a pack of individually plausible images can describe mutually contradictory worlds, so congruence must be manufactured, never assumed.

skills/reference-pack-authority/SKILL.md

Read pinned source

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.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# A generated pack is N plausible worlds, not one

## The failure class — why this is structural, not a model problem

No current image model carries a 3D representation between generations. Tested directly on a
real pack: an image-to-image uplift of the project's own render, explicitly told to move
nothing, came back reframed with a landmark reproportioned; of four models given a 1920×1080
source, all returned 1024×1024 and three invented a third torii. **Each image is individually
plausible; nothing makes them mutually consistent.** A better model does not fix this. Structure
does.

What it cost, measured: a site plan drew the bridge parallel to the gate axis while the
cinematic showed it perpendicular — no camera reconciles them; the plan labelled one torii
where the pack elsewhere implied two; and site elevation was defined by NO image at all, so