agentleFS
arjun988arjun988/blender-skills/.claude/skills/lod-pipeline/SKILL.md

lod-pipeline

Skill2.2k starsChanged 4 months agoMITView on GitHub

Dedicated LOD generation, naming, screen-size targets, and validation for game meshes in Blender via MCP.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Who's talking about arjun988/blender-skills

The biggest 5 of 12 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 12

Talked about on GitHub (12 times).

On GitHub · 12

7 more on GitHub

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before Unity/Unreal/Godot export

    line 22
  2. Distinctive:

    Keep LOD0 as source of truth

    line 81
  3. Distinctive:

    Document budgets in production brief

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LOD Pipeline

Intentional LOD chains. Preserve silhouette. Validate reductions.

When to Use

  • Game assets needing LOD0–N
  • Batch LOD for modular kits
  • Before Unity/Unreal/Godot export

Workflow

Approve LOD0 → Generate LOD1..N → Fix silhouette breaks
  → Naming → Screen-size table → Export verify

Typical Budgets (guide)

LODTris vs LOD0Keep
LOD0100%Full detail
LOD140–60%Major forms
LOD215–30%Silhouette
LOD35–10%Blob / impostor candidate

Tune per asset importance and camera.

Generation Methods

  1. Decimate (planar/collapse) — fast props
  2. Manual retopo low — hero characters/vehicles
  3. Delete interiors / small parts — vehicles, buildings
  4. Bake normals from LOD0 → low — when detail must move to texture

Naming

SM_Asset_LOD0
SM_Asset_LOD1
SM_Asset_LOD2

Collection: COL_LODs_[Asset]

Validation Checklist

  • Silhouette matches at intended distance
  • No major holes / inverted normals
  • UVs still valid (or rebaked)
  • Materials slots consistent across LODs
  • Vertex colors/UVs needed by shader preserved
  • LOD transitions planned (screen size %)

Screen Size Starters

LODScreen size (UE-like guide)
LOD01.0 – 0.5
LOD10.5 – 0.25
LOD20.25 – 0.1
LOD30.1 – 0.0

Constraints

MUST DO

  • Protect silhouette before poly reduction
  • Keep LOD0 as source of truth
  • Document budgets in production brief

MUST NOT DO

  • Blind decimate until unrecognizable
  • Different material slot counts across LODs without reason

Reference Guide

TopicReferenceLoad When
Lod Budgetsreferences/lod-budgets.mdWhen needed
Lod Validationreferences/lod-validation.mdWhen needed

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.