agentleFS
luminary19luminary19/atelier/skills/forge-optimize/SKILL.md

forge-optimize

Skill2 starsChanged 5 months agoNo licenceView on GitHub

Forge suite — web/runtime optimization pipeline for 3D assets: compress, budget, and hand off GLB files to the browser. Takes a raw GLB exported by Blender (or another DCC) and delivers a browser-ready GLB with Draco or Meshopt geometry compression, KTX2/Basis Universal or WebP texture compression, mesh quantization, LOD generation, and spec-validation — then produces the handoff package that atelier-webgl expects (optimized GLB + poster WebP + decoder paths). Use whenever: compressing a GLB for web delivery, reducing file size, applying Draco or Meshopt, encoding KTX2 textures with UASTC or ETC1S, generating LOD levels from a GLB, setting up DRACOLoader / KTX2Loader / MeshoptDecoder in Three.js or R3F, validating a GLB against the Khronos spec, building a before/after size report, running gltf-transform or gltfpack, meeting web 3D budget targets (< 3 MB, < 100 draw calls, < 500k triangles), or preparing assets for the atelier-webgl handoff. Trigger phrases: "optimize GLB", "compress 3D model", "Draco compress", "Meshopt", "KTX2 textures", "web 3D budget", "gltf-transform", "gltfpack", "LOD for web", "GLB too large", "atelier handoff". HEADLESS-ONLY: driven from code, output verified by reading a PNG. Part of the Forge suite.

  • Installs packages

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are 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.

  • 2

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

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.