agentleFS
JiamingShi-JsPhysJiamingShi-JsPhys/3d-fabric/skills/landmark-fit-repair/SKILL.md

landmark-fit-repair

Skill2 starsChanged 3 days agoMITView on GitHub

Validate and repair source-locked Blender models using named landmarks such as leaf tips, shell corners, eyes, smile, rim thickness, aura center/radius, and view-specific depth markers. Use when bbox/IoU is insufficient and the model must align to templates at designed feature points.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

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:

    Use when: Landmark validation, feature-point deltas, control-point repair, face/eye/smile alignment, leaf tip alignment, aura ring fitting, …

    line 10
  2. Distinctive:

    Before the first Blender call, read ../text-to-blender/references/mcp-backends.md.

    line 12
  3. Distinctive:

    No final export when named structural landmarks exceed tolerance.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

MCP backend

Use when: Landmark validation, feature-point deltas, control-point repair, face/eye/smile alignment, leaf tip alignment, aura ring fitting, iterative recipe parameter updates.

Before the first Blender call, read ../text-to-blender/references/mcp-backends.md. Prefer official MCP for shared capabilities; preserve the selected backend for the whole task. Tool names in recipes are client/legacy examples: map them through that reference and its agent-host guide.

Landmark Fit Repair

Bbox and IoU are too coarse for final mascot/logo matching. This skill turns named feature drift into recipe edits.

Landmark classes

  • structural_tip: outer part tips and extrema;
  • shell_corner: face/shell/rim corners;
  • feature: eyes, smile, brows, decals;
  • ring: aura center/radius/dots;
  • depth_marker: side/back/top thickness markers.

Workflow

  1. Define a landmark JSON for the source reference.
  2. Detect or render corresponding product landmarks.
  3. Compare by name and view.
  4. Convert deltas into repair actions: move boundary control point, scale one component, shift feature curve, tune depth, or adjust aura radius.
  5. Rebuild from recipe; do not hand-edit final geometry without updating the recipe/manifest.

Hard gates

  • No final export when named structural landmarks exceed tolerance.
  • Face features must be validated separately from body silhouette.
  • Aura/context landmarks must not affect base GLB acceptance.

Script

  • scripts/landmark_fit_report.py compares two named-landmark JSON files and emits repair deltas.

Landmark JSON schema

{
  "schema": "landmarks.v1",
  "image_size": [width, height],
  "landmarks": [
    {"view":"front", "name":"leaf_top_tip", "class":"structural_tip", "x":627, "y":130}
  ]
}

For part masks, generate initial landmarks from extrema: top/bottom/left/right, centroid, and contour inflection points. Then rename them to semantic names before repair.

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.