landmark-fit-repair — Claude Code skill: fix Blender models
Compares a Blender model against a template at named points — leaf tips, shell corners, eyes, smile, aura radius — and turns the drift into recipe edits.
npx skills add RobLe3/cc-blender-skill --skill landmark-fit-repair -a claude-codeWhat landmark-fit-repair does
Bbox and IoU are too coarse once a mascot or logo has to match the source at designed feature points. This skill works from named landmarks and compares them by name and view: structural_tip for outer extrema, shell_corner for face and rim corners, feature for eyes, smile, brows and decals, ring for aura center and radius, depth_marker for side, back and top thickness.
The workflow is ordered. Define a landmark JSON for the reference, detect or render the matching product landmarks, compare them, then convert deltas into repair actions: move a boundary control point, scale one component, shift a feature curve, tune depth, adjust the aura radius. Rebuild from the recipe — hand-editing final geometry without updating the recipe or manifest breaks the pipeline. scripts/landmark_fit_report.py compares two named-landmark JSON files and emits the repair deltas.
Hard gates apply. No final export while named structural landmarks sit outside tolerance. Face features get validated separately from the body silhouette, and aura or context landmarks must not affect base GLB acceptance. Before the first Blender call you read ../text-to-blender/references/mcp-backends.md and pick an MCP backend: official is preferred for shared capabilities, and the chosen backend stays for the whole task. Without a Blender MCP server the skill has nothing to drive.
What it helps with
- catch mascot drift where bbox no longer tells you anything
- turn a landmark delta into one concrete recipe edit
- validate face features apart from the body silhouette
- block export while structural landmarks are out of tolerance
- diff two landmark JSON files into a repair list
Example prompts for the agent
- Compare the model landmarks against the reference JSON and list the deltas by name
- The smile drifted left in the front view — shift the curve and rebuild from the recipe
- Aura radius is too wide, fix the ring and leave the base GLB alone
How to install landmark-fit-repair
1Skills CLI (Vercel)
npx skills add RobLe3/cc-blender-skill --skill landmark-fit-repair -a claude-code2Manually: put the files in place
~/.claude/skills/landmark-fit-repair/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/landmark-fit-repair/
1Skills CLI (Vercel)
npx skills add RobLe3/cc-blender-skill --skill landmark-fit-repair -a codex2Manually: put the files in place
.agents/skills/landmark-fit-repair/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add RobLe3/cc-blender-skill --skill landmark-fit-repair -a cursor2Manually: put the files in place
.cursor/skills/landmark-fit-repair/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install RobLe3/cc-blender-skill landmark-fit-repair2Manually: put the files in place
.github/skills/landmark-fit-repair/SKILL.md1Skills CLI (Vercel)
npx skills add RobLe3/cc-blender-skill --skill landmark-fit-repair -a gemini-cli2Platform CLI
gemini skills install https://github.com/RobLe3/cc-blender-skill --path plugin/skills/landmark-fit-repairManually: put the files in place
.devin/skills/landmark-fit-repair/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add RobLe3/cc-blender-skill --skill landmark-fit-repair -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about landmark-fit-repair
How do I install landmark-fit-repair in Claude?
Run npx skills add RobLe3/cc-blender-skill --skill landmark-fit-repair -a claude-code. The skill then lives at ~/.claude/skills/landmark-fit-repair/SKILL.md.
What does landmark-fit-repair do?
It compares a Blender model to a reference at named landmarks and converts the deltas into recipe edits: moving a control point, scaling a component, tuning depth or aura radius.
What does the skill need to run?
A Blender MCP server and one backend kept for the whole task. Before the first Blender call the skill has you read ../text-to-blender/references/mcp-backends.md.
Source text
SKILL.md · MIT
---
name: landmark-fit-repair
description: 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.
allowed-tools: Read Bash Glob Grep mcp__blender__execute_blender_code mcp__blender__get_scene_info mcp__blender__get_object_info mcp__blender__get_objects_summary mcp__blender__get_object_detail_summary mcp__blender__render_viewport_to_path mcp__blender__search_api_docs mcp__blender_official__execute_blender_code mcp__blender_official__get_objects_summary mcp__blender_official__get_object_detail_summary mcp__blender_official__render_viewport_to_path mcp__blender_official__search_api_docs
---
## 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](../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
```json
{
"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.
© RobLe3 · MIT · RobLe3/cc-blender-skill