360 Secure SkillHub
360 安全技能中心

landmark-fit-repair

针对 bbox/IoU 精度不足的场景，用结构端点、外壳角点、五官、光环和深度标记等命名 landmark，渲染并检测产品模型对应点位，按名称与视图比对偏差，转换为移动控制点、缩放部件、调整深度或光环半径等配方修复动作，并附硬性门禁与脚本化偏差报告，不直接手工编辑最终几何。

RobLe3
热度 0.00
最近更新 2026-10-19 02:52:29
分类：创作依赖：MCP 服务 / 代码执行 / 读写文件应用场景：品牌素材 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add roble3/cc-blender-skill/landmark-fit-repair
Metadata
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. 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.