agentleFS
JiamingShi-JsPhysJiamingShi-JsPhys/3d-fabric/skills/mascot-logo-reconstruction/SKILL.md

mascot-logo-reconstruction

Skill2 starsChanged 3 days agoMITView on GitHub

Orchestrate a fail-gated, source-locked Blender reconstruction of mascots, logos, brand avatars, and stylized flat characters from wireframes, texture packs, and orthographic views. Use when the user requires a 1:1 brand/model match rather than a plausible stylized interpretation.

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

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when: Brand mascot/logo 3D reconstruction, exact part counts, texture-driven model matching, repeated “does not match reference” …

    line 10
  2. Distinctive:

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

    line 12
  3. Distinctive:

    Treat mascots/logos as designed symbols, not natural objects.

    line 51
  4. Distinctive:

    Do not infer hidden leaves/petals from radial math.

    line 52
  5. Distinctive:

    Avoid primitive-first construction when a silhouette exists.

    line 53
  6. Distinctive:

    Use semantic object names and validation prints.

    line 54
  7. Distinctive:

    Create exactly the structural parts declared by the source manifest.

    line 58
  8. Distinctive:

    Every final reconstruction folder should include:

    line 67

≈ “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: Brand mascot/logo 3D reconstruction, exact part counts, texture-driven model matching, repeated “does not match reference” feedback, or full pipeline coordination across analysis, contour mesh, registration, UV fitting, validation, animation, and export.

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.

Mascot / Logo Reconstruction

This is the top-level skill for 1:1 brand mascot reconstruction. It chains the specialized skills and enforces stop/go gates.

Harmonization requirement

For mascot/logo work, use blender-skill-harmonizer first when multiple source types or validation failures are present. It sets canonical source policy and prevents conflicts between reconstruction, UV, fit-repair, lighting, export, and animation skills.

Skill chain

  1. reference-analysis-validator — source inventory, manifest, part counts, masks.
  2. orthographic-registration — shared front/side/back/top coordinate contract.
  3. contour-to-mesh — structural meshes from measured silhouettes.
  4. atlas-uv-fitting — per-part texture/UV fitting.
  5. blender-materials / blender-lighting — only after geometry and UVs pass.
  6. reference-analysis-validator again — overlay gates before export.
  7. blender-export — export only after gates pass.
  8. blender-animation — only after static model is accepted.

Non-negotiable order

Static reference fidelity comes before animation and beauty rendering.

measure → manifest → contour meshes → depth registration → UV fit → overlay validation → export → animation

Hard gates

  • expected structural part count equals Blender scene/export structural part count.
  • front silhouette overlay passes threshold.
  • face/features landmarks pass tolerance.
  • side/back/top renders match their registered envelopes.
  • texture atlas regions are mapped per part.
  • optional aura/background is separated from base structural GLB.

Modeling guidance

  • Treat mascots/logos as designed symbols, not natural objects. Symmetry is not guaranteed.
  • Do not infer hidden leaves/petals from radial math.
  • Avoid primitive-first construction when a silhouette exists.
  • Use semantic object names and validation prints.

Source-manifest structural part invariant

Create exactly the structural parts declared by the source manifest. Extra background arcs, glow, aura, shadows, guide marks, and decorative rings are context/decor unless the manifest explicitly promotes them to structural geometry.

Front-plane rotation rule

In this Blender coordinate convention, the front camera looks along the Y axis and the reference silhouette lives in the X/Z plane. Therefore 2D rotations inside the front view are rotations around the Y axis, not around Z. Use rotation_euler = (0, angle, 0) for 2D component orientation in the front projection. Z rotation spins objects into/out of screen-space incorrectly for X/Z-plane meshes.

Output contract

Every final reconstruction folder should include:

  • reference_manifest.json
  • registration_report.json
  • atlas_regions.json
  • validation/front_mask_validation.json
  • validation/front_overlay_reference.png
  • named .blend
  • base .glb
  • optional aura/context .glb
  • BUILD_NOTES.md with pass/fail gates

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.