Skip to content
Back to search

didibyte-3d

MarketplaceWorks with Claude CodeGitHub

DIDIBYTE plugins for 3D character work

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/itsdidibyte--mascot-engineering/badge.svg)](/listings/itsdidibyte--mascot-engineering)

HTML

<a href="/listings/itsdidibyte--mascot-engineering"><img src="/api/listings/itsdidibyte--mascot-engineering/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Python packages (once):

pip install numpy pillow scipy jsonschema scikit-image   # scikit-image optional

**As a Claude Code plugin (recommended):** in Claude Code run

/plugin install mascot-engineering --marketplace itsdidibyte/mascot-engineering

(older Claude Code: `/plugin marketplace add itsdidibyte/mascot-engineering`, then `/plugin install mascot-engineering@didibyte-3d`). The skill is then `/mascot-engineering:mascot-engineering` and the agents are `mascot-engineering:<agent>`.

**Without the plugin system:** copy `skills/mascot-engineering` to `~/.claude/skills/` and `agents/*.md` to `~/.claude/agents/` (all projects), or to `.claude/skills/` and `.claude/agents/` inside one project.

Blender 4.2 or newer is needed only for the `.blend` build step (`blender` on PATH, or tell Claude the path).

Check the install (from a clone of this repo):

python3 -m unittest discover -s tests -v                # 36 tests, Blender ones skip if not installed
BLENDER=/path/to/blender python3 -m unittest tests.test_blender_smoke -v   # once per Blender version

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines
  1. {
  2. "name": "didibyte-3d",
  3. "description": "DIDIBYTE plugins for 3D character work",
  4. "owner": {
  5. "name": "DIDIBYTE",
  6. "url": "https://github.com/itsdidibyte"
  7. },
  8. "plugins": [
  9. {
  10. "name": "mascot-engineering",
  11. "source": "./",
  12. "description": "Measured 2D-to-3D mascot pipeline for Blender (alpha)"
  13. }
  14. ]
  15. }
README.md · README · 136 lines
  1. # mascot-engineering: measured 2D-to-3D for Claude Code + Blender
  2. > **Status: alpha (0.2.0-alpha).** The measurement pipeline is tested on synthetic mascots
  3. > with known 3D truth (36 tests, CI). The Blender build step has **not yet been verified in
  4. > real Blender**, and the pipeline has not yet been run on real AI-generated turnarounds.
  5. > Please report what breaks. Community project; not affiliated with Anthropic or the Blender Foundation.
  6. A Claude Code skill and five subagents that turn your mascot's front, side and back
  7. pictures into a **measured** 3D blockout in Blender, and **prove it matches** by
  8. rendering the model from the same angles as your pictures and reporting exactly where
  9. it is too wide, too narrow or missing a part.
  10. It started as a ChatGPT-drafted kit, reviewed and rebuilt with Claude. See
  11. `REVIEW_OF_CHATGPT_V1.md` for what was kept, what was wrong and what changed.
  12. ## Why this exists
  13. Prompting "make this mascot in Blender" makes the AI guess proportions from looking at a
  14. picture, and you go round in circles. This kit:
  15. 1. measures the silhouettes in your images (pixels, not guesses),
  16. 2. builds a base body whose front and side outlines match the drawings by construction,
  17. 3. fits limbs, ears and tails, and finds eyes and other drawn features, from the same pixels,
  18. 4. renders the model with cameras matched to your images and reports, for example,
  19. `z 0.39-0.51: model TOO NARROW by 0.18 on BOTH edges` (arms missing),
  20. 5. tests it against a 3/4 view it was NOT built from (and tunes roundness from it),
  21. 6. iterates one part at a time, with every change logged, and gives you a .blend with
  22. camera-matched reference image planes for refining by hand (plus optional .glb).
  23. ## Install
  24. Python packages (once):
  25. ```bash
  26. pip install numpy pillow scipy jsonschema scikit-image # scikit-image optional
  27. ```
  28. **As a Claude Code plugin (recommended):** in Claude Code run
  29. ```
  30. /plugin install mascot-engineering --marketplace itsdidibyte/mascot-engineering
  31. ```
  32. (older Claude Code: `/plugin marketplace add itsdidibyte/mascot-engineering`, then
  33. `/plugin install mascot-engineering@didibyte-3d`). The skill is then
  34. `/mascot-engineering:mascot-engineering` and the agents are `mascot-engineering:<agent>`.
  35. **Without the plugin system:** copy `skills/mascot-engineering` to `~/.claude/skills/` and
  36. `agents/*.md` to `~/.claude/agents/` (all projects), or to `.claude/skills/` and
  37. `.claude/agents/` inside one project.
  38. Blender 4.2 or newer is needed only for the `.blend` build step (`blender` on PATH, or tell
  39. Claude the path).
  40. Check the install (from a clone of this repo):
  41. ```bash
  42. python3 -m unittest discover -s tests -v # 36 tests, Blender ones skip if not installed
  43. BLENDER=/path/to/blender python3 -m unittest tests.test_blender_smoke -v # once per Blender version
  44. ```
  45. ## Use
  46. In Claude Code, from your project:
  47. ```
  48. /mascot-engineering:mascot-engineering Make a 3D blockout of my mascot. Front: refs/front.png, side (looking right): refs/side.png, back: refs/back.png. Workspace: work/mymascot
  49. ```
  50. (Use `/mascot-engineering` if you copied the skill instead of installing the plugin.)
  51. Claude will ask you only things it cannot measure:
  52. - **G1**: if your views disagree (for example, the neck is lower in the side view), which
  53. view is right for that part. You get `02_views/TURNAROUND.png` to look at.
  54. - **G2**: approve the part plan (which parts, which primitive, what is mirrored).
  55. - **G3**: approve the Blender renders, or accept the listed remaining differences.
  56. ## Try it on the example first
  57. ```bash
  58. S=skills/mascot-engineering/scripts
  59. python3 $S/intake.py work/blobby --id blobby --origin render_3d \
  60. --view front=examples/blobby/refs/front.png --view right=examples/blobby/refs/side.png \
  61. --view back=examples/blobby/refs/back.png
  62. python3 $S/silhouettes.py work/blobby
  63. python3 $S/consistency.py work/blobby # CONSISTENT
  64. python3 $S/propose_spec.py work/blobby --id body_hull --despike
  65. python3 $S/render_preview.py work/blobby
  66. python3 $S/compare.py work/blobby # reports missing arms, ears, feet
  67. python3 $S/fit_limb.py work/blobby --id arm_l --x-seed 0.3 --z-range 0.3 0.56 --mirror-id arm_r
  68. python3 $S/fit_limb.py work/blobby --id ear_l --x-seed 0.15 --z-range 0.85 1.0 --mirror-id ear_r --embed 2
  69. python3 $S/features.py work/blobby --add eye:1,2 # eyes found by colour, placed on the surface
  70. python3 $S/render_preview.py work/blobby && python3 $S/compare.py work/blobby # front IoU ~0.98, only feet left
  71. python3 $S/visual_hull.py work/blobby # instant 3D envelope: 03_geometry/visual_hull.obj
  72. # held-out 3/4 check:
  73. python3 $S/intake.py work/blobby --id blobby --add --view three_quarter_left=examples/blobby/refs/three_quarter_left.png
  74. python3 $S/silhouettes.py work/blobby --view three_quarter_left
  75. python3 $S/check_three_quarter.py work/blobby
  76. ```
  77. `compare.py` exits with code 4 while findings remain; that is expected during iteration.
  78. Swap in `examples/blobby_inconsistent_side/side_head_too_low.png` as the side view to
  79. see the consistency check catch an AI-style drawing error (head 0.08 lower in the side view).
  80. ## What you get per character
  81. ```
  82. 00_intake/ 01_references/ 02_views/ 03_geometry/ 04_build/ 05_validation/ 06_surface_motion/
  83. DECISIONS.md OPEN_ISSUES.md HANDOFF.md manifest.json (+ a ZIP from pack.py)
  84. ```
  85. `04_build/build_spec.json` is the single source of truth; the .blend is rebuilt from it.
  86. ## Honest limits
  87. - Silhouettes give outlines. The exact cross-section between the front and side views,
  88. and dents no view shows (eye sockets, mouth), are labelled `proposed` and refined by eye
  89. or sculpting after the blockout.
  90. - Inconsistent AI views cannot be made consistent by maths: the kit detects the conflict
  91. and asks you which view wins.
  92. - The Blender step was written against the Blender 4.2+ Python API but **has not been run
  93. in the environment where this kit was built** (no Blender there). Run
  94. `tests/test_blender_smoke.py` once: it builds the example in Blender and checks that
  95. Blender's renders match the numpy preview pixel for pixel.
  96. - A blockout is not a rig, UV layout or final topology. Those are later stages.
  97. ## Repository layout
  98. ```
  99. .claude-plugin/ plugin.json, marketplace.json, icon
  100. skills/mascot-engineering/ SKILL.md, reference/ (7 docs), schemas/, scripts/ (+ mascot_lib/)
  101. agents/ 5 subagents
  102. tests/ 36 tests incl. synthetic ground truth + red-team cases (CI: .github/workflows)
  103. examples/ synthetic mascot "blobby" turnaround, 3/4 view, inconsistent side view
  104. REVIEW_OF_CHATGPT_V1.md CHANGELOG.md TEST_RESULTS.md CONTRIBUTING.md LICENSE (MIT)
  105. ```
  106. ## Roadmap to 1.0
  107. 1. Blender smoke test passing on 4.2 LTS and the current release.
  108. 2. Three real mascots taken from AI turnaround to an approved blockout, with timings.
  109. 3. Then: tag 1.0.
  110. ## License
  111. MIT, see `LICENSE`. Example images are synthetic renders made for this project.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.