H-Canopy /
2d-to-3d-web
把你的 2D 素材,做成有纵深的 3D 交互网页。An open-source skill for image-based interactive web scenes
A new way for AI to search for data
4GitHub stars
What XERJ indexed
Selected work

“Publish v1.1 skill workflow, lightweight packaging and interactive ex…”. 20 files, 1,098 lines in assets, the project root, tests.
Licence
The repository
MIT
From GitHub's licence detection. A person still checks the LICENSE file at the pinned commit.
The XERJ corpus
MIT, with credit
The author agreed by email on 2026-10-24. Same terms as the repository. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: adapt with attribution
Example questions
- What does assets do in 2d-to-3d-web?
The prompt
Paste it into your AI agent. It clones H-Canopy/2d-to-3d-web at the pinned commit and indexes it on your machine.
Search the GitHub repository H-Canopy/2d-to-3d-web with XERJ (https://hub.xerj.org/corpus/h-canopy--2d-to-3d-web). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/H-Canopy/2d-to-3d-web 2d-to-3d-web && git -C 2d-to-3d-web checkout 5cafd000b841ffc84a5ca99ba302545202455b69 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./2d-to-3d-web --url http://127.0.0.1:9200 --prefix 2d-to-3d-web --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
H-CanopyWeb and frontend platform corpora
Selected work and consent: the XERJ registry.