Esmfold2
JimLiu/science-skills
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.
Use this repo skill for Make-It-3D single-image 3D creation, including CUDA asset setup, alpha-image validation, coarse NeRF optimization, refinement, rendering, export, and troubleshooting.
Install Make It 3D
$ npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill make-it-3d --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/make-it-3d .claude/skills/make-it-3d && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "make-it-3d" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/make-it-3d into .claude/skills/make-it-3d/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-it-3d", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/make-it-3dType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill make-it-3d --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/make-it-3d .agents/skills/make-it-3d && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "make-it-3d" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/make-it-3d into .agents/skills/make-it-3d/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-it-3d", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill make-it-3d --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/make-it-3d .cursor/skills/make-it-3d && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "make-it-3d" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/make-it-3d into .cursor/skills/make-it-3d/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-it-3d", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/make-it-3d--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill make-it-3d --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/make-it-3d .gemini/skills/make-it-3d && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "make-it-3d" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/make-it-3d into .gemini/skills/make-it-3d/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-it-3d", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill make-it-3dInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/make-it-3d .github/skills/make-it-3d && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "make-it-3d" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/make-it-3d into .github/skills/make-it-3d/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-it-3d", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill make-it-3d --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/make-it-3d .opencode/skills/make-it-3d && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "make-it-3d" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/make-it-3d into .opencode/skills/make-it-3d/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-it-3d", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
make-it-3d- GitHub stars
- 328
- Token cost
- ~1.4k tokens
- SKILL.md length
- 519 words
- Files
- 8 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Use this repo skill for Make-It-3D single-image 3D creation, including CUDA asset setup, alpha-image validation, coarse NeRF optimization, refinement, rendering, export, and troubleshooting.
- Works in 5 steps: Confirm a compatible environment before… → Validate the reference image. The main… → Avoid unnecessary BLIP2 downloads when… → …
- AI & LLM Engineering work in your project
- SKILL.md covers Route Map, Minimal Operating Sequence, Public Install Skeleton and Do Not Do This
- Runs Python scripts from its folder; calls pip; reaches github.com and download.pytorch.org
What it does
Make It 3D is an agent skill from VectorSpaceLab/AREX-Skill. Use this repo skill for Make-It-3D single-image 3D creation, including CUDA asset setup, alpha-image validation, coarse NeRF optimization, refinement, rendering, export, and troubleshooting.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/backend-and-assets.md`, `references/quickstart.md` and `references/repo-provenance.md`).
It sits in AI & LLM Engineering. It works with CUDA. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is Apache-2.0.
When your agent uses it
- AI & LLM Engineering work in your project
Example prompts
- “/make-it-3d”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Confirm a compatible environment before long runs. Use scripts/make_it_3d_env_check.py against the user's working checkout and asset…
- Validate the reference image. The main script reads --ref_path with cv2.IMREAD_UNCHANGED and immediately converts BGRA to RGBA, so the…
- Avoid unnecessary BLIP2 downloads when possible. If the user already knows the object prompt, pass --text "..."; otherwise main.py loads…
- Run coarse optimization in two phases. Use sub-skills/coarse-training/scripts/build_training_commands.py to emit the README-backed frontal…
- Run refinement/export only after a usable coarse workspace exists. Use sub-skills/refinement-and-export/scripts/build_refine_export_command…
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.comdownload.pytorch.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Make It 3D loads about 1.4k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 50 tokens; SKILL.md has 519 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its Apache-2.0 licence (© VectorSpaceLab). 519 words, ~1,398 tokens.
Download SKILL.mdSave it as
.claude/skills/make-it-3d/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- make-it-3d
- description
- Use this repo skill for Make-It-3D single-image 3D creation, including CUDA asset setup, alpha-image validation, coarse NeRF optimization, refinement, rendering, export, and troubleshooting.
- metadata.disco-role
- operating
- disable-model-invocation
- true
- license
- NO_LICENSE
Make-It-3D Repo Skill
Use this skill when a task is about operating Make-It-3D, the ICCV 2023 single-image-to-3D system that optimizes a NeRF with DPT depth, CLIP/Stable-Diffusion guidance, and a refinement/export stage. The skill is self-contained: use the bundled references and scripts here rather than reopening the source README, demos, or scripts just to recover commands, flags, dependencies, or failure handling.
Before giving run commands, check freshness in references/repo-provenance.md. The source snapshot is a script-style research repo, not a pip-installable root package. Future use normally starts from a Make-It-3D checkout plus a CUDA-capable Python environment.
Route Map
| User need | Read next | Why |
|---|---|---|
| Install/diagnose dependencies, DPT weights, Hugging Face access, alpha-mask inputs, or hardware readiness | environment-and-inputs | Owns CUDA/dependency planning, model assets, input PNG requirements, and reusable environment/input checks. |
| Build the two coarse-stage commands, tune camera ranges, select CLIP vs Stable Diffusion guidance, or debug geometry during training | coarse-training | Owns front-view and 360-degree NeRF optimization, important main.py flags, outputs, and geometry failures. |
| Continue to refine stage, render videos, test checkpoints, save meshes, or reason about point-cloud/mesh export dependencies | refinement-and-export | Owns refine/test/export command construction, generated output layout, and mesh/point-cloud troubleshooting. |
| Cross-cutting install/import, missing module, CUDA extension, credential, output, or quality issues | references/troubleshooting.md | Summarizes failures that span multiple sub-skills. |
Minimal Operating Sequence
- Confirm a compatible environment before long runs. Use scripts/make_it_3d_env_check.py against the user's working checkout and asset locations. Make-It-3D expects CUDA for the practical pipeline; the source forces
opt.cuda_ray = True, so raymarching CUDA support matters even when a user asks for--backbone vanilla. - Validate the reference image. The main script reads
--ref_pathwithcv2.IMREAD_UNCHANGEDand immediately converts BGRA to RGBA, so the reference should be a four-channel image with a usable foreground alpha mask. Use sub-skills/environment-and-inputs/scripts/validate_alpha_input.py. - Avoid unnecessary BLIP2 downloads when possible. If the user already knows the object prompt, pass
--text "..."; otherwisemain.pyloads BLIP2 (Salesforce/blip2-opt-2.7b) for captioning, which requires network/model cache and substantial GPU memory. - Run coarse optimization in two phases. Use sub-skills/coarse-training/scripts/build_training_commands.py to emit the README-backed frontal phase and full-360 phase with correct flags.
- Run refinement/export only after a usable coarse workspace exists. Use sub-skills/refinement-and-export/scripts/build_refine_export_commands.py. Note that in the inspected source the refine block is nested under the
--finalpath; include--final --refineif--refinealone does not execute refinement.
Show full SKILL.md (145 more words)Show less
Public Install Skeleton
Use the exact versions required by the user's machine when possible, but the source documentation used this public install pattern:
pip install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio==0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch
pip install git+https://github.com/openai/CLIP.git
pip install git+https://github.com/huggingface/diffusers.git git+https://github.com/huggingface/huggingface_hub.git
pip install git+https://github.com/facebookresearch/pytorch3d.git
pip install git+https://github.com/S-aiueo32/contextual_loss_pytorch.git
pip install -r requirements.txt
pip install ./raymarchingRead references/backend-and-assets.md before executing this literally: the repository pins older CUDA/PyTorch-era dependencies, while modern hosts often require adjusted torch/PyTorch3D/tiny-cuda-nn builds.
Do Not Do This
- Do not start training before checking CUDA, raymarching build/toolkit readiness, DPT weights, Hugging Face access/cache, and alpha input validity.
- Do not promise CPU reproduction of the main Make-It-3D pipeline. CPU checks can validate scripts and some source facts, but they do not substitute for CUDA training/rendering behavior.
- Do not tell future users to read the original README or source files for basic commands. The equivalent distilled guidance is in this skill tree.
- Do not expose local environment names, absolute checkout paths, or private tokens in user-facing outputs. Ask users to provide their own paths and credentials at runtime.
© VectorSpaceLab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts, references) in skills/repositories/repo-skills/make-it-3d of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/backend-and-assets.md
- references/quickstart.md
- references/repo-provenance.md
- references/repo-routing-metadata.json
- references/troubleshooting.md
- scripts/make_it_3d_env_check.py
- sub-skills
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Make It 3D next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Make It 3D this skillVectorSpaceLab/AREX-Skill | 328 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Esmfold2JimLiu/science-skills | 227 | 4 repos | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| MUSA GPU Training Optimizeropen-infra-skills/infra-skills | 141 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Benchmark TuneMesh-LLM/mesh-llm | 3.5k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Cuda Kernel OptimizerKernelFlow-ops/cuda-optimized-skill | 212 | — | ~4.3k | Automated safety check: Pass | MIT | |
| DGX Spark Training Gotchaswshobson/agents | 40k | 1 repos | ~2k | Automated safety check: Pass | MIT |
Similar skills
MUSA GPU Training Optimizer
open-infra-skills/infra-skills
Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.
Benchmark Tune
Mesh-LLM/mesh-llm
A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…
Cuda Kernel Optimizer
KernelFlow-ops/cuda-optimized-skill
Iteratively optimize a CUDA/CUTLASS/Triton kernel only when strict on-device compilation, correctness, timing, and NCU evidence gates pass.
DGX Spark Training Gotchas
wshobson/agents
Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.
Areno Develop Kernel
inclusionAI/AReno
Develop, optimize, debug, and validate an AReno CUDA, Triton, fused, attention, convolution, routing, or MoE operator.
More from VectorSpaceLab/AREX-Skill
All 157 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Works with
Categories
Questions about Make It 3D
What does Make It 3D do?
Use this repo skill for Make-It-3D single-image 3D creation, including CUDA asset setup, alpha-image validation, coarse NeRF optimization, refinement, rendering, export, and troubleshooting. Make It 3D is an agent skill from VectorSpaceLab/AREX-Skill. Use this repo skill for Make-It-3D single-image 3D creation, including CUDA asset setup, alpha-image validation, coarse NeRF optimization, refinement, rendering, export, and troubleshooting.
When should I use Make It 3D?
Make It 3D fits situations like: AI & LLM Engineering work in your project.
How do I install Make It 3D in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/make-it-3d in VectorSpaceLab/AREX-Skill) into .claude/skills/make-it-3d in your project. Claude Code loads it when a task matches its description.
How do I install Make It 3D in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a codex`. Or copy the skill folder (skills/repositories/repo-skills/make-it-3d in VectorSpaceLab/AREX-Skill) into .agents/skills/make-it-3d in your project. Codex loads it when a task matches its description.
Can I use Make It 3D in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill make-it-3d -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/make-it-3d, .gemini/skills/make-it-3d, .github/skills/make-it-3d and .opencode/skills/make-it-3d in your project.
What does Make It 3D need to run?
Going by SKILL.md and its folder, Make It 3D needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python 3.
Does Make It 3D access the network?
SKILL.md names 2 domains. In commands or code: github.com and download.pytorch.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Make It 3D safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Make It 3D use?
Make It 3D is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Make It 3D use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.
What are the alternatives to Make It 3D?
Skills that share tags, products or a category with Make It 3D: Esmfold2 (JimLiu/science-skills, 227 stars), MUSA GPU Training Optimizer (open-infra-skills/infra-skills, 141 stars), Benchmark Tune (Mesh-LLM/mesh-llm, 3.5k stars) and Cuda Kernel Optimizer (KernelFlow-ops/cuda-optimized-skill, 212 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Make It 3D?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 328 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.