Agent skill

Openfold3

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Openfold3

skills CLI

$ npx skills add JimLiu/science-skills --skill openfold3 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills openfold3 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openfold3 .claude/skills/openfold3 && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "openfold3" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/openfold3 into .claude/skills/openfold3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openfold3", 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

$skill-installer install https://github.com/JimLiu/science-skills/tree/main/skills/openfold3

Type 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.

skills CLI

$ npx skills add JimLiu/science-skills --skill openfold3 -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills openfold3 --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/openfold3 .agents/skills/openfold3 && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "openfold3" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/openfold3 into .agents/skills/openfold3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openfold3", 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.

skills CLI

$ npx skills add JimLiu/science-skills --skill openfold3 -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills openfold3 --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/openfold3 .cursor/skills/openfold3 && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "openfold3" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/openfold3 into .cursor/skills/openfold3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openfold3", 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

$ gemini skills install https://github.com/JimLiu/science-skills.git --path skills/openfold3

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add JimLiu/science-skills --skill openfold3 -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills openfold3 --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/openfold3 .gemini/skills/openfold3 && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "openfold3" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/openfold3 into .gemini/skills/openfold3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openfold3", 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.

GitHub CLI

$ gh skill install JimLiu/science-skills openfold3

Installs 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).

skills CLI

$ npx skills add JimLiu/science-skills --skill openfold3 -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/openfold3 .github/skills/openfold3 && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "openfold3" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/openfold3 into .github/skills/openfold3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openfold3", 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.

skills CLI

$ npx skills add JimLiu/science-skills --skill openfold3 -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills openfold3 --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/openfold3 .opencode/skills/openfold3 && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "openfold3" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/openfold3 into .opencode/skills/openfold3/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openfold3", 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: openfold3
GitHub stars: 227
Used in: 4 other repos
Token cost: ~1.8k tokens
SKILL.md length: 537 words
Files: 1
Skills in repo: 27
Repo updated: Jul 1, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.

Predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation
SKILL.md covers Prerequisites, How to run, Query JSON format and Key parameters, plus 4 more sections
Calls pip, huggingface-cli and apt-get; needs HF_TOKEN
Tasks that involve Deep learning

What it does

Openfold3 is an agent skill from JimLiu/science-skills. Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Deep learning. It works with PyTorch. The licence is Apache-2.0.

When your agent uses it

Predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation
Tasks that involve Deep learning

Example prompts

“/openfold3”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit fb309c3. 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
Shell commands in SKILL.md call:
- pip
- huggingface-cli
- apt-get
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- HF_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openfold3 loads about 1.8k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 537 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~63
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from JimLiu/science-skills at commit fb309c3, republished under its Apache-2.0 licence (© JimLiu). 537 words, ~1,828 tokens.

Download SKILL.mdSave it as .claude/skills/openfold3/SKILL.md (or your agent's skills folder).

name: openfold3
description: Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.
license: Apache-2.0
category: biomodels
requirements: gpu
metadata.display-name: OpenFold3

OpenFold3 Structure Prediction

Prerequisites

Requirement	Minimum	Recommended
Python	3.10+	3.11
CUDA	12.1+	12.4+
GPU VRAM	24GB	80GB (H100)
RAM	32GB	64GB
Disk (weights)	3GB	-

How to run

Installation

bash

pip install 'openfold3[cuequivariance]==0.4.1'

The default attention kernel is DeepSpeed DS4Sci_EvoformerAttention. If DeepSpeed is unavailable, switch to the cuEquivariance triangle kernels (no build-from-source) by overriding the eval memory settings in model_config.py (use_deepspeed_evo_attention: False, use_cueq_triangle_kernels: True). Some pre-built environments already ship this override; check before re-patching.

Weights

Apache-2.0, ~2.3 GB from HF OpenFold/OpenFold3. The repo is gated (auto-approval) — accept the access form on the HF model page and authenticate (huggingface-cli login or HF_TOKEN) before downloading:

bash

export OPENFOLD_CACHE=~/.openfold3
huggingface-cli download OpenFold/OpenFold3 checkpoints/of3-p2-155k.pt \
  --local-dir "$OPENFOLD_CACHE"

run_openfold will also auto-download to $OPENFOLD_CACHE on first run if egress is open and HF credentials are available (either HF_TOKEN or a prior huggingface-cli login) with repo access granted. The interactive setup_openfold helper exists but prompts on stdin; prefer the explicit download above for non-interactive runs.

Running

bash

export OPENFOLD_CACHE=/path/to/cache
run_openfold predict \
  --query_json=queries.json \
  --output-dir out/ \
  --use-msa-server false \
  --use-templates false

run_openfold discovers the checkpoint under $OPENFOLD_CACHE automatically. Only pass --inference-ckpt-path <file.pt> if you have a non-standard layout or multiple checkpoints and need to pin one explicitly.

For MSA + templates (slower, higher accuracy), drop the two false flags. The MSA server is api.colabfold.com; template chain-ID remap hits data.rcsb.org (GraphQL) — both must be reachable.

Query JSON format

OpenFold3 does not read FASTA. Queries are a JSON object validated by InferenceQuerySet (pydantic, extra: forbid — unknown keys reject):

json

{
  "queries": {
    "my_complex": {
      "chains": [
        {"molecule_type": "protein", "chain_ids": ["A"], "sequence": "MQIFVK…"},
        {"molecule_type": "protein", "chain_ids": ["B", "C"], "sequence": "MVLSPA…"},
        {"molecule_type": "ligand",  "chain_ids": ["L"], "smiles": "CC(=O)Oc1ccccc1C(=O)O"}
      ],
      "use_msas": true
    }
  },
  "seeds": [42]
}

`molecule_type`	required field
`protein` / `dna` / `rna`	`sequence`
`ligand`	`smiles` or `ccd_codes: ["HEM"]`

chain_ids is a list — repeat the same sequence across multiple chain IDs for homo-oligomers. Per-chain paired_msa_file_paths / main_msa_file_paths let you supply your own a3m instead of the server.

Key parameters

Flag	Default	Description
`--num-diffusion-samples`	5	Structures per (query, seed)
`--num-model-seeds`	1	Number of model seeds per query (multiplies output count alongside JSON `seeds` and diffusion samples)
`--use-msa-server`	true	ColabFold MMseqs2 server for MSA
`--use-templates`	true	ColabFold template search + RCSB remap
`--inference-ckpt-path`	auto-discovered under `$OPENFOLD_CACHE`	Override only — for non-standard layouts or to pin a specific checkpoint file

Output format

out/
├── summary.txt
├── model_config.json / experiment_config.json
├── inference_query_set.json
└── <query_name>/seed_<N>/
    ├── <query>_seed_<N>_sample_<k>_model.cif
    ├── <query>_seed_<N>_sample_<k>_confidences.json           # full PAE/pLDDT
    ├── <query>_seed_<N>_sample_<k>_confidences_aggregated.json
    └── timing.json

*_confidences_aggregated.json is the small one to read first:

json

{
  "avg_plddt": 78.96, "ptm": 0.667, "iptm": 0.0, "gpde": 0.73,
  "has_clash": 0.0, "sample_ranking_score": 0.133,
  "chain_ptm": {"A": 0.667}, "chain_pair_iptm": {}
}

Show full SKILL.md (211 more words)Show less

What good output looks like

summary.txt shows Successful Queries: N matching your input count
avg_plddt > 70 (single-seq) / > 80 (with MSA)
ptm > 0.6; for complexes, iptm > 0.5
has_clash: 0.0
.cif ~50-150 KB per sample for a small protein

Verify

bash

grep -E 'Successful|Failed' out/summary.txt
find out -name '*_model.cif' | wc -l   # = queries x json_seeds x num-model-seeds x num-diffusion-samples

Troubleshooting

Error	Cause	Fix
`_deepspeed_evo_attn requires that DeepSpeed be installed`	default eval kernel is DS4Sci on CUDA	install `deepspeed` (needs nvcc + CUTLASS), or in `model_config.py` eval block set `use_deepspeed_evo_attention: False` + `use_cueq_triangle_kernels: True` (cuEq path; no build)
`CUTLASS_PATH ... not set ... cutlass_library is not installed`	cuEq path still needs the python `cutlass_library` shim	`pip install nvidia-cutlass`
`libXrender.so.1: cannot open shared object file`	rdkit (via pdbeccdutils) needs X11 render libs	`apt-get install libxrender1 libxext6 libsm6`
`ModuleNotFoundError: boto3` (or `awscrt`)	`openfold3.core.data.io.s3` is eager-imported even when weights are local	`pip install boto3 awscrt`
`ValidationError: queries / Field required` or `Input should be an object`	wrong JSON shape	top-level is `{"queries": {"<name>": {...}}}` (a dict, not a list)
`ValidationError ... settings / Extra inputs are not permitted`	tried to override model config via `--runner-yaml`	`--runner-yaml` is `InferenceExperimentConfig` only; kernel/memory settings live in `model_config.py`
`Failed to fetch chain ID mappings from RCSB for N entries`	`data.rcsb.org` unreachable (allowlist/offline)	run with `--use-templates false`, or open egress to `data.rcsb.org`
`CUDA out of memory`	large complex / many samples	reduce `--num-diffusion-samples`; the `low_mem` preset (`model_setting_presets.yml`) offloads more aggressively

Files

Just SKILL.md in skills/openfold3 of JimLiu/science-skills.

Open the folder on GitHubat commit fb309c3

Used in 4 other repositories

We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in JimLiu/science-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Openfold3 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.

Openfold3 compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Openfold3 this skillJimLiu/science-skills	227	4 repos	~1.8k	Automated safety check: Pass	Apache-2.0	3 mo ago
Add Uint Supportpytorch/pytorch	104k	2 repos	~2.3k	Automated safety check: Pass	Custom licence	today
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs	13k	8 repos	~1.7k	Automated safety check: Pass	MIT	3 mo ago
Add Torch Shapes Examplefacebook/pyrefly	7.1k	—	~1.3k	Automated safety check: Pass	MIT	today
Interview Cheatsheetwanshuiyin/ARIS-in-AI-Offer	574	1 repos	~3.4k	Automated safety check: Notes	MIT	today
Ghstack CIpytorch/pytorch	104k	—	~1.4k	Automated safety check: Pass	Custom licence	today

Similar skills

Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
104k GitHub starsUsed in 2 repos~2.3k tokens
AI & LLM EngineeringAuto-check passed
CLIP Image-Text Matching
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
13k GitHub starsUsed in 8 repos~1.7k tokens
AI & LLM EngineeringAuto-check passed
Add Torch Shapes Example
facebook/pyrefly
Official
A skill your agent uses when adding a new PyTorch model to Pyrefly's shape-tracking example corpus under tensor-shapes/pyrefly-torch-stubs/examples — i.e.
7.1k GitHub stars~1.3k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Interview Cheatsheet
wanshuiyin/ARIS-in-AI-Offer
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab).
574 GitHub starsUsed in 1 repo~3.4k tokens
AI & LLM EngineeringAuto-check: notes
Ghstack CI
pytorch/pytorch
Manage CI for PyTorch ghstack stacks by running CI where its results are useful now and deferring other PRs with [no-ci].
104k GitHub stars~1.4k tokensUpdated today
AI & LLM EngineeringAuto-check passed
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.
141 GitHub stars~1.7k tokensUpdated 2 mo ago
AI & LLM EngineeringAuto-check passed

Questions about Openfold3

What does Openfold3 do?

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Openfold3 is an agent skill from JimLiu/science-skills. Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.

When should I use Openfold3?

Openfold3 fits situations like: predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation; tasks that involve Deep learning.

How do I install Openfold3 in Claude Code?

Run `npx skills add JimLiu/science-skills --skill openfold3 -a claude-code`. Or copy the skill folder (skills/openfold3 in JimLiu/science-skills) into .claude/skills/openfold3 in your project. Claude Code loads it when a task matches its description.

How do I install Openfold3 in Codex?

Run `npx skills add JimLiu/science-skills --skill openfold3 -a codex`. Or copy the skill folder (skills/openfold3 in JimLiu/science-skills) into .agents/skills/openfold3 in your project. Codex loads it when a task matches its description.

Can I use Openfold3 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 JimLiu/science-skills --skill openfold3 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openfold3, .gemini/skills/openfold3, .github/skills/openfold3 and .opencode/skills/openfold3 in your project.

What does Openfold3 need to run?

Going by SKILL.md and its folder, Openfold3 needs the command-line tools its instructions call (pip, huggingface-cli and apt-get) and credentials named HF_TOKEN. Our summary lists: Python 3.

Does Openfold3 access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Openfold3 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. Review the folder before installing.

What licence does Openfold3 use?

Openfold3 is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openfold3 use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Openfold3?

Skills that share tags, products or a category with Openfold3: Add Uint Support (pytorch/pytorch, 104k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars), Add Torch Shapes Example (facebook/pyrefly, 7.1k stars) and Interview Cheatsheet (wanshuiyin/ARIS-in-AI-Offer, 574 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openfold3?

JimLiu (a GitHub user) maintains it in JimLiu/science-skills, which has 227 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on July 1, 2026.

Source: JimLiu/science-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Openfold3

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

OpenFold3 Structure Prediction

Prerequisites

How to run

Installation

Weights

Running

Query JSON format

Key parameters

Output format

What good output looks like

Verify

Troubleshooting

Files

Used in 4 other repositories

Compare with similar skills

Similar skills

More from JimLiu/science-skills

Related

Questions about Openfold3