SkillAgentSearch skills...

DiffDock-L

Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) β€” blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model.

Install / Use

npx skills add aipoch/open-science --skill diffdock

Installs into whichever agent you are using.

About this skill
πŸ“„

SKILL.md

Installable skill definition

Quality Score

86/100

Supported Platforms

Universal

Our assessment of DiffDock-L

DiffDock-L scores 86/100 on our quality scale, 2334th of 4,698 Development & Engineering skills we index (top 50%).

Its SKILL.md is 4.8 KB long, split into 6 sections with 1 code example: a solid amount of guidance for an agent.

With 4,918 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
15/20
Description
15/15
Adoption
16/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so DiffDock-L is actively maintained.
  • Our last check on 2026-11-03 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit β€” read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-29. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk β€” read a skill before letting an agent act on it.

DiffDock-L compared with similar skills

All 4 of these similar skills score higher than DiffDock-L; compare them before choosing.

SkillScoreStarsUpdatedFormat
DiffDock-L (this skill)by aipoch864.9k53d agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10072.1ktodayCLAUDE.md
claude-howtoby luongnv8910047.3k2d agoCLAUDE.md

Frequently asked questions

How do I install DiffDock-L?
Run npx skills add aipoch/open-science --skill DiffDock-L. The install tabs above show the steps for each supported agent.
Which AI agents does DiffDock-L work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is DiffDock-L safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is DiffDock-L still maintained?
The repository was last updated about 2 months ago, so DiffDock-L is actively maintained.

name: diffdock description: > Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) β€” blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a PDB, to generate ranked 3D poses for a small fragment library, or to get a starting pose for downstream rescoring. DiffDock predicts geometry, not affinity. license: Apache-2.0 category: biomodels requirements: [gpu] metadata: display-name: DiffDock

github.com/gcorso/DiffDock/blob/main/LICENSE: MIT (Β© 2022 Corso, StΓ€rk,

Jing). verified 2026-06-30

third_party: - kind: weights name: DiffDock-L license: MIT terms_url: https://github.com/gcorso/DiffDock/blob/main/LICENSE

DiffDock-L

DiffDock-L is a blind pose predictor: given a protein structure and a ligand, it samples ligand placements over the whole surface with a diffusion model and ranks them with a separately trained confidence head. The confidence score correlates with pose correctness, not with binding free energy β€” DiffDock does not predict whether or how tightly the ligand binds, so for hit triage you still pair it with a scorer (GNINA, MM-GBSA) or with boltz's affinity head. For protein–protein and nucleic-acid co-folding, route to boltz or chai1. Code and weights are MIT (github.com/gcorso/DiffDock).

Running it

cd $DIFFDOCK_REPO   # a clone of github.com/gcorso/DiffDock
python3 -m inference \
  --config default_inference_args.yaml \
  --protein_path target.pdb \
  --ligand_description "COc1ccc(C#N)cc1" \
  --out_dir out

For more than one complex, give --protein_ligand_csv batch.csv instead of the two single-complex flags; the CSV has four columns β€” complex_name, protein_path, ligand_description (SMILES or an .sdf/.mol2 path), and protein_sequence. Leave protein_path empty and fill protein_sequence to have DiffDock fold the receptor with ESMFold first; that path and a larger-library screening recipe are in references/workflows.md.

Under --out_dir/<complex_name>/ each sample is written as rank{N}_confidence{score}.sdf, plus a copy of rank1.sdf for convenience. The confidence value in the filename is a logit, so it is unbounded and can be negative; among samples for the same complex higher is better, but values are not comparable across different complexes or ligands.

The YAML config overwrites your CLI flags

inference.py loads --config default_inference_args.yaml after argparse and replaces every key it finds, so passing --samples_per_complex 40 or --model_dir ... on the command line is silently ignored if the same key sits in the YAML. To change sampling depth or any other key the YAML defines, copy the YAML, edit the copy, and point --config at it.

The first run is silent for ~11 minutes and needs β‰₯32 GB host RAM

Before the first complex, DiffDock precomputes SO(3) and torus lookup tables. That step is silent on stderr, takes ~11 minutes, and on the default Modal tier runs out of host memory and SIGKILLs mid-precompute. Set provider_params.modal.memory: 65536 (or your provider's equivalent), and do not assume a hang means a crash.

The README's --ligand works on the CLI by accident β€” use --ligand_description

The upstream README shows --ligand, which only works because argparse prefix-matches it to the real flag --ligand_description. That shortcut is CLI-only: as a CSV column header or YAML key, ligand matches nothing and the row is silently treated as having no ligand. Spell the flag and the column header out in full.

Errors worth recognizing

| You see | It means / do this | | ----------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | | ValueError: not allowed to raise maximum limit at startup | setrlimit(NOFILE, 64000) exceeds the sandbox hard limit β€” sed the constant in inference.py to min(64000, rlimit[1]). | | Silent SIGKILL a few minutes into the SO(3) precompute | Host RAM exhausted β€” see the gotcha above. | | python3: not found | You are on the upstream rbgcsail/diffdock image β€” that one runs from /home/appuser/DiffDock under micromamba. |


Next: rescore the rank1.sdf poses before ranking ligands against each other β€” boltz's affinity head is the in-tree option β€” since the DiffDock confidence head alone is not an affinity predictor.

Related Skills

View on GitHub
GitHub Stars4.9k
CategoryDevelopment
Updated1mo ago
Forks294

Languages

TypeScript

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit β€” see the Safety scan above for what the skill file itself contains.

No cautions
DiffDock-L β€” Universal Skill: Install & Safety Check | SkillAgent