Agent skill

Drug Pose Validation

by learningmatter-mit in learningmatter-mit/AtomisticSkills

Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement.

MITAuto-check passed

Install Drug Pose Validation

skills CLI

$ npx skills add learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a claude-code

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

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills drug-pose-validation --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/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/drug-pose-validation .claude/skills/drug-pose-validation && 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 "drug-pose-validation" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/drug-pose-validation into .claude/skills/drug-pose-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "drug-pose-validation", 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/learningmatter-mit/AtomisticSkills/tree/main/skills/drug-pose-validation

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 learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a codex

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

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills drug-pose-validation --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/drug-pose-validation .agents/skills/drug-pose-validation && 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 "drug-pose-validation" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/drug-pose-validation into .agents/skills/drug-pose-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "drug-pose-validation", 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 learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a cursor

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

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills drug-pose-validation --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/drug-pose-validation .cursor/skills/drug-pose-validation && 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 "drug-pose-validation" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/drug-pose-validation into .cursor/skills/drug-pose-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "drug-pose-validation", 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/learningmatter-mit/AtomisticSkills.git --path skills/drug-pose-validation

--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 learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a gemini-cli

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

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills drug-pose-validation --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/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/drug-pose-validation .gemini/skills/drug-pose-validation && 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 "drug-pose-validation" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/drug-pose-validation into .gemini/skills/drug-pose-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "drug-pose-validation", 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 learningmatter-mit/AtomisticSkills drug-pose-validation

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 learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/drug-pose-validation .github/skills/drug-pose-validation && 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 "drug-pose-validation" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/drug-pose-validation into .github/skills/drug-pose-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "drug-pose-validation", 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 learningmatter-mit/AtomisticSkills --skill drug-pose-validation -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 learningmatter-mit/AtomisticSkills drug-pose-validation --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/drug-pose-validation .opencode/skills/drug-pose-validation && 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 "drug-pose-validation" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/drug-pose-validation into .opencode/skills/drug-pose-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "drug-pose-validation", 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: drug-pose-validation
GitHub stars: 176
Token cost: ~1.3k tokens
SKILL.md length: 389 words
Files: 8 (incl. scripts)
Skills in repo: 129
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement.

Works in 4 steps: Prepare inputs → Run pose validation → Run without receptor (ligand-only checks) → …
SKILL.md covers Goal, Instructions, Examples and Constraints, plus 1 more section
Runs Python scripts from its folder

What it does

Drug Pose Validation is an agent skill from learningmatter-mit/AtomisticSkills. Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts (for example `examples/hiv1-protease/README.md`, `examples/hiv1-protease/mixed_validation/validation_report.json` and `scripts/validate_poses.py`).

The repository describes itself as: Integrating AtomisticSkills into Agentic IDEs (Cursor, Claude Code, Codex, Google Antigravity, Hermes Agent, etc). The licence is MIT.

Example prompts

“/drug-pose-validation”

Requirements

Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Prepare inputs
Run pose validation
Run without receptor (ligand-only checks)
Interpret results

What it can do on your machine

Read from SKILL.md and the folder at commit 6257444. 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.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
- doi.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

Drug Pose Validation loads about 1.3k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 389 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~47
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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 learningmatter-mit/AtomisticSkills at commit 6257444, republished under its MIT licence (© learningmatter-mit). 389 words, ~1,311 tokens.

Download SKILL.mdSave it as .claude/skills/drug-pose-validation/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.

name: drug-pose-validation
description: Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement.
metadata.category: drug-discovery
metadata.venv: cpu

drug-pose-validation

Goal

To filter docked or generated ligand poses through physical plausibility checks (bond lengths, angles, planarity, internal clashes, protein-ligand clashes, stereochemistry) using PoseBusters, producing a validated subset of poses plus a machine-readable report.

This skill sits between docking (drug-docking-vina) and downstream refinement (drug-complex-system-builder, drug-protein-ligand-md), ensuring that only physically reasonable poses enter expensive simulation stages.

Instructions

1. Prepare inputs

You need:

Docked poses: an SDF file containing one or more ligand poses (e.g., output from Vina converted to SDF, or from any pose-generation tool).
Receptor structure (optional but recommended): PDB file of the protein. When provided, PoseBusters also checks for protein-ligand steric clashes.

If your docked poses are in PDBQT format, convert them to SDF first:

bash

${CLAUDE_SKILL_DIR}/../../venv/run cpu obabel docking/results/ligand_docked.pdbqt -O docking/results/ligand_docked.sdf -m

2. Run pose validation

bash

${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/validate_poses.py \
  --poses docking/results/ligand_docked.sdf \
  --receptor docking/inputs/protein_prepared.pdb \
  --output_dir docking/validation/

This produces:

docking/validation/validation_report.json: per-pose pass/fail results for each check
docking/validation/valid_poses.sdf: SDF containing only poses that pass all checks
docking/validation/summary.txt: human-readable summary

3. Run without receptor (ligand-only checks)

When no receptor is available, run ligand-only validation (checks bond geometry, planarity, stereochemistry, internal clashes):

bash

${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/validate_poses.py \
  --poses generated/conformers.sdf \
  --output_dir generated/validation/

4. Interpret results

The validation report JSON contains per-pose results:

json

{
  "n_poses_input": 10,
  "n_poses_valid": 7,
  "pass_rate": 0.7,
  "per_pose": [
    {
      "pose_index": 0,
      "valid": true,
      "tests": {
        "mol_pred_loaded": true,
        "sanitization": true,
        "bond_lengths": true,
        "bond_angles": true,
        "internal_steric_clash": true,
        "aromatic_ring_flatness": true,
        "internal_energy": true,
        "minimum_distance_to_protein": true,
        "volume_overlap_with_protein": true
      },
      "diagnostics": { "...": "..." }
    }
  ]
}

The tests dict contains the PoseBusters pass/fail columns that determine validity. The diagnostics dict includes all boolean columns from the full report (loading status, extra sanitization checks, etc.) for debugging. Column names come directly from PoseBusters and vary by mode.

Key tests (ligand-only, mol mode):

bond_lengths / bond_angles: flags chemically unreasonable geometry
aromatic_ring_flatness: aromatic rings should be planar
internal_steric_clash: atoms within the ligand should not overlap
internal_energy: conformer energy should be reasonable relative to an ensemble average

Additional tests with receptor (dock mode):

minimum_distance_to_protein: ligand atoms should not penetrate protein atoms
volume_overlap_with_protein: ligand should not occupy protein-filled space

Poses failing any test are excluded from valid_poses.sdf. If all poses fail, revisit docking parameters or ligand preparation.

Show full SKILL.md (102 more words)Show less

Examples

Example: validate Vina docking output for HIV-1 protease

bash

${CLAUDE_SKILL_DIR}/../../venv/run cpu obabel hiv_docking/results/indinavir_docked.pdbqt -O hiv_docking/results/indinavir_docked.sdf -m

${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/validate_poses.py \
  --poses hiv_docking/results/indinavir_docked.sdf \
  --receptor hiv_docking/inputs/1HSG_prepared.pdb \
  --output_dir hiv_docking/validation/

Constraints

Environment: Requires cpu (includes posebusters).
Input format: Poses must be SDF. Convert PDBQT to SDF with Open Babel before running.
Receptor: Optional but strongly recommended. Without it, protein-ligand clash checks are skipped.
Hydrogen handling: PoseBusters expects explicit hydrogens on the ligand. Ensure hydrogens are present in the input SDF (they should be if you used drug-ligand-prep).

References

Buttenschoen, M.; Morris, G. M.; Deane, C. M. PoseBusters: AI-Based Docking Methods Fail to Generate Physically Valid Poses or Generalise to Novel Sequences. Chem. Sci. 2024, 15, 3130-3139. https://doi.org/10.1039/D3SC04185A

Author: Matthew Cox Contact: GitHub @mcox3406

Files

SKILL.md and 7 other files (scripts) in skills/drug-pose-validation of learningmatter-mit/AtomisticSkills.

SKILL.md
examples/hiv1-protease/README.md
examples/hiv1-protease/mixed_poses.sdf
examples/hiv1-protease/mixed_validation/summary.txt
examples/hiv1-protease/mixed_validation/valid_poses.sdf
examples/hiv1-protease/mixed_validation/validation_report.json
examples/hiv1-protease/test_poses.sdf
scripts/validate_poses.py

Open the folder on GitHubat commit 6257444

Compare with similar skills

Drug Pose Validation 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.

Drug Pose Validation compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Drug Pose Validation this skilllearningmatter-mit/AtomisticSkills	176	—	~1.3k	Automated safety check: Pass	MIT	today
Diffdock Molecular Dockingaipoch/medical-research-skills	2k	—	~776	Automated safety check: Pass	MIT	21 days ago
Train Poseruvnet/RuView	97k	—	~504	Automated safety check: Pass	MIT	today
Drug Screening DockingInternScience/scp	169	1 repos	~2k	Automated safety check: Pass	MIT	4 mo ago
Physical Addressthedaviddias/Front-End-Checklist	74k	—	~574	Automated safety check: Pass	MIT	2 days ago
Tooluniverse Drug Drug Interactionwu-yc/LabClaw	1.1k	2 repos	~813	Automated safety check: Pass	None	6 mo ago

Similar skills

Diffdock Molecular Docking
aipoch/medical-research-skills
Diffusion-based molecular docking to predict 3D ligand–protein binding poses (blind docking) with confidence scoring; use when you need pose prediction for drug discovery or virtual screening.
2k GitHub stars~776 tokensUpdated 21 days ago
Research & ScienceAuto-check passed
Train Pose
ruvnet/RuView
Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.
97k GitHub stars~504 tokensUpdated today
DevelopmentAuto-check passed
Drug Screening Docking
InternScience/scp
Comprehensive drug screening pipeline from molecular filtering through QED/ADMET criteria to protein-ligand docking, identifying promising drug candidates.
169 GitHub starsUsed in 1 repo~2k tokens
Research & ScienceAuto-check passed
Physical Address
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing local business websites, e-commerce sites, or any site where a physical presence affects trust or local search visibility.
74k GitHub stars~574 tokensUpdated 2 days ago
Marketing & SEOAuto-check passed
Tooluniverse Drug Drug Interaction
wu-yc/LabClaw
Comprehensive drug-drug interaction (DDI) prediction and risk assessment.
1.1k GitHub starsUsed in 2 repos~813 tokens
Research & ScienceAuto-check passed
Dock Certs Automation
ComposioHQ/awesome-claude-skills
Automate Dock Certs tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.
77k GitHub starsUsed in 3 repos~742 tokens
Productivity & AutomationAuto-check passed

Questions about Drug Pose Validation

What does Drug Pose Validation do?

Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement. Drug Pose Validation is an agent skill from learningmatter-mit/AtomisticSkills. Validate docked or generated ligand poses for physical plausibility using PoseBusters, filtering out chemically invalid or clashing poses before downstream refinement.

How do I install Drug Pose Validation in Claude Code?

Run `npx skills add learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a claude-code`. Or copy the skill folder (skills/drug-pose-validation in learningmatter-mit/AtomisticSkills) into .claude/skills/drug-pose-validation in your project. Claude Code loads it when a task matches its description.

How do I install Drug Pose Validation in Codex?

Run `npx skills add learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a codex`. Or copy the skill folder (skills/drug-pose-validation in learningmatter-mit/AtomisticSkills) into .agents/skills/drug-pose-validation in your project. Codex loads it when a task matches its description.

Can I use Drug Pose Validation 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 learningmatter-mit/AtomisticSkills --skill drug-pose-validation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/drug-pose-validation, .gemini/skills/drug-pose-validation, .github/skills/drug-pose-validation and .opencode/skills/drug-pose-validation in your project.

What does Drug Pose Validation need to run?

Going by SKILL.md and its folder, Drug Pose Validation needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Drug Pose Validation access the network?

SKILL.md names 2 domains. As links in the text: github.com and doi.org. This is read from the text; nothing was executed.

Is Drug Pose Validation 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 Drug Pose Validation use?

Drug Pose Validation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Drug Pose Validation use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Drug Pose Validation?

Skills that share tags, products or a category with Drug Pose Validation: Diffdock Molecular Docking (aipoch/medical-research-skills, 2k stars), Train Pose (ruvnet/RuView, 97k stars), Drug Screening Docking (InternScience/scp, 169 stars) and Physical Address (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Drug Pose Validation?

learningmatter-mit (a GitHub organization) maintains it in learningmatter-mit/AtomisticSkills, which has 176 GitHub stars. The repository holds 129 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Drug Pose Validation

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

drug-pose-validation

Goal

Instructions

1. Prepare inputs

2. Run pose validation

3. Run without receptor (ligand-only checks)

4. Interpret results

Examples

Example: validate Vina docking output for HIV-1 protease

Constraints

References

Files

Compare with similar skills

Similar skills

More from learningmatter-mit/AtomisticSkills

Questions about Drug Pose Validation