What makes molecular-docking notable?

1.2K downloads. Trust evidence available

How should molecular-docking be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

molecular-docking

Run and diagnose expert-grade protein-ligand molecular docking through SciMiner using Gnina, AutoDock Vina, PackDock, SurfDock, DiffDock, and fpocket. Use for focused docking, pocket-aware engine selection, multi-seed ensemble sampling, pose-pool construction, energy-gap filtering, RMSD clustering, Skill: molecular-docking Owner: sciminer Summary: Run and diagnose expert-grade protein-ligand molecular docking through SciMiner using Gnina, AutoDock Vina, PackDock, SurfDock, DiffDock, and fpocket. Use for focused docking, pocket-aware engine selection, multi-seed ensemble sampling, pose-pool construction, energy-gap filtering, RMSD clustering, Tags: latest:1.0.4 Version history: v1.0.4 | 2026-09-10T11:43:45.313Z

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

1.0.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.4release · observed Sep 10, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170qp1q4twz35wa85ppa8894h83w461:molecular-docking

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-sciminer-molecular-docking/snapshot"

Documentation

CLAWHUB

61,194 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: molecular-docking
description: Run and diagnose expert-grade protein-ligand molecular docking through SciMiner using Gnina, AutoDock Vina, PackDock, SurfDock, DiffDock, and fpocket. Use for focused docking, pocket-aware engine selection, multi-seed ensemble sampling, pose-pool construction, energy-gap filtering, RMSD clustering, cross-run recurrence analysis, critical-contact checks, physics sanity checks, confidence grading, and multi-engine comparisons. Do not use a single run or Rank 1 score as the final answer.
---

# Molecular Docking

Treat docking as a hypothesis-generation and diagnosis workflow, not as a one-shot ranking exercise. Do not report a final pose from one run or from score rank alone.

## Non-negotiable rules

- Inspect the receptor, pocket, ligand, and requested biological context before docking.
- Do not perform unrestricted whole-protein blind docking. If the site is unknown, run `fpocket`, rank plausible sites, and dock each candidate in a separate focused box.
- Use 5 independent random seeds when the selected engine exposes seed control. Request 20 poses per run when supported.
- Pool poses across runs before energy filtering or clustering. Preserve score, seed, run, engine, and source-file provenance.
- Protect an isolated low-scoring pose from cluster-size pruning, but do not declare it correct until geometry, recurrence, contacts, and physical plausibility have been checked.
- Never equate a docking-score difference with an experimentally calibrated binding-free-energy difference. Use energy gaps as triage signals only; do not convert them directly into Boltzmann populations.
- If required sampling controls or pose-level outputs are unavailable, state the limitation, downgrade confidence, and use another suitable engine when possible.

## Engine selection

- Default to `Gnina` for a generic focused-docking request.
- Use the engine explicitly named by the user.
- Use `PackDock` when side-chain repacking or receptor flexibility is central.
- Prefer `SurfDock` for shallow, surface-shaped, or cryptic pockets.
- Use `DiffDock` as an orthogonal pose generator when classical docking disperses, especially for shallow sites; do not treat its confidence as binding affinity.
- Use `fpocket` before docking when no defensible pocket is available.
- For robustness comparisons, use the requested engine set; otherwise compare the default engine with one mechanistically different method when confidence matters.

## Five-stage SOP

### 1. Reconnaissance: profile pocket and ligand

Complete and record the following before submission.

#### Receptor and ligand readiness

- Check missing pocket residues or atoms, alternate locations, unresolved loops, protonation/tautomer states, cofactors, metals, conserved waters, covalent chemistry, and biologically relevant oligomer state.
- Standardize the ligand without silently changing stereochemistry. Enumerate materially plausible protonation or tautomer states when the binding-site c

_meta.json

{
  "ownerId": "kn725br751g8y5tkj1h6d2krf58356et",
  "slug": "molecular-docking",
  "version": "1.0.4",
  "publishedAt": 1789040625313
}

skill-card.md

## Description:

Run and diagnose expert-grade protein-ligand molecular docking through SciMiner using Gnina, AutoDock Vina, PackDock, SurfDock, DiffDock, and fpocket for focused docking, engine selection, ensemble sampling, pose-pool analysis, clustering, physics checks, confidence grading, and multi-engine comparisons.

This skill is ready for commercial/non-commercial use.

## Publisher:

[sciminer](https://clawhub.ai/user/sciminer)

### License/Terms of Use:

MIT-0

## Use Case:

External scientists, drug discovery researchers, and computational chemistry developers use this skill to run structured SciMiner docking workflows and produce auditable docking hypotheses rather than one-shot score rankings.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Authenticated receptor and ligand uploads are sent according to mutable remote SciMiner API documentation, and the local artifact does not define a fixed destination allowlist or integrity check.

Mitigation: Use the skill only when SciMiner's documentation hosting and credential controls are trusted, confirm that uploaded molecular data may leave the environment, and enforce destination/origin checks outside the skill when possible.

Risk: SciMiner credentials may be exposed or over-scoped if handled outside the skill's runtime contract.

Mitigation: Use short-lived, narrowly scoped SciMiner credentials and do not print, persist, derive, or search for the injected SCIMINER_API_KEY.

## Reference(s):

- [ClawHub molecular-docking skill page](https://clawhub.ai/sciminer/skills/molecular-docking)
- [SciMiner tool API documentation](https://sciminer.tech/tool_api_files/)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown with structured audit summaries, tables, file/API provenance, and inline shell/API guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include representative coordinate artifacts, pose/score provenance tables, SciMiner task IDs, and history URLs when jobs are run.]

## Skill Version(s):

1.0.4 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular