diffdock

DiffDock and DiffDock-L molecular docking. Use for protein-small-molecule pose prediction from PDB or sequence plus SMILES/SDF/MOL2, batch docking, virtual screening, and pose-confidence interpretation. Not for binding affinity prediction.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured skill body with executable commands and clean progressive disclosure to real bundle files. The main weakness is conciseness — the introductory sections restate capabilities already in the description and could be trimmed.

Suggestions

Collapse the Overview, Core Capabilities, and When-to-Use sections into a tighter intro that does not restate the description; move trigger phrases to the description only.

Integrate validation/retry feedback loops directly into the batch workflow steps (e.g., 'validate CSV → if errors, fix and re-run prepare_batch_csv.py --validate → only then run inference') rather than isolating them in Troubleshooting.

Trim explanatory prose around parameters and presets, linking sooner to parameters_reference.md for the full detail.

Dimension	Reasoning	Score
Conciseness	Mostly task-specific and useful, but the Overview/Core Capabilities/When-to-Use sections overlap each other and restate the description, and the body runs ~470 lines with some explanatory padding that could be trimmed; not severe enough for 2 but above the lean 4-5 band.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands for single docking, batch CSV prep, batch docking, embedding pre-computation, result analysis, and ensemble docking, with concrete flags and example inputs covering the common cases.	5 / 5
Workflow Clarity	Workflows are clearly sequenced (single, batch Step 1/Step 2, analyze) with validation checkpoints (setup_check.py, prepare_batch_csv.py --validate) and a Best Practices checklist; held below 5 because error-recovery feedback loops live in a separate Troubleshooting section rather than integrated into each workflow step.	4 / 5
Progressive Disclosure	Overview lives in SKILL.md while details are split into one-level-deep, clearly signaled references (confidence_and_limitations.md, parameters_reference.md, workflows_examples.md) plus scripts and assets, each documented in the Resources section with explicit 'Read this file when users need:' navigation; all referenced paths are real bundle files.	5 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that concretely names the tool, its capabilities, explicit use-when triggers, and an out-of-scope boundary. The only minor gap is missing a couple of natural phrasing synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'protein-small-molecule pose prediction', 'batch docking', 'virtual screening', and 'pose-confidence interpretation' — giving comprehensive coverage rather than the 1-2 actions at level 3.	5 / 5
Completeness	Explicitly states what ('DiffDock and DiffDock-L molecular docking' with concrete capabilities) and when ('Use for ... pose prediction ... batch docking, virtual screening, and pose-confidence interpretation'), plus a negative trigger ('Not for binding affinity prediction').	5 / 5
Trigger Term Quality	Strong natural keywords ('molecular docking', 'batch docking', 'virtual screening') plus format extensions (PDB, SMILES/SDF/MOL2), but a few common variations like 'binding pose' or 'protein-ligand docking' are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (DiffDock pose prediction) with distinct triggers and an explicit boundary ('Not for binding affinity prediction'), minimizing overlap with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/diffdock/SKILL.md
Commit: b2a92ba

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.