diffdock

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/chemistry/diffdock/SKILL.md

Quality

Content

75%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.

The body is a well-structured, highly actionable overview with good progressive disclosure and clear batch workflows that include validation checkpoints. Scores are held at 4 by minor verbosity, a couple of illustrative-only snippets, and slightly inconsistent inline signaling of the workflows_examples reference.

Suggestions

Tighten the Overview by removing marketing language ('state-of-the-art', 'crucial for') and deduplicate the overlapping Best Practices and Performance Optimization lists to improve conciseness.

Add an inline pointer to references/workflows_examples.md from the Core Workflows section (e.g., 'For full step-by-step examples: Read references/workflows_examples.md') to match the signaling pattern of the other references.

Make the ensemble docking snippet and scoring-function integration more concrete (e.g., a runnable GNINA example or a one-line MM/GBSA command) to close the remaining actionability gaps.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, actionable content (commands, code, tables, presets) and avoids teaching basics, but a few marketing phrases ('state-of-the-art', 'crucial for') and some redundancy between Best Practices and Performance Optimization could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready Modal wrappers, bash commands, parameter presets, and flagged analysis invocations covering common cases; minor gaps remain (e.g., the ensemble snippet is illustrative and MM/GBSA is pointer-only), keeping it just below fully executable.	4 / 5
Workflow Clarity	Multi-step workflows are clearly sequenced with checkpoints (setup_check.py, CSV validation, present-cost-before-launch, confidence thresholds, visual inspection); validation is present so the batch cap does not apply, though there is no tight validate-fix-retry loop on docking output itself.	4 / 5
Progressive Disclosure	The SKILL.md is an overview that appropriately splits detail into real, well-described references/scripts/assets with 'Read this file when...' guidance; the only gap is that workflows_examples.md is described in Resources but not signaled inline from the Core Workflows sections like the other two references.	4 / 5
	Total	16 / 20 Passed

Description

75%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.

The description is specific, distinct, and well-scoped with good natural trigger terms, but it lacks an explicit positive 'Use when...' trigger clause, which caps completeness. Adding a concrete usage trigger would lift the completeness score.

Suggestions

Append an explicit 'Use when...' clause (e.g., 'Use when predicting protein-ligand binding poses or running virtual screening from PDB/SMILES inputs.') to satisfy the completeness trigger requirement.

Add a few more natural user phrasings such as 'dock this ligand' or 'where does this molecule bind' to push trigger-term coverage toward comprehensive.

Optionally include the '.sdf'/'.mol2' ligand formats alongside PDB/SMILES to round out file-extension coverage of inputs.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Predict protein-ligand binding poses from PDB/SMILES', 'confidence scores', 'virtual screening' for 'structure-based drug design' — plus an explicit negative scope, matching the comprehensive-coverage anchor.	5 / 5
Completeness	The 'what' is clearly stated but there is no explicit 'Use when...' positive trigger clause in the description; per the judging guidelines a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural-term coverage including 'molecular docking', 'protein-ligand', 'virtual screening', 'structure-based drug design' and file extensions (PDB/SMILES), but a few common synonyms are absent, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	A clear niche (diffusion-based docking for structure-based drug design) with an explicit 'Not for affinity prediction' boundary gives distinct triggers and minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (586 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/diffdock/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.