diffdock-molecular-docking

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.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/diffdock-molecular-docking/SKILL.md

Quality

Content

65%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 well-organized, mostly executable skill body with a clear single-docking workflow and good reference structure. It is held back by a missing referenced file, lack of output validation/feedback loops for batch operations, and minor redundancy.

Suggestions

Add the missing references/workflows_examples.md file (or remove the three references to it), since batch/advanced workflows are advertised as a key feature but the target file does not exist in the bundle.

Add an output-validation/feedback step to the inference workflow (e.g., check that rank*.sdf files and confidence_scores.txt were produced and are non-empty), so batch operations clear the workflow-clarity cap.

Tighten redundancy: collapse the overlap between When to Use and Key Features, and replace the repeated "(version not specified)" annotations in Dependencies with a single pinned-version note.

Dimension	Reasoning	Score
Conciseness	The body is efficient and avoids explaining concepts Claude already knows, but has minor redundancy — Key Features overlaps When to Use, Implementation Details re-states pose generation/ranking, and "(version not specified)" repeats five times — that could be trimmed.	4 / 5
Actionability	Provides a copy-paste-ready inference command with documented arguments and a concrete setup-check command, but defers the full argument list and batch usage to reference files, leaving minor gaps.	4 / 5
Workflow Clarity	The sequence (verify environment → run inference → outputs) is clear and includes a pre-flight check via setup_check.py, but the skill explicitly supports batch docking yet has no output validation or error-recovery feedback loop, so the batch-operation cap at 3 applies.	3 / 5
Progressive Disclosure	Structure is clean with well-signaled one-level-deep references, but the body references references/workflows_examples.md three times (When to Use, Key Features, Implementation Details) and that file is not present in the bundle, breaking navigation for a core feature.	3 / 5
	Total	14 / 20 Passed

Description

82%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 strong, concise description that clearly states both capability and trigger conditions for a well-scoped niche. Its only real gap is breadth of concrete actions and missing format-level trigger terms (file extensions/SMILES).

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions — "predict 3D ligand–protein binding poses (blind docking)" and "confidence scoring" — but stops at 1–2 actions rather than listing several, matching the anchor for domain + 1–2 concrete actions.	3 / 5
Completeness	It explicitly answers both what ("Diffusion-based molecular docking to predict 3D ligand–protein binding poses (blind docking) with confidence scoring") and when ("use when you need pose prediction for drug discovery or virtual screening") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("molecular docking", "blind docking", "pose prediction", "drug discovery", "virtual screening") that a user would say, but it omits file extensions/format terms (.pdb, .sdf, SMILES) that appear in the body, so it falls short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Molecular docking with blind-docking and ligand–protein pose prediction is a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/diffdock-molecular-docking/SKILL.md
Commit: 63c61d3

Reviewed: 4 hours 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.