molecular-dynamics

Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces). For structural biology, drug binding, and biophysics.

Quality

77%

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 ./skills/molecular-dynamics/SKILL.md

Quality

Content

71%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 content is highly actionable with complete, executable code and a clear workflow, but it is somewhat verbose and fails to use its existing reference file for progressive disclosure, inlining content that should be split out.

Suggestions

Link the existing references/mdanalysis_analysis.md from the body (e.g., 'See [mdanalysis_analysis.md](references/mdanalysis_analysis.md) for selection language, H-bonds, PCA, and FES details') and move the inlined advanced analyses there.

Trim concept explanations Claude already knows (the Newton's-equations overview, NVT/NPT definitional docstrings) to improve token efficiency.

Add explicit validation gates between workflow stages (e.g., 'Confirm energy has converged before starting NPT') to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but includes explanations Claude already knows ('integrating Newton's equations of motion', docstrings restating NVT/NPT meaning) and a padded 'Best Practices' list that could be trimmed.	3 / 5
Actionability	Provides fully executable, copy-paste-ready functions covering the common cases (system prep, minimization, NVT/NPT, RMSD/RMSF, contacts) with concrete args and return values.	5 / 5
Workflow Clarity	Clear numbered sequence (preparation → minimization → NVT → NPT → analysis) with checkpoints implicit via energy prints and checkpoint reporters, but lacks explicit 'validate then proceed' gates between stages.	4 / 5
Progressive Disclosure	Has section structure, but a reference file (references/mdanalysis_analysis.md) exists yet is never linked or signaled from the body, and MDAnalysis content that belongs in the reference is inlined instead of split out.	3 / 5
	Total	15 / 20 Passed

Description

83%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 concrete, tool-specific, and well-targeted with multiple specific actions and a clear niche. Its main gap is the lack of an explicit 'Use when...' trigger clause and missing file-extension keywords.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when running or analyzing MD simulations, or when the user mentions trajectories, RMSD/RMSF, or .dcd/.xtc files') to push completeness to a 5.

Include common file extensions (.pdb, .dcd, .xtc, .nc) and synonyms ('MD', 'trajectory analysis') to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces)') with comprehensive coverage.	5 / 5
Completeness	Clearly states the 'what' with concrete actions and provides a domain 'when' ('For structural biology, drug binding, and biophysics'), but it is a domain list rather than an explicit 'Use when...' trigger clause, so it falls just short of the 5 anchor.	4 / 5
Trigger Term Quality	Good natural-term coverage ('molecular dynamics simulations', 'RMSD', 'RMSF', 'drug binding', 'structural biology') but missing file extensions like .dcd/.xtc/.pdb and common synonyms such as 'MD' or 'trajectory analysis'.	4 / 5
Distinctiveness Conflict Risk	Names specific tools (OpenMM, MDAnalysis) and a distinct MD-simulation niche with named analyses, giving it clear triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 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/molecular-dynamics/SKILL.md
Commit: 1e5eeff

Reviewed: 4 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.