molecule-visualization

Publication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.

Quality

78%

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/molecule-visualization/SKILL.md

Quality

Content

86%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 an actionable, well-organized reference with copy-paste-ready commands for every workflow and a clean one-level-deep reference structure. Minor conciseness gains are available by trimming redundancy between the intro and 'When to Use', and explicit validation checkpoints would lift workflow clarity further.

Suggestions

Trim redundancy between the opening paragraph and the 'When to Use' list, which restate the same capability set.

For read-only batch operations like molecule grids, note a quick validation step (e.g. confirming the CSV parsed and all SMILES rendered) to add an explicit checkpoint.

Optionally fold the inline Style Guide bullet list into the reference pointer to keep the overview leaner.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with task-oriented sections and executable examples that assume Claude's competence (no explanations of what SMILES, PDB, or RDKit are); minor redundancy where the intro paragraph and 'When to Use' restate capabilities already in the description.	4 / 5
Actionability	Every workflow ships copy-paste-ready bash commands with realistic flags and example inputs (SMILES, file paths, options), and the script reference table maps each script to its key inputs, covering the common cases.	5 / 5
Workflow Clarity	Seven workflows are clearly delineated by script and flags with realistic sequencing, but each is an independent single-script invocation with no validation or error-recovery checkpoints; no destructive/batch context triggers the lower cap.	4 / 5
Progressive Disclosure	A clear overview points one level deep to the verified references/style_guide.md via a well-signaled section with a bulleted summary of its contents, while scripts are organized under scripts/ and referenced by path, giving easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

71%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 conveys a strong, specific set of capabilities but lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger terms are good but omit user-natural synonyms and relevant file extensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when generating publication figures of molecules, SAR grids, scaffolds, protein-ligand interactions, or interactive 3D viewers.'

Include natural trigger phrases and file extensions a user would actually say, such as 'draw molecules', 'depict structures', and .pdb/.sdf/.smi/.csv.

Consider adding a brief mention of the target audience or domains (drug discovery, medicinal chemistry) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists five concrete, distinct capabilities (2D structure drawings, molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, interactive 3D views), giving comprehensive coverage of the skill's actions.	5 / 5
Completeness	The 'what' is clear and concrete, but there is no explicit 'Use when...' clause or equivalent trigger guidance; the 'when' is only weakly implied from the capability list, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Strong natural terms ('molecular visualization', 'scaffold highlighting', 'protein-ligand interaction diagrams', 'interactive 3D views'), but missing common synonyms a user might say ('draw molecules', 'depict structures') and relevant file extensions (.pdb, .sdf, .smi, .csv).	4 / 5
Distinctiveness Conflict Risk	A clear niche (publication-quality molecular visualization for drug discovery) with mostly distinct triggers; only minor overlap risk with adjacent chemistry or rendering skills.	4 / 5
	Total	16 / 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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/molecule-visualization/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.