zinc-database

Access the ZINC (230M+ purchasable compounds) database when you need to look up compounds by ZINC ID/SMILES, run similarity/analog searches, or download 3D ready-to-dock structures for virtual screening and drug discovery.

Quality

72%

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/zinc-database/SKILL.md

Quality

Content

57%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 action-rich with a genuinely runnable example, but it suffers from duplication, absent validation checkpoints for batch downloads, and an orphaned reference file that the body never points to. Fixing these would lift the skill from competent to strong.

Suggestions

Add a clearly signaled link to references/api_reference.md (e.g., an 'Advanced features' section) so the existing bundle file is discoverable instead of orphaned, and move the inlined tranche/endpoint reference detail there to remove duplication.

Add an explicit validation/retry checkpoint for batch 3D downloads (e.g., verify downloaded .db2.gz files decompress and contain expected compound counts before proceeding) to support error recovery.

Remove the duplicated tranche-encoding explanation (keep it in one place) and tighten 'Implementation Details' so it does not restate the example script.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and terse lists, but tranche encoding is explained twice (docstring plus a dedicated section) and query patterns/parse_tranche duplicate material that also appears in api_reference.md, so several sections could be tightened.	3 / 5
Actionability	Provides a complete runnable Python script with real endpoints/URLs plus concrete curl examples covering the common cases; held below 5 only because dist/adist semantics are hedged ('often used as a threshold-like knob') rather than crisply specified.	4 / 5
Workflow Clarity	A rough sequence exists in the example main() (steps 1-4), but batch 3D-structure downloads and queries have no validation checkpoints or error-recovery loop, and the rubric caps batch operations lacking validation at 3.	3 / 5
Progressive Disclosure	The body is reasonably sectioned, but the bundle file references/api_reference.md is never linked or signaled from the body, and detailed reference material (tranche/endpoint details) is inlined in the body while duplicating the reference file — matching the 'references present but not clearly signaled' anchor.	3 / 5
	Total	13 / 20 Passed

Description

87%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, action-oriented, and explicitly pairs a 'what' with a concrete 'when' trigger clause, placing it among the strong reference examples. Its only weakness is modest keyword/extension coverage relative to the fully comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (ZINC, purchasable compounds) and lists several concrete actions ('look up compounds by ZINC ID/SMILES', 'run similarity/analog searches', 'download 3D ready-to-dock structures'), with only minor grouping of actions rather than full enumeration.	4 / 5
Completeness	Explicitly answers both what (look up compounds, run searches, download 3D structures) and when via the concrete trigger clause 'when you need to look up compounds by ZINC ID/SMILES, run similarity/analog searches, or download 3D ready-to-dock structures'.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ('ZINC ID/SMILES', 'similarity/analog searches', 'virtual screening', 'drug discovery', '3D ready-to-dock structures') that users would actually say, but file extensions (e.g. .mol2, .sdf) and some synonyms are not surfaced.	4 / 5
Distinctiveness Conflict Risk	A clear niche (ZINC purchasable-compounds database, docking-ready 3D structures, virtual screening) with distinct triggers and minimal risk of firing for an unrelated skill.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/zinc-database/SKILL.md
Commit: 63c61d3

Reviewed: 3 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.