zinc-database

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

Quality

70%

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/databases/zinc-database/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable API examples and a well-structured one-level-deep reference, but it is somewhat padded with domain background Claude already knows and lacks validation/feedback loops in its batch-operation workflows. Trimming explanatory prose and adding validation checkpoints would raise the weaker dimensions.

Suggestions

Trim background explanations Claude already knows (e.g., the detailed tranche-system description, file-format definitions, Lipinski's Rule of Five) and link to the reference instead.

Add explicit validation/feedback checkpoints to the batch workflows (e.g., verify download completeness and integrity before using 3D structures for docking).

Consolidate the repeated curl patterns into one parameterized example rather than restating near-identical calls across sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but padded with explanations Claude already knows (the tranche system restated, Lipinski's Rule of Five, file-format definitions, and repeated curl patterns), which keeps it above the verbose anchor yet short of a lean every-token-earns-its-place body.	2 / 3
Actionability	Provides fully executable curl commands and complete Python functions with documented parameters and copy-paste-ready examples throughout, matching the top anchor for concrete executable guidance.	3 / 3
Workflow Clarity	Four numbered workflows with code provide a clear sequence, but batch/bulk operations (3D structure downloads, batch retrieval) lack explicit validation or feedback checkpoints, which caps workflow clarity at 2 per the rubric's batch-operations scoring note.	2 / 3
Progressive Disclosure	The body is well-organized into clear sections and points to a single one-level-deep reference (references/api_reference.md) that exists as a real file and is clearly signaled with a summary of its contents, matching the top anchor.	3 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 and clearly niched, but lacks an explicit "Use when..." trigger clause and uses slightly compressed cheminformatics jargon that limits natural trigger-term breadth. Adding an explicit when-to-use clause and expanding trigger phrasings would raise the weaker dimensions.

Suggestions

Append an explicit "Use when..." clause listing natural user triggers (e.g., "Use when searching purchasable compounds, finding analogs, or preparing docking libraries").

Expand trigger terms beyond "ZINC ID/SMILES" to common phrasings users say, such as "compound database", "virtual screening library", or "find similar molecules".

Keep the concrete action list but ensure each capability maps to a recognizable user intent.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery" — matching the anchor for listing several specific actions rather than naming only a domain.	3 / 3
Completeness	The "what" is explicit, but there is no "Use when..." clause or equivalent explicit trigger guidance; the "when" is only implied by the trailing purpose phrase, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes relevant domain terms (SMILES, ZINC ID, virtual screening, docking, analog), but the compressed "ZINC ID/SMILES" phrasing and cheminformatics jargon miss common natural variations a user might say, so it does not reach the broad coverage of the top anchor.	2 / 3
Distinctiveness Conflict Risk	Targets a clear, distinct niche (the ZINC compound database) with specific triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 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/databases/zinc-database/SKILL.md
Commit: dc00e07

Reviewed: 8 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.