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.

2.36x

Quality

73%

Does it follow best practices?

Impact

90%

2.36x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/pharma/zinc-database/SKILL.md

Quality

Content

65%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.

Highly actionable content with executable curl and Python examples and clear workflow sequencing, but it is padded in places, omits validation checkpoints for batch operations, and leans monolithic with a broken reference path.

Suggestions

Collapse the 9 overlapping "When to Use" bullets and remove the promotional K-Dense Web section to tighten the token budget.

Add explicit validation steps to the batch workflows (e.g., check the curl exit status / non-empty tabular output before parsing into pandas).

Move the full API reference and Python integration into a real references/ file and link to it, so the signaled references actually exist on disk.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete endpoints and code, but padded by 9 overlapping "When to Use" bullets, restated capabilities, and a promotional K-Dense Web section; could be tightened. Not level 3 because not every token earns its place, and not level 1 because the bulk is concrete API/working guidance rather than concept explanation.	2 / 3
Actionability	Provides fully executable curl commands and Python functions with parameters and example responses — copy-paste ready, matching the level-3 anchor.	3 / 3
Workflow Clarity	Workflows 1–4 are numbered and sequenced, but batch/download operations lack explicit validation or verification checkpoints (e.g., confirm the curl returned valid rows before parsing), which caps workflow clarity at 2 per the batch-operation guideline.	2 / 3
Progressive Disclosure	Sections provide some structure, but the full API reference, Python integration, tranche system, and disclaimers are inline rather than split out, and the one signaled reference ("references/api_reference.md") does not exist on disk. Not level 3 because content that should be separate is inline and navigation is not backed by real files; not level 1 because sectioning is present.	2 / 3
	Total	9 / 12 Passed

Description

82%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.

A strong, specific description in third person with good trigger terms and a clear niche, but it lacks an explicit "Use when..." clause so the use-when guidance is only implied rather than stated.

Suggestions

Add an explicit trigger clause such as "Use when searching purchasable compounds by ZINC ID or SMILES, running similarity/analog searches, or preparing 3D-ready docking libraries."

Keep the concrete action list but ensure the when-to-use phrasing mirrors how a user would phrase the request (e.g., "find analogs", "get docking-ready structures").

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery" — matching the level-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but offers only an implied "when" via "for virtual screening and drug discovery"; there is no explicit "Use when..." trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes natural domain terms a user would say — "ZINC", "SMILES", "similarity searches", "docking", "virtual screening and drug discovery" — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The ZINC database niche with purchasable-compound triggers is distinct and unlikely to fire for unrelated skills, matching the level-3 anchor.	3 / 3
	Total	11 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/zinc-database/SKILL.md
Commit: df37802

Reviewed: 18 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.