chembl-database

Query the ChEMBL database for bioactive molecules, targets, bioactivities, and approved drugs; use this when you need to filter by physicochemical properties (e.g., MW, LogP), chemical structure (SMILES), or retrieve drug mechanism information.

Quality

76%

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/chembl-database/SKILL.md

Quality

Content

61%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.

A well-structured, largely actionable body with good progressive disclosure and a solid executable example, weakened by redundant prose sections and the absence of validation/feedback checkpoints for database operations.

Suggestions

Consolidate 'When to Use' and 'Key Features' into a single section to remove redundancy and tighten the token budget.

Add a validation/feedback step to the example workflow (e.g., check that query results are non-empty and advise retrying with broader filters or consulting references/api_reference.md on failure).

Trim 'Implementation Details' bullets that merely restate the commented code, keeping only the points not already evident from the example.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the 'Key Features' section largely restates 'When to Use', and 'Implementation Details' re-explains behavior already shown in the code comments, so it could be tightened.	3 / 5
Actionability	Provides a complete, copy-paste-ready Python example covering the five common cases plus a bundled CLI script; minor gaps remain because field names and operators are acknowledged as API-schema-dependent.	4 / 5
Workflow Clarity	A numbered 1–5 sequence is present with one empty-result guard, but there are no validation/feedback checkpoints; as a database-operation skill lacking a validate→fix→retry loop, workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	Well-structured with one-level-deep references to the real bundle files (references/api_reference.md and scripts/query_chembl.py), keeping the bulk API reference external; minor organization gaps from the duplicated When-to-Use/Key-Features sections.	4 / 5
	Total	14 / 20 Passed

Description

92%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.

A strong, third-person description that clearly states what the skill does and when to use it, with concrete actions and domain-specific triggers tied to a distinctive named database.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Query the ChEMBL database for bioactive molecules, targets, bioactivities, and approved drugs', 'filter by physicochemical properties', 'retrieve drug mechanism information' — with comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers both 'what' ('Query the ChEMBL database for bioactive molecules, targets, bioactivities, and approved drugs') and 'when' ('use this when you need to filter by physicochemical properties ... or retrieve drug mechanism information') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain triggers like 'filter by physicochemical properties (e.g., MW, LogP)', 'chemical structure (SMILES)', and 'drug mechanism information', but a few common synonyms (e.g., IC50/Ki/bioactivity as triggers, 'drug discovery') are absent.	4 / 5
Distinctiveness Conflict Risk	Names a specific, well-known data source (ChEMBL) with a clear niche and distinct, domain-specific triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 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/chembl-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.