chembl-database

Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.

Quality

71%

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/chembl-database/SKILL.md

Quality

Content

68%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 highly actionable with extensive executable examples and good progressive disclosure to real bundle files, but it is somewhat redundant across sections and lacks validation/checkpoint steps in its workflows. Trimming repeated examples and adding verification steps would lift the weaker dimensions.

Suggestions

Consolidate the overlapping examples across 'Core Capabilities', 'Query Workflow', and 'Common Use Cases' to remove redundancy and tighten token use.

Add explicit validation/checkpoint steps to the workflows (e.g. verify result counts, check data_validity_comment, confirm pagination exhaustion) to raise workflow clarity.

Remove or relocate the promotional K-Dense Web paragraph, which is non-instructional padding that hurts conciseness without aiding task execution.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-forward content, but 'Core Capabilities', 'Query Workflow', and 'Common Use Cases' sections repeat overlapping query patterns, and the promotional K-Dense Web block adds non-instructional padding.	3 / 5
Actionability	Provides numerous copy-paste-ready, executable Python snippets covering molecule/target/activity/structure/drug queries, filter operators, and pandas export — fully concrete and runnable.	5 / 5
Workflow Clarity	Three workflows are clearly numbered and sequenced, but none include validation checkpoints or feedback loops, and batch loops (kinase inhibitors, drug repurposing) risk API hammering without explicit guardrails.	3 / 5
Progressive Disclosure	Well-organized sections with two real, clearly signaled one-level-deep bundle files (scripts/example_queries.py, references/api_reference.md) whose contents are summarized in the body; minor gaps where some reference-grade detail is inlined.	4 / 5
	Total	15 / 20 Passed

Description

75%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 and distinctive, naming ChEMBL and several concrete query actions, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Adding trigger guidance would raise the score.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when querying ChEMBL for bioactive molecules, IC50/Ki values, inhibitors, or SAR data for medicinal chemistry.'

Include a few more natural synonyms users might say ('drug targets', 'bioassays', 'compound screening') to broaden trigger coverage.

Mention the ChEMBL database name as an explicit trigger so users who name ChEMBL directly land on this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clear and comprehensive, but there is no 'Use when...' clause or equivalent explicit trigger guidance — only a weakly implied 'for medicinal chemistry' — so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Strong domain keywords a medicinal chemist would naturally say ('compounds', 'bioactivity', 'IC50', 'Ki', 'inhibitors', 'SAR', 'medicinal chemistry'), but a few natural synonyms and the database name as a trigger are under-represented.	4 / 5
Distinctiveness Conflict Risk	Names the specific ChEMBL database with distinct bioactivity/medicinal-chemistry triggers, giving a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/chembl-database/SKILL.md
Commit: 4902409

Reviewed: 6 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.