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

72%

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 ./bundled/skills/chembl-database/SKILL.md

Quality

Content

75%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 comprehensive executable examples and well-signaled references to real bundle files, but it carries some redundancy and time-sensitive padding that hurts conciseness, and inline API-reference content could be pushed to the reference file for cleaner progressive disclosure.

Suggestions

Trim the Overview statistics and the 'When to Use This Skill' list (which duplicate the description) to tighten conciseness toward a 4-5.

Move the 'Filter Operators' listing and the 'Common Use Cases' examples into references/api_reference.md, leaving a concise pointer from the body.

Add a lightweight validation note to the workflows (e.g., check result lists are non-empty before iterating, handle rate-limit responses) to push workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense executable code, but includes some padding — time-sensitive database statistics ('2 million compounds, 19 million bioactivity measurements'), an Overview/When-to-Use section that overlaps the description, and a 'Common Use Cases' section that repeats patterns already shown in Core Capabilities; fits 'mostly efficient but could be tightened'.	3 / 5
Actionability	Abundant copy-paste-ready, executable Python covering molecule/target/activity/similarity/substructure/drug queries plus pandas export and caching configuration; specific examples cover the common cases, matching the 5 anchor.	5 / 5
Workflow Clarity	Three numbered workflows (Finding Inhibitors, Analyzing a Known Drug, SAR Study) give clear sequences with code per step; validation checkpoints are implicit/missing (e.g., no empty-result or rate-limit checks) so it sits at 4 rather than 5, and the operations are read-only so the destructive-cap does not apply.	4 / 5
Progressive Disclosure	Body points clearly to one-level-deep bundle files (scripts/example_queries.py, references/api_reference.md, both verified to exist) with descriptive summaries; minor gap is that substantial API-reference material (Filter Operators, multiple inline examples) is inlined rather than pushed into api_reference.md, keeping it just below 5.	4 / 5
	Total	16 / 20 Passed

Description

70%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 well-targeted to a distinct niche with good natural trigger terms, but it lacks an explicit 'Use when...' trigger clause, which caps completeness at 3. Adding a concrete trigger sentence would raise the overall score.

Suggestions

Add an explicit trigger clause such as 'Use when querying bioactivity data, finding inhibitors or agonists, or performing SAR / drug-discovery lookups against ChEMBL.'

Broaden trigger terms to include synonyms users say: 'agonists', 'drug targets', 'approved drugs', 'bioassays', 'dose-response'.

Optionally name the output capability (e.g., 'export results to pandas DataFrames') to round out specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies') with only minor coverage gaps (e.g., target info, approved-drug lookups not named); not quite comprehensive enough for a 5.	4 / 5
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance — only a weakly implied 'for medicinal chemistry' — so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Strong domain keywords a medicinal chemist would actually say ('bioactive molecules', 'IC50', 'Ki', 'inhibitors', 'SAR', 'medicinal chemistry'); a few common variants are missing ('agonists', 'drug targets', 'approved drugs'), keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	Names the specific ChEMBL database niche with distinct triggers (IC50/Ki, SAR, bioactive molecules), making conflict with other skills minimal; clearly a 5 per the anchor.	5 / 5
	Total	16 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/chembl-database/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.