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

73%

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/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 executable code and well-signaled references to real bundle files, but is somewhat verbose and the batch/API workflows lack validation checkpoints, capping workflow clarity.

Suggestions

Trim the Overview statistics and reduce duplication between Common Use Cases, Workflows, and Core Capabilities to tighten token usage.

Add validation/error-handling checkpoints to the workflows (e.g. check that target matches were found before iterating activities, handle pagination limits, verify non-empty results).

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code examples, but the Overview restates ChEMBL facts Claude likely knows (e.g. 'manually curated database', compound/target counts) and sections like Performance Optimization and Common Use Cases duplicate patterns already shown, adding padding.	3 / 5
Actionability	Fully executable, copy-paste ready code throughout — molecule/target/activity/similarity filters, filter operators table, DataFrame export — covering the common cases with specific endpoint calls and parameters.	5 / 5
Workflow Clarity	Three numbered workflows are clearly sequenced, but operations are effectively batch/read queries against a live API with no validation checkpoints or error-handling/feedback loops; the guidelines flag missing validation for batch/database operations, capping this at 3.	3 / 5
Progressive Disclosure	Good structure with a Resources section that clearly signals one-level-deep references to scripts/example_queries.py and references/api_reference.md (both real files), keeping the bulk of detail offloaded; minor gaps as several inlined examples overlap the bundled files.	4 / 5
	Total	15 / 20 Passed

Description

71%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 with strong concrete actions, but lacks an explicit 'Use when...' trigger clause, capping completeness. Trigger term coverage is good though missing a few synonyms.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when querying ChEMBL for bioactive molecules, drug targets, IC50/Ki activity data, or similar compounds for medicinal chemistry research.'

Include additional natural synonyms a user might say, such as 'molecules', 'drug targets', 'assays', or 'similar compounds'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Search compounds by structure/properties', 'retrieve bioactivity data (IC50, Ki)', 'find inhibitors', 'perform SAR studies' — with comprehensive coverage of the ChEMBL domain.	5 / 5
Completeness	The 'what' is clearly stated (query ChEMBL, search compounds, retrieve bioactivity, find inhibitors, perform SAR), but there is no explicit 'when' or 'Use when...' clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural terms (compounds, bioactivity, IC50, Ki, inhibitors, SAR, medicinal chemistry) but misses common synonyms/variations a user might say (e.g. 'drug targets', 'assays', 'molecules', 'similar compounds').	4 / 5
Distinctiveness Conflict Risk	ChEMBL-specific triggers (IC50, Ki, bioactivity, inhibitors, SAR, medicinal chemistry) establish a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 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/chembl-database/SKILL.md
Commit: 3a6c3a9

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.