chembl-database

Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.

Quality

82%

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

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.

A highly actionable, well-organized API skill body with concrete commands throughout, held back by some inline reference bulk and missing error-recovery guidance in the workflow. The core command examples are a strong model for actionability.

Suggestions

Move the "Full subcommand list" (with per-endpoint searchable flags) into references/api_endpoints.md and keep only the primary subcommand summary in SKILL.md to reduce duplication and inline bulk.

Add an explicit feedback loop to the Workflow, e.g. "If `status` fails or returns an error, wait and retry once before proceeding" and a note on handling empty paginated results.

Fix the inline command formatting where the literal `bash` prefix is baked into the code span (e.g. `bash uv run ...`) so examples are copy-paste ready, and consolidate the --output requirement into one location.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and command-focused, but the "Key subcommands at a glance" and "Full subcommand list" sections duplicate each other, and the required --output rule is restated in multiple places.	2 / 3
Actionability	Nearly every section gives concrete, executable `uv run scripts/chembl_api.py ...` invocations with real IDs, filters, and output paths, plus fenced copy-paste examples for status and pagination.	3 / 3
Workflow Clarity	The 8-step Workflow is clearly sequenced and opens with a status validation checkpoint, but it lacks explicit error-recovery feedback loops (e.g., what to do when status/pagination fails).	2 / 3
Progressive Disclosure	There is a clearly signaled one-level reference (references/api_endpoints.md), but the large inline "Full subcommand list" with per-endpoint searchable flags is reference-grade material that lives in the main file.	2 / 3
	Total	9 / 12 Passed

Description

100%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, third-person description that concretely names capabilities and provides explicit "Use when" triggers with natural keywords. No significant weaknesses relative to the rubric anchors.

Dimension	Reasoning	Score
Specificity	"Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures" lists multiple concrete data types/actions rather than vague language.	3 / 3
Completeness	It explicitly states what ("Query the ChEMBL database for...") and when ("Use when the user asks about...") with explicit trigger guidance.	3 / 3
Trigger Term Quality	"compounds, targets, IC50/Ki values, drug mechanisms, or structure searches" covers natural terms a user would actually say, including common assay-value phrasings.	3 / 3
Distinctiveness Conflict Risk	The ChEMBL-specific niche and concrete trigger terms make it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/chembl_database/SKILL.md
Commit: 0b42509

Reviewed: 8 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.