CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

A highly actionable, well-structured API skill whose command catalog is copy-paste ready in most sections. The main gaps are the inconsistent "bash"-prefixed inline code formatting, the inline subcommand catalog duplicating the reference file's role, and the orphaned citation.bib reference.

Suggestions

Convert the inline "bash uv run ..." code spans in sections 2–6 and 8 into fenced bash code blocks so every example is copy-paste executable.

Move the full subcommand list (section 10) into references/api_endpoints.md and keep only the "key subcommands at a glance" summary in SKILL.md to cut duplication and token cost.

Either link references/citation.bib from the body (e.g., a Citation section) or remove it from the bundle so every reference file is discoverable.

DimensionReasoningScore

Conciseness

The body is dominated by lean, executable command examples with essentially no explanation of concepts Claude already knows, but the ~40-line full subcommand list and decorative horizontal rules between every section could be trimmed or pushed to the reference file.

4 / 5

Actionability

Nearly every section gives concrete, runnable commands with realistic IDs and filters, but sections 2–6 and 8 wrap commands in inline code spans prefixed with a literal "bash" (e.g. "`bash uv run scripts/chembl_api.py molecule --id CHEMBL25 ...`") which breaks copy-paste execution, unlike the proper fenced blocks in sections 1, 7, and 9.

4 / 5

Workflow Clarity

The 8-step Workflow section gives a clear, ordered sequence beginning with a status check, and the "Output to File" rule plus "read the output file" step act as checkpoints; however, there are no explicit error-recovery or re-check loops (acceptable here since all operations are read-only queries, so the destructive/batch cap does not apply).

4 / 5

Progressive Disclosure

Sections are well organized with a clearly signaled one-level reference to references/api_endpoints.md (verified to exist and be relevant), but the body still inlines the full subcommand/searchability catalog that naturally belongs in that reference, and references/citation.bib is present in the bundle yet never linked from the body.

4 / 5

Total

16

/

20

Passed

Description

87%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 description that pairs a concrete capability statement with an explicit, well-phrased "Use when" trigger clause in third-person voice. The only refinement opportunities are broadening the action verbs beyond "Query" and adding a few more synonym triggers.

DimensionReasoningScore

Specificity

The description lists several specific capabilities ("bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures"), but relies on a single action verb ("Query") with similarity/substructure only implied by "structure searches", which leaves minor gaps versus the comprehensive multi-action anchor.

4 / 5

Completeness

It clearly answers both "what" ("Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures") and "when" ("Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches") with explicit, concrete trigger phrases — a textbook match for the top anchor.

5 / 5

Trigger Term Quality

Triggers like "compounds, targets, IC50/Ki values, drug mechanisms, or structure searches" are natural phrases users would say, but common synonyms such as "potency", "EC50", "ligand", or "drug lookup" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

Naming "the ChEMBL database" plus domain-specific triggers like "IC50/Ki values" carves out a clear niche with minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

google-deepmind/science-skills

Path

skills/chembl_database/SKILL.md

Reviewed

Table of Contents

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.