CtrlK
BlogDocsLog inGet started
Tessl Logo

pubchem-database

Query PubChem, search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics. Use when a user asks about a specific chemical, drug, or molecule.

80

Quality

100%

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

100%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.

The body is highly actionable, concise, and well-structured with executable examples for every capability and clear pointers to two real reference files. It is a strong, token-efficient skill body.

DimensionReasoningScore

Conciseness

Lean and action-oriented throughout; it never explains concepts Claude already knows and every section earns its place, though the 12 numbered capabilities are dense but not padded.

3 / 3

Actionability

Each capability ships a complete, copy-paste-ready 'uv run scripts/pubchem_api.py ...' command with real arguments and an output flag — fully executable, not pseudocode.

3 / 3

Workflow Clarity

Prerequisites are numbered with a gating notification step, Core Rules enforce wrapper/fact-verification, and fallback strategies are explicit; operations are non-destructive reads so the absence of retry loops does not apply.

3 / 3

Progressive Disclosure

SKILL.md is an overview that points to real one-level-deep references (references/endpoints.md, references/workflows.md), clearly signaled and well-organized; verified the referenced files exist.

3 / 3

Total

12

/

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.

The description is concise, third-person, and specific, clearly stating both capabilities and an explicit use-when trigger with natural user terms. It is among the strongest examples in the rubric.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity' — matching the multi-action score-3 anchor; not vague.

3 / 3

Completeness

Explicitly answers both what ('Query PubChem, search..., retrieve...') and when ('Use when a user asks about a specific chemical, drug, or molecule'), with an explicit 'Use when' trigger.

3 / 3

Trigger Term Quality

Includes natural user terms ('chemical, drug, or molecule') plus technical handles (CID/SMILES), giving good coverage of phrases a user would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear PubChem/cheminformatics niche with distinct chemical/drug/molecule triggers, unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
google-deepmind/science-skills
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.