interpro-database

Identify domains, families, and sites in proteins; find all proteins in a family or sharing a domain; explore species distribution for a domain; annotate genomes with protein families and GO terms. InterPro combines 14 databases (e.g., Pfam, CDD) into one searchable resource. InterPro-N significantly expands annotation and sequence coverage with deep learning. Includes domain architecture (IDA) search.

Quality

83%

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

85%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 dense, actionable API skill with excellent code examples, clear multi-step workflows, and well-structured progressive disclosure; the main weakness is conceptual prose explaining biology Claude largely already knows.

Suggestions

Trim the 'InterPro Entry Types' definitions and the InterPro-N 'panoptic segmentation' conceptual explanation to the minimum needed for correct usage, removing textbook biology Claude already knows.

Consider moving the inline per-endpoint parameter lists fully into references/api_reference.md, keeping SKILL.md to the high-level endpoint map and one example per endpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable reference material, but it explains textbook biology Claude already knows (entry-type definitions like 'A group of proteins sharing a common evolutionary origin') and conceptual InterPro-N prose ('panoptic segmentation task, labeling residues') that could be tightened.	2 / 3
Actionability	Provides fully executable CLI invocations and Python snippets with concrete flags and arguments (e.g., the 4 endpoint constructions and IDA examples), copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Multi-step processes are explicitly sequenced (the two-step ida_search then ida workflow) with a clear InterPro-N fallback feedback loop and an explicit 'NEVER iterate to count' validation rule.	3 / 3
Progressive Disclosure	SKILL.md is an overview with well-signaled, one-level-deep references to real files (references/api_reference.md and references/example_responses.tsv) and a real scripts/interpro_client.py wrapper, with exhaustive detail appropriately split out.	3 / 3
	Total	11 / 12 Passed

Description

82%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 specific, capability-rich description for a clearly distinct bioinformatics skill, weakened only by the absence of an explicit 'when to use' trigger clause.

Suggestions

Append a 'Use when...' clause stating when Claude should reach for this skill (e.g., when the user asks to find domains/families in proteins, explore species distribution, or annotate genomes with protein families and GO terms).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Identify domains, families, and sites in proteins; find all proteins in a family or sharing a domain; explore species distribution for a domain; annotate genomes with protein families and GO terms'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' with concrete capabilities but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Uses natural bioinformatics terms a user would say ('domains', 'families', 'protein family', 'species distribution', 'GO terms', 'genomes', 'InterPro'), giving good coverage rather than opaque jargon.	3 / 3
Distinctiveness Conflict Risk	The InterPro protein-family/domain annotation niche is specific and distinctive, with triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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/interpro_database/SKILL.md
Commit: 0b42509

Reviewed: 7 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.