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

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/interpro_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 examples and a well-organized reference structure, but carries some conceptual padding and could be tighter. Workflow sequencing is clear, though error-recovery checkpoints are mostly implicit rather than explicit validate-then-proceed loops.

Suggestions

Trim conceptual padding — the Overview paragraph and the InterPro-N deep-learning architecture description ('panoptic segmentation') explain things Claude already understands; keep only usage-relevant detail.

Add an explicit validate/retry checkpoint for the common failure modes the wrapper already handles (429/408), e.g., a short 'If a query stalls or rate-limits, the wrapper retries; for count queries always use the count subcommand' feedback loop.

Move more of the per-endpoint parameter detail out of the inlined Quick Reference into references/api_reference.md, leaving only the most common parameters inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient API-specific material, but includes conceptual padding Claude doesn't need — e.g., the Overview paragraph on uniting member databases and the InterPro-N 'panoptic segmentation' architecture explanation — so it could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready CLI and Python examples cover the common cases (fetch/count, linked endpoints, IDA search, InterPro-N flag), with explicit correct/wrong patterns for counting.	5 / 5
Workflow Clarity	Clear sequencing for multi-step processes (IDA Step 1 → Step 2) and explicit do/don't lookup rules with correct/wrong examples; the skill is read-only so the destructive/batch validation cap does not apply, but general error-recovery checkpoints are only implicit.	4 / 5
Progressive Disclosure	Good structure with well-signaled one-level-deep references to real bundle files (references/api_reference.md, references/example_responses.tsv) and scripts/interpro_client.py; some parameter detail is still inlined in the Quick Reference that could be further offloaded.	4 / 5
	Total	16 / 20 Passed

Description

75%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, action-oriented, and clearly distinct, but it omits any explicit 'Use when...' trigger guidance, which caps completeness. Voice is appropriately third-person/imperative with no first/second person.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when identifying protein domains/families, finding proteins that share a domain, exploring species distribution, or annotating genomes with GO terms').

Include a few synonym or file-style trigger terms users might say (e.g., 'Pfam', 'InterProScan-style annotation', 'domain architecture') to broaden trigger coverage.

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' — plus IDA search, giving comprehensive coverage.	5 / 5
Completeness	Clearly answers 'what' with several concrete capabilities, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Strong domain-natural terms ('protein family', 'domain', 'species distribution', 'annotate genomes', 'GO terms') that a bioinformatician would actually say, but missing common synonyms or accession-style triggers; not the full 5-level coverage.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (InterPro protein domain/family annotation, InterPro-N deep-learning predictions, IDA search) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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: 6883275

Reviewed: 4 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.