uniprot-database

Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For broader biological evidence lookup across databases, use bio-database-evidence. Use this for direct HTTP/REST work or UniProt-specific control.

Quality

70%

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 ./bundled/skills/uniprot-database/SKILL.md

Quality

Content

61%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 well-structured, actionable reference for the UniProt REST API with real endpoints and a helper script, but it carries some padding and lacks validation/feedback loops for the batch ID-mapping workflow. Progressive disclosure is good, with minor inline/reference overlap.

Suggestions

Trim the Overview marketing intro and generic Best Practices items ('Cache results', 'Be respectful of API resources') to tighten conciseness.

Add a validation/feedback loop to the ID mapping workflow: check for FAILED status, surface the error message, and retry or report rather than assuming the job completes.

De-duplicate the inline query-syntax and field examples now that they are fully covered in references/query_syntax.md and references/api_fields.md; keep only one canonical example inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material, but the Overview intro ('world's leading comprehensive protein sequence and functional information resource') and generic Best Practices ('Be respectful of API resources', 'Cache results') add padding Claude does not need.	3 / 5
Actionability	Provides real endpoints, executable query strings, concrete accession formats, and a documented helper script with named functions — mostly executable guidance with only minor gaps.	4 / 5
Workflow Clarity	The ID mapping workflow lists sequenced steps (submit, check status, retrieve results) but is a batch operation (max 100,000 IDs) with no validation/feedback loop, so workflow clarity is capped at 3 per the rubric.	3 / 5
Progressive Disclosure	Clear sectioned overview with well-signaled one-level-deep references to real files (api_fields.md, id_mapping_databases.md, query_syntax.md, api_examples.md) and uniprot_client.py, though query-syntax and field lists appear both inline and in reference files.	4 / 5
	Total	14 / 20 Passed

Description

78%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, concise description that names concrete capabilities and provides explicit use-when guidance plus boundary deconfliction against a sibling skill. The 'when' clause is slightly generic, keeping completeness and trigger quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the UniProt domain and four concrete actions ('Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL'), giving several specific actions with only minor coverage gaps.	4 / 5
Completeness	Clearly states what it does (the four actions) and gives an explicit 'when' ('Use this for direct HTTP/REST work or UniProt-specific control'), but the trigger guidance could be more specific.	4 / 5
Trigger Term Quality	Includes natural terms users would say (protein searches, FASTA, ID mapping, UniProt, REST/HTTP) with good coverage, though a few natural variations like 'protein sequence' are missing.	4 / 5
Distinctiveness Conflict Risk	UniProt-specific niche with explicit boundary deconfliction ('For broader biological evidence lookup across databases, use bio-database-evidence') yields a clear niche with minimal conflict risk.	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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/uniprot-database/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.