uniprot-database

Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.

0.95x

Quality

71%

Does it follow best practices?

Impact

91%

0.95x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bio/uniprot-database/SKILL.md

Quality

Content

63%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 well-structured with concrete endpoints and query examples and a sequenced ID-mapping workflow, but it is dampened by mild padding, a Python helper section that references a non-existent script, and reference links that point to files absent from the bundle.

Suggestions

Remove or trim the Overview's explanatory definition of UniProt and de-duplicate the capability lists repeated across Overview, 'When to Use', and 'Core Capabilities' to tighten token usage.

Either provide the missing scripts/uniprot_client.py and the /references/*.md files, or remove the links to them and inline only what is actually needed, so progressive disclosure navigation is not broken.

Add an explicit error-recovery branch to the ID Mapping workflow (e.g., 'if status is FAILED, resubmit or inspect the job details') and a minimal executable Python requests.get example so guidance is fully actionable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete code blocks, but pads the Overview ('world's leading comprehensive protein sequence and functional information resource') explaining what UniProt is, and repeats capability lists across Overview, When-to-Use, and Core Capabilities sections, so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready query strings, endpoint URLs, field lists, and query-syntax examples that are directly executable, but the Python Implementation section only lists function signatures for a helper script that does not actually exist, leaving a gap in fully executable Python.	4 / 5
Workflow Clarity	The ID Mapping workflow is a clear 3-step sequence (submit, check status, retrieve results) with an explicit status-check checkpoint, but it lacks a defined feedback loop for what to do when a job fails, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Section headers and explicit reference pointers are present, but the referenced bundle files (/references/api_fields.md, query_syntax.md, id_mapping_databases.md, api_examples.md, scripts/uniprot_client.py) do not exist in the bundle, so navigation is broken; additionally, sizeable query-syntax and field-list content is inlined rather than offloaded to those missing references.	3 / 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 tight, third-person description that names concrete capabilities and an explicit use-condition, with smart disambiguation against the bioservices alternative. Its main limitation is an abstract 'when' clause and slightly incomplete action/term coverage rather than any vagueness or over-claim.

Dimension	Reasoning	Score
Specificity	Names the domain (UniProt REST API) and several concrete actions — 'Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL' — but omits streaming, batch retrieval, and field customization, leaving minor coverage gaps rather than comprehensive listing.	4 / 5
Completeness	Both 'what' (direct REST API access with named capabilities) and 'when' ('Use this for direct HTTP/REST work or UniProt-specific control') are present, but the 'when' clause is abstract rather than concrete user trigger phrases, so it falls just below the explicit-trigger anchor of 5.	4 / 5
Trigger Term Quality	Includes natural domain terms users would say ('Protein searches', 'FASTA retrieval', 'ID mapping', 'Swiss-Prot/TrEMBL', 'REST API') plus the FASTA format, but is missing common synonyms and explicit file extensions, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves a clear UniProt-specific niche and actively reduces overlap by advising bioservices for multi-database Python workflows, giving it distinct triggers with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/uniprot-database/SKILL.md
Commit: df37802

Reviewed: 7 hours 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.