Name: uniprot-database
Rating: 57.599999999999994 (1 reviews)
Author: administrakt0r

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.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/uniprot-database/SKILL.md

The canonical home for this skill is uniprot-database in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

57%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-organized with real endpoints and concrete query examples, giving strong actionability. It is weakened by verbosity/overlap across sections, missing validation for batch ID-mapping, and bundle reference files that are named but absent.

Suggestions

Ship the referenced bundle files (api_fields.md, query_syntax.md, id_mapping_databases.md, api_examples.md, uniprot_client.py) or remove the dangling references, since broken links hurt navigation.

Add an explicit validate/retry step to the ID mapping workflow (e.g. handle a FAILED status and re-submit) to satisfy the batch-operation feedback-loop requirement.

Trim redundancy by collapsing the overlapping Query Syntax Examples and Best Practices material, and drop the encyclopedic Overview sentence about what UniProt is.

Dimension	Reasoning	Score
Conciseness	Well-structured but padded: the Overview restates known facts ('UniProt is the world's leading...') and Core Capabilities, Query Syntax Examples, and Best Practices overlap considerably, so it could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste-ready REST endpoints and query examples (e.g. 'https://rest.uniprot.org/uniprotkb/search?query=...'), with only minor gaps such as the referenced helper script not being provided.	4 / 5
Workflow Clarity	The ID mapping workflow is sequenced (run → status → results) with a status checkpoint, but batch operations (up to 100,000 IDs) lack explicit validation or error-recovery feedback loops, capping this at 3 per the rubric.	3 / 5
Progressive Disclosure	References are clearly signaled in-body and in a Resources section, but the referenced files (/references/*.md, scripts/uniprot_client.py) do not exist, so navigation breaks and substantial detail stays inlined in SKILL.md.	3 / 5
	Total	13 / 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, specific description that names the resource, lists concrete capabilities, and gives explicit when-to-use guidance with a helpful alternative-routing note. The main weakness is a slightly abstract 'when' clause and a few missing natural synonyms.

Suggestions

Make the 'when' clause more concrete by listing triggering user scenarios (e.g. 'Use when retrieving protein sequences, mapping IDs across databases, or querying Swiss-Prot annotations').

Add a couple of natural synonyms such as 'sequence retrieval' or 'protein database' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL' — but omits batch retrieval and field customization, leaving minor coverage gaps versus a comprehensive 5.	4 / 5
Completeness	Clearly states what ('Direct REST API access to UniProt...') and when ('Use this for direct HTTP/REST work or UniProt-specific control'), but the 'when' trigger is somewhat abstract rather than listing concrete user scenarios.	4 / 5
Trigger Term Quality	Includes natural domain terms users would say (protein, FASTA, UniProt, ID mapping, Swiss-Prot/TrEMBL) with good coverage, but misses common synonyms like 'sequence retrieval' or 'protein database'.	4 / 5
Distinctiveness Conflict Risk	Targets a single named resource (UniProt) with distinct triggers, and the bioservices comparison ('For Python workflows with multiple databases, prefer bioservices') sharply reduces overlap risk.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/uniprot-database/SKILL.md
Commit: 900c504

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.