CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/databases/uniprot-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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-organized, actionable skill body that leverages reference files for bulk detail and provides concrete endpoints and query examples. The main gap is missing validation/error-recovery feedback loops for batch operations like ID mapping, which caps workflow clarity.

Suggestions

Add an explicit validation/error-recovery step to the ID mapping workflow (e.g., 'If status returns FAILED, inspect the submission payload and resubmit; poll status until COMPLETED before retrieving results').

Reduce overlap between inline 'Query Syntax Examples' and /references/query_syntax.md by keeping only a brief representative sample inline and pointing to the reference for the rest.

Convert the search examples into a single copy-paste-ready Python snippet using the provided helper script to lift actionability from 4 to 5.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete endpoints and examples rather than padding, though the inline 'Query Syntax Examples' and 'Common search patterns' sections duplicate content that also lives in references and could be trimmed.

4 / 5

Actionability

Provides concrete REST endpoints, executable query strings, an ID mapping step sequence, and a helper script with documented function signatures — minor gaps only (examples are query strings rather than full copy-paste scripts).

4 / 5

Workflow Clarity

The ID mapping workflow is sequenced (submit, status, results) but batch operations (ID mapping up to 100,000 IDs, batch retrieval) lack explicit validation/error-recovery feedback loops, capping this per the batch-operations rule.

3 / 5

Progressive Disclosure

Good structure with an overview plus four clearly signaled one-level-deep reference files and a script, though some inline query-syntax and field examples overlap with the dedicated reference files.

4 / 5

Total

15

/

20

Passed

Description

83%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, specific description with concrete capabilities and a clear use-when clause plus a helpful disambiguation pointer to bioservices. The main weakness is the 'when' guidance being framed in technical terms rather than concrete user trigger phrases.

Suggestions

Make the 'Use this for...' clause more concrete with user-facing trigger phrases (e.g., 'Use when the user asks for protein sequences, UniProt accessions, FASTA downloads, or cross-database ID mapping').

Add common synonyms or file extensions (e.g., .fasta, protein sequences, UniProtKB) to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Has a clear 'what' (direct REST API access + concrete actions) and an explicit 'Use this for...' when clause, but the when is somewhat technical rather than concrete user-situation trigger phrases.

4 / 5

Trigger Term Quality

Good domain keywords (FASTA, ID mapping, Swiss-Prot/TrEMBL, HTTP/REST, UniProt) that users would naturally say, but missing some synonyms and file extensions like .fasta.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (direct UniProt REST access) and the explicit redirect to bioservices for multi-database workflows actively reduces conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
synthetic-sciences/openscience
Reviewed

Table of Contents

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.