CtrlK
BlogDocsLog inGet started
Tessl Logo

uniprot-database

Direct REST API access to UniProt for protein search, entry retrieval, and identifier mapping; use when you need programmatic UniProtKB queries or cross-database ID conversion.

65

Quality

79%

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 ./scientific-skills/Evidence Insight/uniprot-database/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-structured, actionable skill body with executable code covering all advertised features and real external reference files for query syntax and API fields. The main gap is missing explicit validation/retry feedback loops for the async ID-mapping batch operation.

Suggestions

Add an explicit validation step in the ID-mapping workflow: after fetching results, check for empty/failed mappings and surface a clear error before returning, with a retry-with-backoff path.

Contextualize the reference files inline where the relevant parameter is introduced (e.g., link query_syntax.md right at the `query` parameter) rather than only listing them under Key Features.

Trim redundancy between the Example Usage code and the Implementation Details section by letting the prose focus only on constraints and gotchas not already visible in the code.

DimensionReasoningScore

Conciseness

The body is mostly efficient with well-organized sections and tight inline code, but the 'Implementation Details' section partially restates endpoint usage already shown in the code example, adding some redundancy.

4 / 5

Actionability

It provides executable, copy-paste-ready Python covering search, retrieval, and the full async ID-mapping workflow with real endpoints and parameters; minor gaps (e.g., no retry/backoff, no pagination handling) keep it just below 5.

4 / 5

Workflow Clarity

The ID-mapping async workflow is clearly sequenced (submit -> poll -> fetch) with failure handling on a FAILED status, but it lacks an explicit validation checkpoint confirming successful non-empty results before use, and the batch mapping operation has no retry/empty-result feedback loop.

4 / 5

Progressive Disclosure

Good structure with clear sections and real one-level-deep references (references/query_syntax.md, references/api_fields.md) that exist as files; bulk query/API detail is appropriately externalized, though references are listed rather than contextualized inline where they matter most.

4 / 5

Total

16

/

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 that clearly states concrete capabilities and includes an explicit 'use when' trigger for programmatic UniProt access and ID conversion. It could be marginally stronger with a few more natural synonyms and identifier tokens in the trigger.

Suggestions

Add natural synonyms and concrete identifier examples to the trigger, e.g., 'use when you need to look up UniProt accessions or convert Ensembl/RefSeq/gene names to UniProt IDs'.

DimensionReasoningScore

Specificity

Multiple concrete actions are explicitly named — 'protein search, entry retrieval, and identifier mapping' and 'cross-database ID conversion' — with concrete target domains (UniProtKB, cross-database IDs).

5 / 5

Completeness

The 'what' is explicit and the 'when' is provided via the 'use when you need programmatic UniProtKB queries or cross-database ID conversion' clause, but the when-clause is moderately specific rather than fully concrete with trigger phrases.

4 / 5

Trigger Term Quality

Natural terms like 'protein search', 'identifier mapping', 'ID conversion', and 'UniProtKB queries' are present and user-natural, but synonyms and concrete identifier tokens (e.g., accession, Ensembl/RefSeq IDs) are absent from the description.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (programmatic UniProt REST access / ID mapping) unlikely to trigger for unrelated skills; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.