CtrlK
BlogDocsLog inGet started
Tessl Logo

proteomexchange-skill

Submit compact ProteomeXchange PROXI requests for datasets, libraries, peptidoforms, proteins, PSMs, spectra, and USI examples. Use when a user wants concise PROXI summaries

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 compact, well-structured skill body for a single-purpose read-only API client that is largely executable and clearly organized. Small improvements could come from de-duplicating the base_url in examples and showing the save_raw path as an executable example.

Suggestions

De-duplicate the base_url across the Common PROXI patterns examples (e.g. reference 'the base_url above') to tighten conciseness.

Add an executable bash example demonstrating the save_raw=true workflow and reporting the saved raw_output_path, since it is currently only described in prose.

Consider one or two natural-language synonyms (e.g. 'proteomics data', 'mass-spectrometry datasets') in the description's trigger to broaden trigger-term coverage.

DimensionReasoningScore

Conciseness

Lean and free of concept over-explanation, assuming Claude's competence, but the base_url is repeated verbatim across three example payloads where a reference to 'the base_url above' would trim tokens.

4 / 5

Actionability

Provides a copy-paste-ready bash command and concrete JSON patterns for the common cases, but the save_raw=true / raw_output_path workflow is described only in prose without an executable example, a minor gap.

4 / 5

Workflow Clarity

A simple single-purpose read-only skill with an unambiguous Input -> run script -> Output flow, including explicit failure handling (ok=false with error.code/message); the simple-skill exception applies and no destructive-operation cap is triggered.

5 / 5

Progressive Disclosure

Well-organized into clear sections (Operating rules, Execution behavior, Input, Output, Execution, References) with a single one-level-deep bundle reference (scripts/rest_request.py, verified present) and no nested references.

5 / 5

Total

18

/

20

Passed

Description

87%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 well-targeted, explicit description for a specialized API skill with a concrete Use-when trigger and strong distinctiveness. The main limitation is a narrow action vocabulary and absence of synonym variants in the trigger terms.

DimensionReasoningScore

Specificity

Names the domain and several concrete targets (datasets, libraries, peptidoforms, proteins, PSMs, spectra, USI examples) plus two actions (submit PROXI requests, get concise summaries), but the action vocabulary is narrow, so it falls short of the comprehensive multi-action anchor 5.

4 / 5

Completeness

Clearly states what the skill does (submit compact PROXI requests for the listed entities) and provides an explicit 'Use when a user wants concise PROXI summaries' trigger clause with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Good coverage of natural domain terms a proteomics user would actually say (ProteomeXchange, PROXI, datasets, spectra, USI, PSMs), though it lacks synonym variants and equivalent file/extension forms that would reach anchor 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (ProteomeXchange PROXI API) with distinct triggers (PROXI, ProteomeXchange) that no other general skill would match, giving minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.