aeon

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%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, highly actionable reference skill with excellent progressive disclosure and mostly executable code, weakened by redundancy across sections and the absence of explicit validation checkpoints in its workflows.

Suggestions

Remove the redundancy between the per-capability 'Algorithm Selection' lists and the consolidated 'Algorithm Selection Guide' in Best Practices — keep one location and cross-reference it to tighten the body.

Trim or move 'Common Workflows' examples that re-demonstrate the classification pipeline and feature-extraction+ML already shown in Core Capabilities, or relocate them to a reference file.

Add explicit validation checkpoints to the model-building workflow (e.g. train/test split -> evaluate accuracy -> if below baseline, tune hyperparameters and re-evaluate) instead of listing validation only as a best-practice tip.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy and free of basic-concept prose padding, but structural redundancy (per-capability 'Algorithm Selection' lists duplicated by a consolidated 'Algorithm Selection Guide', and 'Common Workflows' re-demonstrating classification/feature-extraction shown in Core Capabilities) means it could be meaningfully tightened, fitting the 3-anchor over the 4-anchor.	3 / 5
Actionability	Most quick-start blocks are copy-paste ready with real imports and dataset loaders (e.g. RocketClassifier + load_classification('GunPoint')), but several snippets (anomaly detection, segmentation, similarity search) call fit_predict on an undefined 'y', a minor gap that keeps it below fully-executable.	4 / 5
Workflow Clarity	Numbered steps exist in 'Data Preparation' and 'Model Selection' and validation is mentioned as a tip, but the workflows lack explicit validation checkpoints or validate->fix->retry feedback loops, fitting 'steps listed but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references: each capability section links to its references/<topic>.md file, all 11 referenced files exist, and a consolidated 'Reference Documentation' index makes navigation easy.	5 / 5
	Total	15 / 20 Passed

Description

100%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.

An exemplary description: third-person voice, comprehensive concrete capabilities, explicit 'Use when' triggers with multiple natural synonyms, and a clearly distinct time-series niche. It matches the quality of the rubric's good_overall_examples.

Dimension	Reasoning	Score
Specificity	Lists seven concrete task types (classification, regression, clustering, forecasting, anomaly detection, segmentation, similarity search) with scikit-learn-compatible API context, matching the comprehensive-coverage anchor rather than the 4-anchor's 'minor gaps'.	5 / 5
Completeness	Explicitly answers both 'what' (the seven time series ML tasks) and 'when' via a concrete 'Use when working with temporal data, sequential patterns, or time-indexed observations...' trigger clause.	5 / 5
Trigger Term Quality	Four natural synonyms for the domain ('time series', 'temporal data', 'sequential patterns', 'time-indexed observations') plus all task names give comprehensive coverage; no canonical file extension applies to this domain, so its absence is not a gap.	5 / 5
Distinctiveness Conflict Risk	Clear time-series-ML niche with the 'specialized algorithms beyond standard ML approaches' qualifier; temporal trigger phrases minimize overlap with general ML/sklearn skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/aeon/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.