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

86%

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

80%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, highly actionable skill body with strong progressive disclosure via verified reference files. The main gap is workflow clarity — sequences lack explicit validation checkpoints or feedback loops for fragile operations.

Suggestions

Add explicit validation/verification steps to multi-step workflows (e.g., assert estimator fitted before predict, check predicted horizon length matches the constructor horizon) and include a validate->fix->retry loop for fragile operations like forecasting or model selection.

Trim low-value inline comments (e.g., "# Higher scores indicate anomalies", "# same UCR dataset") and collapse redundant loader examples to improve token efficiency.

For destructive or batch operations (e.g., dataset downloads, large benchmarking runs), add an explicit checkpoint step before proceeding.

Dimension	Reasoning	Score
Conciseness	Largely efficient with executable code, but includes minor padding such as "# Higher scores indicate anomalies", "# same UCR dataset", and lightly redundant loader examples that could be trimmed.	4 / 5
Actionability	Copy-paste ready executable code blocks across every capability, with specific class names, parameters, and algorithm-selection guides covering the common cases.	5 / 5
Workflow Clarity	Capability sections present quick-start sequences, but there are no explicit validation checkpoints or validate->fix->retry feedback loops, and multi-step guidance stays implicit; the listed steps in Best Practices lack checkpoints.	3 / 5
Progressive Disclosure	Clear overview body with well-signaled, one-level-deep references to real files (all 11 referenced references/*.md files exist), with bulk detail appropriately split out and easy navigation via the Reference Documentation list.	5 / 5
	Total	17 / 20 Passed

Description

92%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, well-rounded description that names concrete tasks, gives explicit use-when triggers, and carves out a distinctive niche. Slight room to add natural synonyms or format cues for trigger-term breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete tasks — "classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search" — giving comprehensive coverage of specific capabilities rather than vague language.	5 / 5
Completeness	Explicitly answers both what (the enumerated ML tasks) and when ("Use when working with temporal data, sequential patterns, or time-indexed observations") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural terms like "time series", "temporal data", "sequential patterns", and "time-indexed observations", but lacks common file/format synonyms or shorthand variations users might say, so it falls just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (time series ML with scikit-learn-compatible APIs) with distinct triggers and minimal overlap risk against general ML skills.	5 / 5
	Total	19 / 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: 1e5eeff

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.