outlier-detection-handler

Use outlier detection handler for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.

Quality

50%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/outlier-detection-handler/SKILL.md

Quality

Content

52%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.

The content is well-structured with real bundled scripts and validation checkpoints, but it is heavily padded with redundant boilerplate sections and its documented parameters disagree with the actual script. Core detection usage is described in prose rather than shown as an executable command.

Suggestions

Collapse the redundant output/error sections (Output Requirements, Output Contract, Returns, Error Handling, Failure Handling) into one concise block.

Reconcile the Parameters table with scripts/main.py: the script exposes --method zscore|iqr|grubbs and no --action flag, so document those real options.

Add a copy-paste-ready detection example such as 'python scripts/main.py --data measurements.csv --method iqr' instead of prose-only input/output.

Dimension	Reasoning	Score
Conciseness	The ~190-line body is padded with overlapping boilerplate sections (Output Requirements, Output Contract, Returns, Error Handling, Failure Handling, Lifecycle Status, Evaluation Criteria, Risk Assessment, Security Checklist), and the 'When to Use' line even copy-pastes the description ('Use this skill when the task needs Use outlier detection handler...').	2 / 5
Actionability	Concrete validation commands exist ('python -m py_compile scripts/main.py', 'python scripts/main.py --help') and a Parameters table is provided, but no executable detection command is shown and the documented parameters ('3-sigma', action 'flag/remove/winsorize') do not match the actual script (which uses 'zscore' and has no --action argument).	3 / 5
Workflow Clarity	A clear 5-step workflow is sequenced with scope-validation, fallback, and Quick Check/User Checkpoints present, but the validate-fix-retry loop is not integrated into the workflow with specific commands the way the top anchor requires.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers and the bundled scripts/main.py is a real one-level-deep reference that is clearly signaled, though generic policy/checklist content is inlined and requirements.txt is referenced but absent from the bundle.	4 / 5
	Total	13 / 20 Passed

Description

48%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.

The description names a distinct niche but leans on abstract workflow-quality language instead of concrete actions and trigger phrases. It answers 'what' only by naming the tool and gives a vague 'when', missing natural synonyms like 'anomaly'.

Suggestions

State concrete actions, e.g. 'Identify, flag, and handle statistical outliers in datasets using Z-score, IQR, or Grubbs methods.'

Add explicit trigger guidance with natural phrases: 'Use when the user mentions outliers, anomalies, data quality checks, or pre-analysis screening.'

Replace abstract qualifiers ('structured execution, explicit assumptions') with the concrete scenarios that signal the skill.

Dimension	Reasoning	Score
Specificity	The description names the domain ('outlier detection handler', 'data analysis workflows') but lists no concrete detection/handling actions; 'structured execution, explicit assumptions, and clear output boundaries' are abstract workflow qualities rather than what the skill does.	2 / 5
Completeness	A 'what' is present only as the skill name ('outlier detection handler') and a weak 'when' clause ('for data analysis workflows that need...') exists, but neither is concrete; the when is abstract and could apply to many analysis skills.	3 / 5
Trigger Term Quality	'outlier detection' and 'data analysis workflows' are relevant natural terms, but common synonyms such as 'anomaly detection', 'statistical outliers', 'data quality', and file extensions are missing.	3 / 5
Distinctiveness Conflict Risk	'outlier detection' is a clear, distinct niche with minimal conflict risk, though the generic trigger phrases ('structured execution, explicit assumptions') create minor overlap with general data-analysis skills.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/outlier-detection-handler/SKILL.md
Commit: 63c61d3

Reviewed: 10 hours 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.