detecting-data-anomalies

Process identify anomalies and outliers in datasets using machine learning algorithms. Use when analyzing data for unusual patterns, outliers, or unexpected deviations from normal behavior. Trigger with phrases like "detect anomalies", "find outliers", or "identify unusual patterns".

Quality

73%

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 ./plugins/ai-ml/anomaly-detection-system/skills/detecting-data-anomalies/SKILL.md

Quality

Content

57%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured overview that delegates detail to real one-level references and lists a clear algorithm-selection workflow. It is held back by no executable code, missing in-flow validation checkpoints, and some verbosity in the examples and resources.

Suggestions

Add one minimal executable code snippet (e.g., fit Isolation Forest with contamination and emit scores) so the core task is copy-paste ready without opening the reference.

Insert an explicit validation checkpoint in the workflow (e.g., inspect the score distribution / top-N anomalies before reporting) to create a feedback loop and lift workflow_clarity.

Trim the inline example scenarios and generic Resources bullets, or move the detailed scenarios into the existing references/examples.md and link to it.

Dimension	Reasoning	Score
Conciseness	The body is instructional and avoids re-explaining basics, but the full Output list, three verbose example scenarios with contamination/precision targets, and generic Resources bullets (e.g., "Feature scaling: StandardScaler, RobustScaler, MinMaxScaler selection guide") could be tightened, matching anchor 2 rather than the every-token-earns-its-place anchor 3.	2 / 3
Actionability	Steps name concrete algorithms and parameters (Isolation Forest, contamination 0.01-0.05, StandardScaler, labels -1/1) but contain no executable code blocks or commands, delegating implementation to references/implementation.md, matching anchor 2 (some concrete guidance but incomplete) rather than the copy-paste-ready anchor 3.	2 / 3
Workflow Clarity	A clear 10-step numbered sequence is present, but there are no explicit validation/verification checkpoints embedded in the flow; the Error Handling table is separate from the workflow rather than an in-sequence feedback loop, so per the rubric cap it sits at anchor 2 not 3.	2 / 3
Progressive Disclosure	Sections are well organized and the body clearly signals one-level-deep real references ("See ${CLAUDE_SKILL_DIR}/references/implementation.md" and "references/errors.md", both verified to exist), with implementation and error detail appropriately split out, matching anchor 3.	3 / 3
	Total	9 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 cleanly answers both what and when with natural trigger phrases and a distinct niche. Its main weakness is the grammatically broken opening ("Process identify") and only partial specificity of concrete actions.

Suggestions

Fix the opening phrasing to a clean third-person verb phrase such as "Process and identify anomalies and outliers in datasets using machine learning algorithms."

List a few more concrete actions (e.g., score records, tune contamination thresholds, export flagged rows) to lift specificity from anchor 2 toward anchor 3.

Dimension	Reasoning	Score
Specificity	Quotes "Process identify anomalies and outliers in datasets using machine learning algorithms" name the domain and several actions, but the phrasing is grammatically broken ("Process identify") and not a comprehensive list of multiple concrete actions, matching anchor 2 rather than the multi-action anchor 3.	2 / 3
Completeness	It states what ("identify anomalies and outliers in datasets using machine learning algorithms") and when ("Use when analyzing data for unusual patterns, outliers, or unexpected deviations") with explicit triggers, matching the anchor-3 example that answers both what and when.	3 / 3
Trigger Term Quality	Explicit triggers "detect anomalies", "find outliers", "identify unusual patterns" plus "unusual patterns, outliers, or unexpected deviations" give good coverage of natural terms a user would say, matching anchor 3.	3 / 3
Distinctiveness Conflict Risk	ML anomaly/outlier detection is a clear niche with distinct triggers ("detect anomalies", "find outliers") unlikely to fire for unrelated skills, matching anchor 3 rather than the somewhat-overlapping anchor 2.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/anomaly-detection-system/skills/detecting-data-anomalies/SKILL.md
Commit: bddba3c

Reviewed: 5 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.