observability-pattern-detector

Automated pattern recognition in Claude Code telemetry. Use when detecting failures, slowness, anomalies, trends, inefficiencies, conversation patterns, or tool sequences.

Quality

68%

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 ./skills/observability-pattern-detector/SKILL.md

Quality

Content

53%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 rich with executable LogQL queries but is organized as a monolithic catalog with redundant query sections and largely broken script references. Workflow sequencing and progressive disclosure are the weakest aspects.

Suggestions

Create the four missing referenced scripts (detect-anomalies.sh, detect-trends.sh, detect-sequences.sh, generate-pattern-report.sh) or remove their entries from the Scripts section so references resolve.

Move the per-operation query details into separate reference files and keep SKILL.md as a concise overview with one-level-deep links, rather than inlining every LogQL query twice (Operations and Pattern Detection Queries).

Add a brief sequencing/validation note for running the scripts end-to-end (e.g., run detect-failures.sh, inspect output, then generate-pattern-report.sh) to give the catalog a clear workflow with a verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete query listings without explaining concepts Claude already knows, but it duplicates similar LogQL queries across the 'Operations' and 'Pattern Detection Queries' sections, adding redundant tokens that could be tightened.	3 / 5
Actionability	Concrete, copy-pasteable LogQL queries and a full example JSON output are provided for each operation, but the 'Algorithm' lines are abstract pseudo-steps ('Group by error_type → Calculate frequency → Rank by impact') and four of five referenced scripts do not exist.	4 / 5
Workflow Clarity	The skill is a catalog of independent detection operations rather than a sequenced multi-step process, so operations are listed but there is no explicit ordering, and no validation/verification checkpoints are given for running the referenced scripts.	3 / 5
Progressive Disclosure	All per-operation query details are inlined into SKILL.md, and the Scripts section references five files of which only one (detect-failures.sh) actually exists, so most references are dangling and navigation to deeper material is broken.	2 / 5
	Total	12 / 20 Passed

Description

83%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-constructed description that clearly states what the skill does and gives an explicit, concrete 'Use when' trigger clause. It is held back only by single-verb action repetition and mild overlap with general observability skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Automated pattern recognition in Claude Code telemetry') and enumerates seven concrete detection targets ('failures, slowness, anomalies, trends, inefficiencies, conversation patterns, or tool sequences'), though all share the single verb 'detecting' rather than distinct action verbs, leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both 'what' (automated pattern recognition in Claude Code telemetry) and 'when' (a concrete 'Use when detecting...' clause listing specific trigger situations), matching the anchor for clear, explicit what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	The 'Use when detecting failures, slowness, anomalies, trends...' clause supplies several natural keywords a user would say, but terms like 'inefficiencies', 'conversation patterns', and 'tool sequences' lean technical and lack common synonyms.	4 / 5
Distinctiveness Conflict Risk	'Claude Code telemetry' is a clear niche with specific triggers, but the detection terms (failures, slowness, anomalies) overlap with broader monitoring/observability skills, giving minor conflict risk rather than a fully isolated niche.	4 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/observability-pattern-detector/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.