log-analyzer

Use this skill when the user wants to analyze log files — find errors and their frequency, detect anomalies, build incident timelines, or summarize what happened during an outage.

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

72%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 body is highly actionable with clean executable code, but it is monolithic — multiple concerns crammed into one file with no explicit workflow sequence or validation checkpoints. Splitting parsing/AI/reporting into reference scripts and adding a sequenced workflow would lift the weaker dimensions.

Suggestions

Add an explicit numbered workflow (parse → extract errors → frequency → AI analysis → report) with a validation step confirming parsed record counts before AI analysis.

Move the parser and report functions into ./scripts/ and reference them from the body, keeping only a quick-start example inline, to improve progressive disclosure.

Replace the hardcoded model id 'claude-opus-4-6' with a non-version-pinned reference (e.g. a model alias or a clearly marked placeholder) so the skill does not age out.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — reusable Python functions with minimal framing prose and a tight overview that assumes Claude's competence — with only minor removable detail (e.g. the inline 'Common log format' comment).	4 / 5
Actionability	Provides fully executable, copy-paste-ready Python (parse_log_file, extract_errors, error_frequency, analyze_logs_with_ai, build_incident_timeline, generate_log_report) plus a quick-reference function table covering the common cases.	5 / 5
Workflow Clarity	A pipeline is implied (parse → extract errors → frequency → AI analysis → report) but never explicitly sequenced, generate_log_report covers only part of it, and there are no validation or verification checkpoints for the AI-sampling or output steps.	3 / 5
Progressive Disclosure	All ~150 lines and multiple distinct concerns (parsing, AI analysis, reporting) are inlined in a single SKILL.md with no bundle files or one-level-deep references; section headers and a quick-reference table give some structure but the content that should be split is inline.	3 / 5
	Total	15 / 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.

The description is strong: it states concrete capabilities and an explicit, natural trigger clause that answers both what and when. The only minor gap is keyword synonym coverage (e.g. 'logs', '.log', 'crash', 'stack trace').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'find errors and their frequency, detect anomalies, build incident timelines, or summarize what happened during an outage' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (analyze logs, find errors, detect anomalies, build timelines, summarize outages) and 'when' via the concrete 'Use this skill when the user wants to analyze log files...' trigger clause.	5 / 5
Trigger Term Quality	Covers natural terms like 'log files', 'errors', and 'outage', but misses common synonyms and variations users would say such as 'logs', '.log files', 'crash', or 'stack trace'.	4 / 5
Distinctiveness Conflict Risk	The log-analysis/outage niche has distinct triggers and minimal overlap risk with other skills; it is unlikely to fire for unrelated work.	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: ProwlrBot/prowlr-marketplace
Path: external/community/log-analyzer/SKILL.md
Commit: 32f0050

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.