162-java-profiling-analyze

Use when you need to analyze Java profiling data collected during the detection phase — including interpreting flamegraphs, memory allocation patterns, CPU hotspots, threading issues, systematic problem categorization, evidence documentation with profiling-problem-analysis and profiling-solutions markdown files, or prioritizing fixes using Impact/Effort scoring. This should trigger for requests such as Analyze JFR profile; Analyze the profile; Analyze the performance; Analyze the memory. Part of cursor-rules-java project

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

57%

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

The body is a well-organized overview that defers detail to a real one-level reference, but it suffers from redundant restatement across its intro, coverage list, and workflow, and its actionable detail lives in the reference rather than inline.

Suggestions

Collapse the overlapping intro, "What is covered in this Skill", and "Workflow" sections into a single non-redundant sequence so each fact appears once.

Remove the duplicate "Analyze the profiling" line in "When to use this skill" and consider dropping that section since the triggers already live in the description.

Add at least one concrete executable snippet or command (e.g. an async-profiler / JFR invocation) inline so the skill is actionable before opening the reference.

Dimension	Reasoning	Score
Conciseness	The body mostly assumes Claude's competence and avoids explaining concepts, but it is padded with repetition: the intro, "What is covered", and "Workflow" sections restate the same inventory/validate/identify/document content, and the "When to use" list duplicates the description triggers and even repeats "Analyze the profiling" twice.	2 / 3
Actionability	It gives some concrete guidance (tool names like async-profiler/JFR/GCViewer, file patterns such as *.jfr and allocation-flamegraph, output templates profiling-problem-analysis-YYYYMMDD.md, Impact/Effort 1-5), but the executable analysis steps are deferred to the reference rather than shown, so it stops short of copy-paste-ready instruction.	2 / 3
Workflow Clarity	The four-step workflow is clearly sequenced and includes a validation checkpoint (step 2: validate data quality and assumptions) plus EDGE CASE handling, but there is no explicit error-recovery feedback loop and the in-step checkpoints are implicit, leaving it short of the 3 anchor.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview that points to a single one-level-deep reference [references/162-java-profiling-analyze.md] (verified to exist), signaled clearly in both Workflow step 1 and a dedicated Reference section, with content appropriately split between overview and detail.	3 / 3
	Total	9 / 12 Passed

Description

82%

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 description that covers concrete capabilities and gives explicit natural-language triggers, clearly scoped to Java profiling analysis. The main weaknesses are the second-person voice and a few overly generic trigger phrases that risk overlap with sibling skills.

Suggestions

Rephrase to third-person voice (e.g. "Use when Java profiling data must be analyzed") to avoid the second-person specificity penalty.

Qualify the generic triggers to be Java-specific (e.g. "Analyze a JFR profile", "Analyze Java memory allocations") to reduce conflict with non-Java analysis skills.

Drop the trailing "Part of cursor-rules-java project" metadata-style line from the description; it adds tokens without aiding triggering.

Dimension	Reasoning	Score
Specificity	It lists many concrete actions ("interpreting flamegraphs, memory allocation patterns, CPU hotspots, threading issues, systematic problem categorization, evidence documentation... prioritizing fixes using Impact/Effort scoring"), which would be a 3, but the "Use when you need to analyze" phrasing is second-person voice, which the rubric penalizes by one point.	2 / 3
Completeness	It explicitly answers both what (analyze Java profiling data, interpret flamegraphs, document findings, prioritize fixes) and when ("Use when you need to analyze Java profiling data" and "This should trigger for requests such as...").	3 / 3
Trigger Term Quality	It includes natural phrases a user would say ("Analyze JFR profile; Analyze the profile; Analyze the performance; Analyze the memory") plus domain terms (flamegraphs, JFR), giving good coverage of likely triggers.	3 / 3
Distinctiveness Conflict Risk	The Java-profiling niche is clear (JFR, flamegraphs, cursor-rules-java), but several triggers ("Analyze the profile", "Analyze the performance", "Analyze the memory") are generic and could overlap with other analysis skills, so it is not yet a clean distinct-trigger 3.	2 / 3
	Total	10 / 12 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: jabrena/cursor-rules-java
Commit: 86eb63d

Reviewed: 4 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.