CtrlK
BlogDocsLog inGet started
Tessl Logo

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; Analyze the threading; Analyze GC logs from profiling; Prioritize Java profiling bottlenecks by impact. Part of Plinth Toolkit

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, token-efficient skill body with a clear validated workflow and clean one-level reference. Its main gap is actionability: it tells Claude what to look at and produce but defers the concrete commands, templates, and scoring formula entirely to the reference file.

Suggestions

Add the Impact/Effort scoring rule (e.g., 'Impact 1-5, Effort 1-5; priority = Impact/Effort, address ratio >= 1 first') inline so prioritization is actionable without opening the reference.

Include at least one concrete invocation example (e.g., an async-profiler or JFR command) or the exact template headings for the two output markdown files so the produce step is copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean and bullet-driven, assumes Claude knows what flamegraphs/JFR/GC are, and avoids concept explanation; every section is load-bearing, matching the 'lean and efficient' anchor.

3 / 3

Actionability

It names concrete file patterns to scan ('allocation-flamegraph, heatmap-cpu, memory-leak, *.jfr') and output filenames, but gives no executable commands or the Impact/Effort formula — 'Analyze memory/CPU/threading findings, cross-reference multiple files, and prioritize issues by Impact/Effort' is direction rather than instruction, so it sits at 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

A clear 4-step sequence with an explicit validation checkpoint ('Validate data quality and assumptions' as step 2) plus edge-case clarifying loops ('If request scope is ambiguous, stop and ask'), matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

The body is a concise overview with a single clearly signaled, one-level-deep reference to a real file ('references/162-java-profiling-analyze.md'), matching the 'clear overview with well-signaled one-level-deep references' anchor.

3 / 3

Total

11

/

12

Passed

Description

92%

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: concrete actions, explicit 'Use when' triggers with natural phrasings, and a clear Java-profiling niche. Its only weakness is that several trigger phrases ('Analyze the performance', 'Performance analysis') are broad enough to risk overlapping with adjacent analysis skills.

Suggestions

Qualify the broader triggers (e.g., 'Analyze the performance of a Java application from JFR/flamegraph data') so they are less likely to fire for non-Java or non-profiling analysis requests.

Drop or scope the standalone 'Performance analysis' trigger, which is generic enough to conflict with unrelated performance skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('interpreting flamegraphs, memory allocation patterns, CPU hotspots, threading issues, systematic problem categorization, evidence documentation ... prioritizing fixes using Impact/Effort scoring'), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (the enumerated analysis actions) and when ('Use when you need to analyze Java profiling data ... This should trigger for requests such as'), matching the clear what-and-when anchor.

3 / 3

Trigger Term Quality

Provides natural phrasings a user would say ('Analyze JFR profile; Analyze the profile; Analyze the performance; Analyze the memory; Analyze the threading ... Prioritize Java profiling bottlenecks by impact'), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The Java-profiling niche and Step-2/detection-phase framing are specific, but generic triggers like 'Analyze the performance', 'Performance analysis', and 'Analyze the memory' could overlap with other performance or memory-analysis skills, so it does not reach the 'unlikely to conflict' anchor.

2 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jabrena/plinth
Reviewed

Table of Contents

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.