CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

164-java-profiling-verify

Use when you need to verify Java performance optimizations by comparing profiling results before and after refactoring — including baseline validation, post-refactoring report generation, quantitative before/after metrics comparison, side-by-side flamegraph analysis, regression detection, or creating profiling-comparison-analysis and profiling-final-results documentation. This should trigger for requests such as Verify performance fix; Verify the performance; Verify the memory; Verify the threading; Compare before and after profiling results; Check for performance regressions after refactoring. Part of Plinth Toolkit

62

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/164-java-profiling-verify/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

Well-structured body with excellent progressive disclosure (one real, clearly signaled reference holding the operational detail) and a sequenced workflow with explicit validation checkpoints. It loses points for repeated restatement of the same constraints/trigger phrases and for providing no inline executable commands.

Suggestions

Collapse the Scope, Constraints, and "What is covered" sections into one statement of the identical-test-conditions requirement to remove triple redundancy.

Drop or trim the "When to use this skill" section — it duplicates the frontmatter description, which is already loaded into context with the skill.

Inline one concrete executable snippet (e.g., the shell check that both baseline and post-refactoring report directories exist and are non-empty) so step 1 is actionable without opening the reference.

DimensionReasoningScore

Conciseness

"Use identical test conditions" is stated three times (intro, Scope, CONSISTENCY constraint), "What is covered" repeats the intro paragraph, and "When to use this skill" restates trigger phrases already in the description — real redundancy, though no space is wasted explaining concepts Claude already knows.

3 / 5

Actionability

Concrete file names ("profiling-comparison-analysis-YYYYMMDD.md") and a specific reference path are given, but steps like "Run profiling with identical load/test conditions" contain no executable commands or examples — all operational detail is deferred to the reference file.

3 / 5

Workflow Clarity

Four numbered steps in a clear sequence with an explicit checkpoint in step 1 ("verify baseline artifacts exist and are non-empty"), a VALIDATE constraint, and edge-case recovery paths ("report what is missing and ask whether to proceed") — but no explicit validate-fix-retry loop for failed comparisons.

4 / 5

Progressive Disclosure

The body is a lean overview pointing to a single one-level-deep reference ("[references/164-java-profiling-verify.md](references/164-java-profiling-verify.md)"), clearly signaled both in the workflow and a dedicated Reference section; the referenced file exists and contains the detailed steps, commands, and templates.

5 / 5

Total

15

/

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 strong description: it comprehensively states concrete capabilities and includes an explicit trigger list of natural user phrases. Its only deductions are the second-person voice and slightly incomplete synonym coverage.

Suggestions

Rewrite the opening in third person (e.g., "Verifies Java performance optimizations by comparing profiling results...") to avoid the voice penalty.

Add the missing natural variations "Verify the GC", "Verify the profiling", and "performance benchmark" to the trigger list for full synonym coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("baseline validation, post-refactoring report generation, quantitative before/after metrics comparison, side-by-side flamegraph analysis, regression detection") with named deliverables, which is comprehensive coverage — but the second-person phrasing "Use when you need to verify" incurs the mandated 1-point penalty.

4 / 5

Completeness

It explicitly answers both "what" (verify Java performance optimizations via before/after profiling comparison with specific sub-tasks and deliverable documents) and "when" (a dedicated trigger list of concrete user phrases), matching the top anchor.

5 / 5

Trigger Term Quality

"This should trigger for requests such as Verify performance fix; Verify the performance; Verify the memory; Verify the threading; Compare before and after profiling results; Check for performance regressions after refactoring" gives good natural-phrase coverage, but common variations like "Verify the GC" and "performance benchmark" (present in the body) are missing.

4 / 5

Distinctiveness Conflict Risk

The Java profiling-verification niche is distinct with specific document names and before/after framing, but broad triggers like "Verify the memory" carry minor overlap risk with sibling Plinth Toolkit profiling steps (baseline collection, refactoring).

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

jabrena/plinth

Path

skills/164-java-profiling-verify/SKILL.md

Revision

86b41dc

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill