CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/jacoco-analysis

Use for any question or task about Java, Kotlin, Scala or Groovy code coverage on Gradle or Maven, including a build that should fail below a minimum or a coverage report that comes out empty in CI: JaCoCo agent setup, HTML, XML and CSV reports, check rules such as 80% lines, the six counters, and JaCoCo XML to LCOV or Cobertura.

Quality

91%

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

Overview
Quality
Evals
Security
Files

Quality

Content

81%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 a complete Maven plugin config, a worked failure/recovery example, and a valuable anti-patterns table, and it correctly pushes Gradle/parsing/CI detail into a real reference file. It is held back by a six-counter definition table that re-teaches concepts Claude already knows, triplicate rule XML, and one dangling reference path (references/cobertura.md).

Suggestions

Replace the six-counter definition table with a one-line list of counter names plus the complexity formula; the quoted definitions (e.g. 'A source line is considered executed when at least one instruction...') re-explain what Claude already knows.

Show the check-rule XML once: the 'Wire the Maven plugin' and 'Gating with the check goal' sections both render full BUNDLE INSTRUCTION/BRANCH limit blocks, and the compact snippet repeats them a third time — keep only the two-rule pattern with excludes.

Fix the References section: 'lcov-analysis (references/cobertura.md)' points to a file not present in this bundle — clarify it belongs to the sister skill, and consolidate the five repeated links to references/gradle-parsing-and-ci.md.

DimensionReasoningScore

Conciseness

The six-counter definition table ("The smallest unit JaCoCo counts are single Java byte code instructions", "A source line is considered executed when...") re-explains concepts Claude already knows, the INSTRUCTION/BRANCH limit XML appears three times (plugin block, gating section, compact snippet), and the pinned "0.8.13" version is time-sensitive. Not 2 because most sections (anti-patterns, worked example, CI) are tight and every token there earns its place.

3 / 5

Actionability

Fully executable guidance: complete copy-paste plugin XML, `./mvnw -B verify`, report paths, the value-options table, and a worked example covering the common failure case ("the build fails on the BRANCH rule (minimum 0.70), naming the bundle and the missed limit"). Not 4 because concrete examples cover the common cases end-to-end with no gaps.

5 / 5

Workflow Clarity

Clear 4-step sequence in 'How to use' plus a worked example with an explicit feedback loop: build fails on the BRANCH rule → open index.html → drill into red branches → add tests → "re-run `./mvnw -B verify` until `check` passes". Not 4 because error recovery and validation checkpoints are explicit rather than implicit.

5 / 5

Progressive Disclosure

Good split: Gradle config, XML parser, gating table, and CI job are correctly deferred to the one-level-deep references/gradle-parsing-and-ci.md, which exists and contains that content. Not 5 because the References section cites "references/cobertura.md", which does not exist in this bundle (a dangling pointer), and the same reference file is linked five separate times. Not 3 because content placement is otherwise appropriate and clearly signaled.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it opens with an explicit 'Use for' trigger clause naming the languages and build tools, lists concrete capabilities, and even covers common failure scenarios (empty CI report, minimum-threshold build failure). Trigger terms match what users would naturally say, and the niche is clearly distinct.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "JaCoCo agent setup, HTML, XML and CSV reports, check rules such as 80% lines, the six counters, and JaCoCo XML to LCOV or Cobertura" — with comprehensive coverage of the skill's capabilities. Not 4 because there are no minor gaps; every major capability (setup, reports, gating, counters, conversions) is named.

5 / 5

Completeness

Explicitly answers both: what ("JaCoCo agent setup, HTML, XML and CSV reports, check rules such as 80% lines, the six counters, and JaCoCo XML to LCOV or Cobertura") and when ("Use for any question or task about Java, Kotlin, Scala or Groovy code coverage on Gradle or Maven, including a build that should fail below a minimum or a coverage report that comes out empty in CI"). Not 4 because the 'when' clause is explicit with concrete trigger scenarios, not merely present.

5 / 5

Trigger Term Quality

Comprehensive natural vocabulary: "code coverage", "Java, Kotlin, Scala or Groovy", "Gradle or Maven", "coverage report that comes out empty in CI", "build that should fail below a minimum", "JaCoCo", "LCOV", "Cobertura". These are the exact phrases a user would say; not 4 because synonyms and alternate tool names are already covered.

5 / 5

Distinctiveness Conflict Risk

Clear niche: JVM-language coverage on Maven/Gradle with JaCoCo-named triggers; minimal conflict risk with generic coverage tooling. Not 4 because LCOV/Cobertura appear only as conversion targets, keeping the triggers unambiguous for this skill.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Reviewed

On this page