Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need to generate or improve Java project documentation — including README.md files, package-info.java files, and Javadoc enhancements — through a modular, step-based interactive process that adapts to your specific documentation needs. This should trigger for requests such as Improve the code with documentation; Apply documentation; Refactor the code with documentation; Generate README or developer documentation for a Java project; Document Java APIs architecture or project workflow
.claude/skills/jabrena-170-java-documentation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -33% | 0% |
Generate comprehensive Java project documentation through a modular, step-based interactive process that covers README.md, package-info.java, and Javadoc. This is an interactive SKILL.
What is covered in this Skill?
@param/@return/@throws tags./mvnw clean compile and ./mvnw javadoc:javadocBefore applying any documentation generation, ensure the project validates. If validation fails, stop immediately — do not proceed until all validation errors are resolved.
./mvnw validate or mvn validate before applying any documentation generationRun ./mvnw validate or mvn validate and stop immediately if validation fails.
Read references/170-java-documentation.md and identify required outputs (README, package-info, Javadoc enhancements).
Create or update documentation using the selected file-handling strategy (overwrite/add/backup/skip).
Execute ./mvnw clean compile and ./mvnw javadoc:javadoc (or equivalent) to validate generated docs.
For detailed guidance, examples, and constraints, see references/170-java-documentation.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | pass→fail | 8,864 | 3,451 | -61% | 1 | 1 | 0% | 1,360 | 772 | -43% | 0 | 0 | — |
case-01 | fail→fail | 7,842 | 5,868 | -25% | 1 | 1 | 0% | 1,281 | 789 | -38% | 0 | 0 | — |
case-02 | fail→fail | 17,759 | 5,585 | -69% | 1 | 1 | 0% | 2,991 | 821 | -73% | 0 | 0 | — |
case-03 | fail→fail | 24,778 | 5,696 | -77% | 1 | 1 | 0% | 4,080 | 835 | -80% | 0 | 0 | — |
case-10 | fail→pass | 16,502 | 7,850 | -52% | 1 | 1 | 0% | 3,083 | 1,249 | -59% | 0 | 0 | — |
case-04 | pass→fail | 8,911 | 6,093 | -32% | 1 | 1 | 0% | 1,451 | 911 | -37% | 0 | 0 | — |
case-05 | pass→pass | 13,046 | 19,329 | +48% | 1 | 1 | 0% | 2,544 | 4,279 | +68% | 0 | 0 | — |
case-06 | pass→fail | 6,989 | 5,101 | -27% | 1 | 1 | 0% | 1,225 | 762 | -38% | 0 | 0 | — |
case-07 | fail→fail | 5,119 | 4,410 | -14% | 1 | 1 | 0% | 694 | 1,189 | +71% | 0 | 0 | — |
case-08 | fail→pass | 9,940 | 3,635 | -63% | 1 | 1 | 0% | 1,386 | 1,090 | -21% | 0 | 0 | — |
case-11 | pass→pass | 12,294 | 10,062 | -18% | 1 | 1 | 0% | 2,077 | 1,811 | -13% | 0 | 0 | — |
case-12 | fail→pass | 10,612 | 4,921 | -54% | 1 | 1 | 0% | 1,537 | 1,379 | -10% | 0 | 0 | — |
case-13 | pass→pass | 14,540 | 11,724 | -19% | 1 | 1 | 0% | 2,074 | 2,289 | +10% | 0 | 0 | — |
case-14 | pass→pass | 13,477 | 9,718 | -28% | 1 | 1 | 0% | 2,057 | 1,975 | -4% | 0 | 0 | — |
case-15 | fail→pass | 11,257 | 3,928 | -65% | 1 | 1 | 0% | 1,806 | 1,062 | -41% | 0 | 0 | — |
case-16 | fail→pass | 13,054 | 5,347 | -59% | 1 | 1 | 0% | 1,882 | 1,263 | -33% | 0 | 0 | — |
case-17 | fail→pass | 15,578 | 2,913 | -81% | 1 | 1 | 0% | 2,404 | 962 | -60% | 0 | 0 | — |
case-18 | fail→pass | 8,669 | 6,508 | -25% | 1 | 1 | 0% | 1,320 | 1,525 | +16% | 0 | 0 | — |
case-19 | pass→pass | 8,672 | 3,295 | -62% | 1 | 1 | 0% | 1,375 | 1,047 | -24% | 0 | 0 | — |
case-20 | fail→pass | 10,689 | 3,373 | -68% | 1 | 1 | 0% | 1,634 | 1,069 | -35% | 0 | 0 | — |
case-21 | fail→pass | 8,915 | 3,251 | -64% | 1 | 1 | 0% | 1,492 | 1,007 | -33% | 0 | 0 | — |
case-22 | pass→pass | 11,409 | 5,783 | -49% | 1 | 1 | 0% | 1,795 | 1,381 | -23% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +27 percentage points is the difference between those two pass rates over the 18 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.