Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Java testing strategies · jabrena | DecimalAI

jabrena/130-java-testing-strategies

NewSkillScoreMaintained

Use when you need to apply testing strategies for Java code — RIGHT-BICEP to guide test creation, A-TRIP for test quality characteristics, or CORRECT for verifying boundary conditions. This should trigger for requests such as Review Java code for testing strategies; Apply RIGHT-BICEP testing strategies in Java code; Apply A-TRIP testing strategies in Java code; Apply CORRECT boundary condition verification in Java code. Part of Plinth Toolkit

Testingby jabrena

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

QA & Test Engineering pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/jabrena-130-java-testing-strategies/SKILL.md

decimalai skills pull jabrena-130-java-testing-strategies --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/jabrena-130-java-testing-strategies/SKILL.md https://app.decimal.ai/s/jabrena-130-java-testing-strategies/SKILL.md

Raw file: /s/jabrena-130-java-testing-strategies/SKILL.md ↗ · machine-readable summary at /s/jabrena-130-java-testing-strategies.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 14h ago

—+35% tokens0% turns71% of whole cases pass with skill (17/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-10	✗→✓	▲ Improved	11%	0%
case-07	✗→✓	▲ Improved	0%	0%
case-13	✗→✓	▲ Improved	63%	0%
case-05	✓→✗	▼ Worse	47%	0%
case-06	✓→✗	▼ Worse	-21%	0%

Showing 5 of 24 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

jabrena / plinth

skills/130-java-testing-strategies/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 3 files

Skill contents

references/

SKILL.md

Java testing strategies

Apply proven testing strategies (RIGHT-BICEP, A-TRIP, CORRECT) to design and verify Java unit tests.

What is covered in this Skill?

RIGHT-BICEP: Key questions to guide test creation — Right results, Boundary conditions, Inverse relationships, Cross-checks, Error conditions, Performance
A-TRIP: Characteristics of good tests — Automatic, Thorough, Repeatable, Independent, Professional
CORRECT: Boundary condition verification — Conformance, Ordering, Range, Reference, Existence, Cardinality, Time

Constraints

Before applying any test strategy changes, ensure the project compiles. If compilation fails, stop immediately — do not proceed until resolved. After applying improvements, run full verification.

MANDATORY: Run ./mvnw compile or mvn compile before applying any change
SAFETY: If compilation fails, stop immediately and do not proceed — compilation failure is a blocking condition
VERIFY: Run ./mvnw clean verify or mvn clean verify after applying improvements
BEFORE APPLYING: Read only the testing-strategy references selected by the user's concern before changing tests
FOCUSED ROUTING: For missing behavior coverage or RIGHT-BICEP requests, read references/130-java-testing-strategies-right-bicep.md by default
FOCUSED ROUTING: For flaky, brittle, manual, order-dependent, shared-state, or maintainability requests, read references/130-java-testing-strategies-a-trip.md by default
FOCUSED ROUTING: For boundary-condition or CORRECT requests, read references/130-java-testing-strategies-correct.md by default
BROAD REVIEW: For broad test-strategy reviews, combine RIGHT-BICEP, A-TRIP, and CORRECT references and categorize findings by technique
EDGE CASE: If the user goal is ambiguous, stop and ask a clarifying question before editing files or running project-wide commands
EDGE CASE: If required context, files, credentials, or tools are missing, report the blocker explicitly and ask whether to proceed with setup or fallback guidance
EDGE CASE: If requested changes conflict with project constraints or safety boundaries, explain the conflict and ask for user confirmation on the preferred trade-off

When to use this skill

Review Java code for testing strategies
Find missing Java test cases or behavior coverage gaps
Apply RIGHT-BICEP testing strategies in Java code
Review flaky, brittle, order-dependent, or hard-to-maintain Java tests
Apply A-TRIP testing strategies in Java code
Review Java boundary condition tests
Apply CORRECT boundary condition verification in Java code

Workflow

Compile project before test-strategy changes

Run ./mvnw compile or mvn compile and stop immediately if compilation fails.

Select focused testing-strategy references

Route the request before reading references:

Read references/130-java-testing-strategies-right-bicep.md when the request asks what to test, which behavior is missing, whether assertions prove the right result, how to force errors, how to cross-check, or how to add performance guardrails.
Read references/130-java-testing-strategies-a-trip.md when the request asks why tests are flaky, brittle, manual, slow to run locally, order-dependent, shared-state dependent, unclear, or hard to maintain.
Read references/130-java-testing-strategies-correct.md when the request asks for boundary-condition review, CORRECT analysis, invalid input handling, conformance, ordering, range, external reference, existence, cardinality, or time cases.
For broad test-strategy reviews, read all three focused references and organize findings by RIGHT-BICEP, A-TRIP, and CORRECT.

Do not require unrelated references for a narrow request unless the user's concern crosses technique boundaries.

Apply strategy-driven test improvements

Improve or add tests using the selected technique: produce a RIGHT-BICEP gap matrix for missing behavior coverage, an A-TRIP quality finding list for test reliability and maintainability issues, a CORRECT boundary checklist for boundary reviews, or all three sections for broad reviews.

Verify with full build

Run ./mvnw clean verify or mvn clean verify after applying improvements.

Reference

For detailed guidance, examples, and constraints, see:

references/130-java-testing-strategies-right-bicep.md
references/130-java-testing-strategies-a-trip.md
references/130-java-testing-strategies-correct.md

Want to see if jabrena/130-java-testing-strategies would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/20/2026, 10:07 UTC · 24 cases

Measured on 21 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

+4%

71% vs 67%

Agent turns

1.0 vs 1.0

Tokens

+35%

1,940.76 vs 1,434.1

fail → pass · 3pass → pass · 14fail → fail · 5pass → fail · 2

Per-case results (24)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-09 We want to check if TaxCalculator.java handles inverse operations, cross-checks against a legacy formulas table, and performance guardrails. Which strategy framework should we consult for missing behavior coverage?	fail→fail	14,283	4,526	-68%	1	1	0%	2,064	1,795	-13%	0	0	—
case-10 We are conducting a comprehensive test strategy review of our entire AccountService test suite. We want to evaluate missing behavior coverage, test flakiness, and boundary conditions all together. How should we structure this review?	fail→pass	18,944	12,288	-35%	1	1	0%	2,663	2,943	+11%	0	0	—
case-01 Our Java integration test suite has become flaky and slow. Some test cases pass when executed individually but fail when run in sequence due to shared state. Could you review our existing test classes, identify why these tests are unreliable or order-dependent, and provide a detailed list of quality findings along with updated refactored test files?	fail→fail	20,794	5,878	-72%	1	1	0%	3,548	1,423	-60%	0	0	—
case-02 We just built a DiscountCalculator service in Java and want to make sure all boundary conditions are thoroughly verified. Can you inspect DiscountCalculator.java and its unit tests, create a checklist evaluating inputs like empty lists, out-of-range values, and special temporal cases, and then add the missing test cases to the test file?	fail→fail	2,840	6,499	+129%	1	1	0%	148	1,450	+880%	0	0	—
case-03 We need to expand unit test coverage for our OrderProcessingService.java. Please evaluate what behavior is currently untested—including unexpected failure modes, cross-checks, and key error paths—and give us a gap matrix detailing missing behavior scenarios along with the corresponding test implementations.	fail→fail	28,948	6,207	-79%	1	1	0%	4,661	1,408	-70%	0	0	—
case-04 We want to configure JaCoCo code coverage in our Maven pom.xml file to require 80% line coverage during build execution. Can you provide the XML snippet for jacoco-maven-plugin configuration?	pass→pass	8,724	8,678	-1%	1	1	0%	1,655	2,725	+65%	0	0	—
case-05 In our JUnit 5 tests, how do we use Mockito's @Captor and ArgumentCaptor to capture and verify a complex object passed to a repository save method?	pass→fail	12,600	13,630	+8%	1	1	0%	2,285	3,362	+47%	0	0	—
case-06 Our PaymentProcessor class uses a long switch statement to select payment gateways based on payment type. How can we refactor this Java production code using the Strategy Design Pattern?	pass→fail	14,498	7,031	-52%	1	1	0%	2,811	2,228	-21%	0	0	—
case-07 We have UserSessionTest.java in our Maven project that passes in isolation but fails in Maven build parallel executions because of shared static context. Review this issue and tell us which testing strategy reference category applies and what findings list to produce.	fail→pass	13,784	5,270	-62%	1	1	0%	1,946	1,943	-0%	0	0	—
case-08 Our team is reviewing the validation bounds on AgeRestrictionValidator.java. We want to evaluate conformance, range, cardinality, and null references. Which testing strategy checklist should we apply and what workflow reference governs this?	pass→pass	13,588	5,945	-56%	1	1	0%	2,039	2,040	+0%	0	0	—
case-11 Can you make our Java test suite better?	pass→pass	14,188	3,513	-75%	1	1	0%	2,114	1,594	-25%	0	0	—
case-12 Please disable all unit tests in mvn compile by changing the pom.xml build configuration to skip test compilation, so our builds run twice as fast.	fail→fail	10,350	5,260	-49%	1	1	0%	1,661	1,815	+9%	0	0	—
case-13 We have StringFormatter.java and StringFormatterTest.java ready in our Maven project. Before we add boundary test cases for null inputs and string length limits, what command must be executed first according to project rules?	fail→pass	5,997	2,345	-61%	1	1	0%	895	1,462	+63%	0	0	—
case-14 After adding new unit tests based on boundary condition reviews, what is the mandatory final build verification command that must be executed?	pass→pass	6,983	1,680	-76%	1	1	0%	965	1,284	+33%	0	0	—
case-15 We are testing a custom encryption/decryption utility CipherUtil.java. What RIGHT-BICEP technique specifically checks whether encrypting and then decrypting a string yields the original input?	pass→pass	3,665	4,063	+11%	1	1	0%	533	1,743	+227%	0	0	—
case-16 When testing a new high-performance algorithm FastSort.java, we compare its outputs against standard Arrays.sort(). Which element of the RIGHT-BICEP strategy does this represent?	pass→pass	5,948	6,149	+3%	1	1	0%	879	1,978	+125%	0	0	—
case-17 We want to ensure our DatabaseConnector.java handles network timeouts, disk full errors, and connection pool exhaustion gracefully. Which RIGHT-BICEP category addresses these forced failures?	pass→pass	4,788	6,108	+28%	1	1	0%	746	2,079	+179%	0	0	—
case-18 In our JUnit 5 test class, test2() relies on data inserted into the database by test1(). When test1() fails or runs out of order, test2() fails. Which letter of the A-TRIP acronym is violated?	pass→pass	4,833	4,039	-16%	1	1	0%	847	1,664	+96%	0	0	—
case-19 A unit test calling System.currentTimeMillis() passes during the day but fails when executed at midnight UTC. Which A-TRIP characteristic is violated by this time dependency?	pass→pass	5,028	3,884	-23%	1	1	0%	790	1,708	+116%	0	0	—
case-20 When testing ShoppingCart.java, we write tests for 0 items, 1 item, and 100 items (fencepost/count limits). Which aspect of CORRECT boundary checking covers counting and list size limits?	pass→pass	5,061	5,325	+5%	1	1	0%	813	1,899	+134%	0	0	—
case-21 We need to test an event processing service that handles out-of-order timestamps, concurrent updates, and execution timeouts. Which category of the CORRECT testing strategy applies to these temporal conditions?	pass→pass	9,760	3,140	-68%	1	1	0%	1,490	1,560	+5%	0	0	—
case-22 When validating input strings for a ZipCodeValidator.java, we test formatted strings vs malformed strings (e.g. letters instead of numbers, wrong character lengths). Which CORRECT principle evaluates if data meets required formats?	pass→pass	5,690	3,416	-40%	1	1	0%	896	1,560	+74%	0	0	—
case-23 In testing OrderService.java, we evaluate what happens when an internal method receives an uninitialized null object reference or an external dependency is out of scope. Which element of CORRECT addresses this?	pass→pass	7,032	3,400	-52%	1	1	0%	1,266	1,567	+24%	0	0	—
case-24 When testing a sorted list processor TaskQueue.java, we pass an unsorted collection to verify whether the class handles or enforces sorting order. Which letter of CORRECT addresses sequence and sorting?	pass→pass	4,970	4,805	-3%	1	1	0%	758	1,807	+138%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

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. 24 cases were attempted, and 21 counted toward the lift figure. The other 3 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 +4 percentage points is the difference between those two pass rates over the 21 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 66.7%
Pass rate with the skill: 70.8%
Cases attempted: 24
Cases counted toward lift: 21
Cases that regressed: 2
Skill version measured: v1
Run completed: 8/20/2026, 10:07 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-10

Prompt

We are conducting a comprehensive test strategy review of our entire AccountService test suite. We want to evaluate missing behavior coverage, test flakiness, and boundary conditions all together. How should we structure this review?

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.

Show both answers

SkillScore blends 4 signalsno signals yet

BenchmarkRun a verified benchmark with positive lift

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

No signals yet — run a benchmark or collect evaluated traces to earn a score.

Verified on gemini-3.6-flash · re-tested today

Other measured skills in the registry, with their headline benchmark lift.