ericrisco/rsc-harness / skills/java
java
VerifiedUse when writing, reviewing or refactoring modern Java (21+, 25 LTS) — records and sealed interfaces as algebraic data types, exhaustive pattern-matching switch over instanceof ladders, virtual-thread concurrency, structured concurrency and ScopedValue replacing ThreadLocal, Stream and Optional pipelines, compact-constructor validation, parametrized JDBC, and the Maven/Gradle build surface. NOT Spring framework wiring (that is `spring-boot`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.9 KB |
| evals/README.md | markdown | 1.7 KB |
| evals/cases.yaml | config | 4.5 KB |
| references/builds.md | markdown | 5.0 KB |
| references/concurrency.md | markdown | 5.0 KB |
| references/streams.md | markdown | 4.0 KB |
| scripts/verify.shexecutable | script | 3.2 KB |
evals/README.md
View on GitHub# Eval harness — `java` skill
These are routing/trigger fixtures plus one capability rubric, not an automated CI harness.
`cases.yaml` is the fixture; this file is how to run it by hand or with a grader-agent.
**Triggering.** Load the full skill catalog so the routing layer sees every sibling
(spring-boot, kotlin-android, security-audit, deployment, postgresdb, go, python, harness, …).
Feed each `should_trigger.prompt` in a fresh session and confirm the agent invokes the `java`
skill; feed each `should_not_trigger.prompt` and confirm it does NOT fire `java` and instead
routes to the stated `route_to` sibling. LLM routing is non-deterministic, so run 3–5 trials
per prompt and pass on the majority; aim for ≥90% trigger accuracy. Watch the non-obvious case
("ThreadLocal disappears inside submitted tasks") — it should still fire `java` and land on
ScopedValue, and the Spanish case ("modela este dominio de pagos") should fire too.
**Capability.** Run the `capability.scenario` once without the skill body and once with
`java/SKILL.md` (plus `references/`) loaded, and grade each answer against the `must_include`
rubric (fraction of points present and correct). The skill earns its place only if the
with-skill answer clearly beats the baseline — chiefly: sealed interface + record cases (no
JavaBean), compact-constructor validation, an exhaustive `switch` with deconstruction and no
`default`, no instanceof ladder, a virtual-thread-per-task executor (not a pool), no `null`
returns, and a `pom.xml` pinned to `<release>25</release>`. Grading is judgment-based; a human
or grader-agent reads each rubric point against the output. Keep `cases.yaml` faithful to the
SKILL's "When to use / When NOT to use" — update both in the same change when scope shifts.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |