Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when writing Java code with `dev.axllm:ax` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -66% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 21% | 0% |
This skill helps an agent write Java code with the generated Ax package dev.axllm:ax. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package.
dev.axllm:ax.API.md and axir-api.json.axir-capabilities.json.examples/.javascript-quickjs, python-pyodide.javaAxAgent helper = Ax.agent("question:string -> answer:string", java.util.Map.of()); var out = helper.forward(llm, java.util.Map.of("question", "How should I proceed?"));
Ax.agent, AxAgentProcessCodeRuntime, RuntimeCapabilities, RuntimeEnvelope, javascript-quickjs, python-pyodideAx.optimize, Ax.playbook, AxPlaybook, AxBootstrapFewShot, AxGEPA, OptimizerEngine, OptimizerEvaluatorprovider-api examples only when the user explicitly has provider credentials available.no-key examples for deterministic local checks and provider request mapping.tools/*/skills/ into user packages.Other measured skills in the registry, with their headline benchmark lift.