Skip to main content

ax-cpp-refine

Use when writing C++ code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.

Source facts

Repository
ax-llm/ax
Last source activity
October 26, 2026 at 12:31
Detected SKILL.md language
English
Stars
2,972
Forks
201

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

Showing SKILL.md

SKILL.md
Source instructions · Read-only preview
name
ax-cpp-refine
description
Use when writing C++ code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.
version
25.4.6
# Ax Refinement Patterns For C++ This skill helps an agent write C++ code with the generated Ax package `axllm`. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package. ## When To Use - Improve generated outputs with evaluator feedback or optimizer artifacts. - Port TypeScript refinement intent into generated-language surfaces without assuming TypeScript-only helpers. - Use generated optimizer APIs when the target package does not expose a standalone refine helper. ## Package Facts - Language: C++. - Package: `axllm`. - Package API docs: `API.md` and `axir-api.json`. - Capability manifest: `axir-capabilities.json`. - Runnable examples: `examples/`. - Real network support: yes. - Scripted no-key transport support: yes. - Runtime profiles: `javascript-quickjs`, `python-pyodide`. ## Core Pattern ```cpp axllm::AxGEPA engine(reflection_client, options); auto result = engine.optimize(request, evaluator); ``` ## Relevant API Surface - AxGen: `axllm::ax`, `axllm::axllm::novel_f1_score`, `axllm::AxGen`, `axllm::run_control`, `axllm::AxRunControl`, `axllm::AxCachingFunction`, `axllm::set_caching_function` - Optimizers: `axllm::optimize`, `axllm::playbook`, `axllm::AxPlaybook`, `axllm::AxBootstrapFewShot`, `axllm::AxGEPA`, `axllm::OptimizerEngine`, `axllm::OptimizerEvaluator` ## Guardrails - Start from package examples for exact native syntax before inventing a new call shape. - Use `provider-api` examples only when the user explicitly has provider credentials available. - Use `no-key` examples for deterministic local checks and provider request mapping. - Treat AxIR as the source of generated package truth: if package docs disagree with source code, update the compiler and regenerate packages. - Do not copy repo-maintainer skills from `tools/*/skills/` into user packages.
View on GitHub