Run maclocal-api test suites with pass/fail assertions and AI-judge analyses.
npx skills add https://github.com/scouzi1966/maclocal-api --skill test-macafm
Please help me install this Agent Skill. Skill: test-macafm Source: https://github.com/scouzi1966/maclocal-api/tree/main/.claude/skills/test-macafm Command: npx skills add https://github.com/scouzi1966/maclocal-api --skill test-macafm
Run the maclocal-api test suite — automated pass/fail assertions and AI-judge analyses to verify server behavior, catch regressions, and validate model onboarding.
Run the maclocal-api test suite against your current build to verify stability.
High-intent search queries and answers about installing and using this skill.
Use the maclocal-api test suite to run automated pass/fail assertions and AI-judge analyses. It orchestrates builds, tests, and reporting by utilizing the AFM binary, a selected model, and repository Scripts/references data.
Yes, you can run regression checks after code changes for MLX models using the automated test suite. It validates server behavior and catches regressions by executing tests across smoke, standard, and full tiers.
To validate model onboarding for maclocal-api, you need the AFM binary, a selected model, and the Scripts/references data located in your repository. These elements are required to orchestrate the automated builds and tests.
The smoke, standard, and full test tiers for AFM represent different levels of automated test execution depth. They generate pass/fail assertions and AI-judge analyses to validate builds, verify regressions, and confirm model onboarding.
AI-judge analysis works by evaluating maclocal-api test results to provide quick quality feedback across builds. It processes automated pass/fail assertions generated during the validation of server behavior and model onboarding.
kagentiCopy orchestration and skill management skills into a target repository.
oabdelmaksoudImplement evaluation-driven development with code and model-based evaluators.
tabgabOrchestrate opp_repl test suites and aggregate per-suite results for CI release gating.
solo-istAutomate headless Playwright QA tests for Prose web-mode builds.
