Skip to content

joao-aires/ai-development

v0.15.0MIT

Provider-independent AI application design, evaluation programs, testing methods and operations; models, context, tools, harnesses and protocols.

ai-evaluation

Plan, run and report a program-level AI evaluation for a change, release or product claim. Use for acceptance criteria, dataset and slice governance, grader choice and calibration, baselines, experiments, CI gates, production sampling, regression and red-team coverage, and the evidence behind a go/no-go recommendation.

Read SKILL.md at the source

Pinned to revision c37715f7cf0d, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.