How do skills get better over time?
Runs are scored against your rubrics, Context proposes improved skill versions from what worked, and a person approves before anything ships.
Evals scores completed runs against the criteria your team wrote. From those scores and corrections, Context can propose an improved version of a skill and replay it against past tasks to show the difference. Nothing replaces the current version until a person reviews and approves it. The loop is described on the Evals page.
Written for developers, it and security. Last reviewed 2026-09-15.
Related questions
Still need an answer?
Tell us what you were looking for and we reply within one business day.
Contact the team →Running a security review?
Documents, controls, and the request form live in the Trust Center.
Open the Trust Center →