adewale/
skill-eval-harness
adewale/skill-eval-harnessHarnesses
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
73
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
Turn product ideas into production launches with Spec-Driven Development. Repeatable Claude Code workflows with quality gates, token budgets, and auditable artifacts.

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.