AI Agent Skills

Extract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes proposed criteria to .adlc/drafts/evals/.

Analyze evaluation results and close the loop. Specification failures create local CDRs to fix agent rules; generalization failures go to evaluator backlog.

Research, create, improve, migrate, evaluate, package, install-check, govern, and safely publish qiaomu-flavored agent skills from workflows, prompts, transcripts, docs,…

Turn proven session behavior into a skill, rule, profile, AGENTS.md diff, or team learning; artifacts seed /autoresearch evals. Triggers "harvest this workflow", "turn t…