executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
Explore skills
Productivity · SKILL.md
proxy_recovery_evaluator
proxy_recovery_evaluatorEvaluate whether a soft-mode reduced Flow Matching recovery is executable, metric-bearing, and mechanism-faithful.
Independent GitHub snapshot · Automated classification · Original documentation governs
Skill documentation
GitHubname: proxy_recovery_evaluator description: Evaluate whether a soft-mode reduced Flow Matching recovery is executable, metric-bearing, and mechanism-faithful.
Proxy Recovery Evaluator
Use this skill to judge soft-mode proxy recovery. It requires explicit proxy declaration, numeric CFM loss decrease, optimizer parameter changes, OT path/target checks, ODE check, and generated-skill invocation evidence. Run python tests/test_proxy_eval.py.