skill-auto-improvelisted

# Skill Auto-Improve **Purpose**: Turn ad-hoc, manual artifact tuning into a controlled, measurable loop. Given any artifact and an eval harness, the orchestrator runs subagents (a Proposer + an Evaluator) under the autoresearch invariant — *the eval harness is immutable, the artifact is free to change, KEEP a change only if the metric improves beyond noise, otherwise REVERT* — and logs every step. It works across LLM vendors and improves skills, prompts, workflows, and eval datasets. ## 1. Red Flags (Anti-Rationalization) **STOP and READ THIS if you are thinking:** - "I'll let the Proposer pick the tier / decide if its own change is good" -> **WRONG**. The author cannot grade itself. Tier is computed deterministically by `measure_change_size.py`; KEEP/REVERT is decided by the orchestrator from the Evaluator's number, never by the Proposer. - "A tiny positive delta means KEEP" -> **WRONG**. LLM/agent metrics are noisy (σ≈0.05–0.10). A change is only KEPT when `delta > sigma`; within-noise moves are reverted so noise never accumulates as drift. - "I'll just rewrite the whole file" -> **WRONG**. Changes are surgical (one section / one set of dataset ops). Full overwrites are how good content silently disappears. - "I can let it edit the eval set to make scores go up" -> **WRONG**. The harness (and frontmatter name/tier, dataset id/grader) is immutable. Editing the ruler to fit the result is the cardinal sin of measurement. - "Run it straight on `main`" -> **WRONG**. Use `--gi