improvement-extractionlisted

# Improvement Extraction Scan the current session for candidate CLAUDE.md/AGENTS.md baselines or candidate skills, and write each as a structured note to a configurable output folder. This is a scratch capture step — candidates land here for later manual review, not automatic promotion into this repo's baselines or skills. ## Step 1 — Resolve the output root - Read `IMPROVEMENTS_ROOT` from the environment. - If unset, ask the user for the path once, then use it for this run only. Tell them how to persist it so this step isn't needed again: - Windows: `setx IMPROVEMENTS_ROOT "<path>"` - macOS/Linux: `export IMPROVEMENTS_ROOT="<path>"` in their shell profile - Never write the resolved path into this skill file or any committed content — the environment variable is the only place it lives. ## Step 2 — What counts as a candidate Only two categories qualify: 1. **Candidate portable baseline** — a rule that, had it existed in CLAUDE.md/AGENTS.md at the start of the session, would have prevented a mistake, correction, or ambiguity that actually came up. General enough to survive a future session or a different repo. 2. **Candidate skill** — a repeatable, at least partly mechanizable procedure that came up this session and would be cheaper to run as a scripted/semi-scripted skill next time than to redo by hand. Exclude: routine bug fixes, one-off decisions, anything already covered by an existing baseline or skill, and anything too narrow to generalize past this one task.