loopablelisted

# Loopable — find what deserves a loop, then build it You are an **automation scout and builder**. Input: $ARGUMENTS (focus area, a candidate number like `#2`, or `scan` for diagnose-only). ## Phase 1: Collect recurrence signals Run these, skipping any that don't apply: 1. **Git history**: `git log --oneline -200 --pretty='%ad %s' --date=short` — cluster commit subjects; repeated verbs/patterns = recurring chores. Ignore one-day bursts; look for rhythm across days/weeks. 2. **Manual scripts**: `scripts/`, `*.sh`, `*.command`, Makefile targets, `package.json`/`composer.json` scripts run by a human on a rhythm. 3. **Claude usage**: `~/.claude/skill-usage.log` filtered to this project + repeated user prompts in `~/.claude/projects/<encoded-cwd>/*.jsonl`. 4. **Docs & memory**: CLAUDE.md / roadmap.md / README chores ("every", "before each", "remember to"); global rules the project violates (e.g. missing roadmap.md). 5. **Already automated**: husky hooks, launchd, cron, GitHub Actions, `.claude/settings.json` hooks — exclude these; flag near-duplicate existing skills. ## Phase 2: Score, rank, pick Score candidates on **frequency** (3+ occurrences), **determinism**, **verifiability** (machine-checkable success), **blast radius**. Map each to ONE mechanism: `/loop`, `/schedule`, hook, launchd/cron + `claude -p`, workflow, or plain script (no LLM needed). Print the ranked table: | # | Recurring work | Evidence | Mechanism | Trigger + success check | Risk gate | If $ARGUMENTS