auto-workflow-builder

<!-- autoresearch: variation B — sharper output (priority tiers + data-verification gates + delta-against-existing + exit taxonomy) --> > **${var}** — URL to analyze (GitHub repo, X account, blog, project site, API docs, etc.). Multiple URLs comma-separated. Prefix with `force:` to re-analyze a URL already in the ledger. ## Overview The operator runs this on-demand to decide *what to enable* for a new watch target. Original produces a wall of tables with no priority and recommends skills that may not actually have data to work with. This version: 1. Verifies every recommendation is backed by an *observed* signal on the URL. 2. Tiers output into **MUST** (2–3 max), **SHOULD**, **NICE** with a one-line concrete "why". 3. Emits a *delta* against current `aeon.yml` rather than a full config dump. 4. Stays silent (no notification, no article) when existing config already covers the URL. 5. Anchors skill names in `skills.json` (authoritative), not a stale mapping table. --- ## Steps ### 0. Parse input and load context If `${var}` is empty → exit `AUTO_WORKFLOW_EMPTY`, notify `auto-workflow: set var= to one or more URLs (comma-separated)`. Parse `${var}`: - Split on `,`, trim each entry - Detect `force:` prefix on any entry → sets `force=true` for that URL (skip ledger dedup) - Normalize each URL: - Add `https://` if scheme missing - `twitter.com/` → `x.com/` - `@handle` → `https://x.com/handle` - Strip trailing `/`, fragment, and tracking params (`utm_*`, `ref`, `sr...