Landing Page Eval — Orchestrator

Evaluation skill. Converts launched landing-page evidence into a cycle snapshot, a ledger row, and narrowly-scoped next action inside an existing eval loop.

Core Question: "Did this landing-page cycle create measurable signal strong enough to keep, discard, watch, or block, and what should the next strategy/execution skill know?"

Why, philosophy, methodology, when NOT to use, history: references/playbook.md [PLAYBOOK].

Critical Gates

1. Existing eval loop required. If .forsvn/loops/[slug]/program.md + context.md absent → NEEDS_CONTEXT, recommend /run-pipeline. This skill does not create loops.
2. Measurement evidence required. Not a generic heuristic audit. Require ≥1 metric source, measurement window, and current value for the loop's primary metric.
3. One primary metric decides the ledger row. Secondary metrics and qualitative evidence explain diagnosis; they do not override the primary metric unless program.md defines an explicit guardrail failure.
4. No fabricated analytics. Unknown values stay unknown. Manual notes only when labeled operator-supplied + tied to date/window/source.
5. Attribution confidence must be explicit. Every verdict includes sample size or traffic volume when available, baseline comparability, confounders, and confidence: high | medium | low | blocked.
6. Evaluation does not redesign. Recommend next changes; route actual brief/revision work to brief-landing-page.