write-adlisted

Writes and evaluates Meta paid-ad copy (retargeting + cold-traffic) — audience-temperature-aware framing, hard char-cap enforcement, policy compliance, 7-dim rubric. Meta-only at v1. Not for landing-page headlines (use write-copy), cold-outreach DMs (use write-outreach), organic social posts (use write-social), or channel-mix strategy (use plan-campaign).
hungv47/meta-skills · ★ 9 · AI & Automation · score 75

Install: claude install-skill hungv47/meta-skills

# Write Ad — Orchestrator Ready-to-publish Meta ad copy across retargeting (warm) and cold-traffic audiences. Multi-agent strategy → draft → format → voice → critic → humanmaxxing pipeline. Capability metadata lives in [`routing.yaml`](routing.yaml). Agent table + 2 routes + 7-dim rubric + post-humanmaxxing regression rule: [`references/agent-manifest.md`](references/agent-manifest.md). Methodology: [`references/playbook.md`](references/playbook.md). **Core question:** Would this ad still make sense if the platform stripped every claim that isn't substantiated by a named entity or measured number? ## Critical Gates — load first 1. **Audience-temp is non-negotiable.** Missing audience-temp BLOCKs (drives entire strategist tree — warm objection map vs cold objection map). Offer + creative-format + proof also hard-block via Missing-Input Hard Blocks. 2. **One audience-temp per artifact.** Run twice for campaigns spanning warm + cold; do NOT stack two audience-temps in one artifact. 3. **Hero + 2 distinct variants per artifact.** Strategist enforces 3 distinct `angle_archetype` values + 3 distinct `anchor_proof` entries. Variants isolate ONE variable each (Variable Subtraction). 4. **Format-checker is a HARD gate, not a critic dim.** Bounces on Meta char-cap violation / banned policy phrase / unsubstantiated measured claim. PASSED / REVISION_REQUIRED (does NOT consume critic cycle) / FORMAT_FAIL (escalate to user). 5. **Humanmaxxing runs ONCE per variant with `protected_token