name: marketing-copy-board
description: Review ad copy, landing page copy, or marketing email copy for the three failure modes that quietly kill conversion — a skeptical customer's real objections going unanswered, claims and CTAs that won't actually move the conversion metric, and brand-voice or compliance risk in the claims being made. Three independent reviewer lenses each flag issues blind, then cross-examine each other, then a board verdict tags every finding CONFIRMED/CORROBORATED/DISPUTED. Use when asked to review ad copy, landing page copy, or marketing email copy before it ships.
trigger: The user pastes or references ad copy, landing page copy, or marketing email copy and asks for a review, feedback, or "will this convert" — or asks specifically about customer objections, conversion, or brand/compliance risk in marketing copy.
version: 1.0.0
compatible_agents: [claude-code, codex, openclaw]

Marketing Copy Board — independent review, then cross-examination, then a verdict

This is a three-phase board process, not three opinions dumped side by side. Phase 1 finds
candidate issues independently; Phase 2 makes the board argue over them to kill false positives
and confirm real ones; Phase 3 delivers one verdict the marketer can actually act on before the
copy ships.

Anti-sycophancy rule (applies throughout)

Do not default to praise. Your job is to find the specific reasons this copy fails to convert or
creates risk — not to affirm that it's "punchy" or "on-brand." Ground every finding in the actual
copy shown to you; never invent a product claim, price, or feature that isn't there. If no target
audience or offer context was given, ask for it rather than guessing who this is supposed to
persuade.

Phase 1 — Three independent passes (blind)

Run each lens as an independent pass. Each lens must reach its own conclusion without seeing the
others' output yet. For each finding, capture internally: what's wrong, the concrete consequence
(reader bounces, objection goes unanswered, claim invites a complaint) — not a vague warning — and,
if quick, the one-line rewrite. Quote the actual copy line.

🕵️ Skeptical Customer

Lens: read this the way a wary stranger would, not a believer. Look for unsupported superlatives
("the best," "revolutionary") with no proof point attached, the obvious "why should I trust this"
objection left unanswered (price, risk, social proof, "why now"), and any claim a skeptical reader
would immediately think "prove it" about. Ask "what's the first objection a stranger has, and does
this copy answer it before they leave?"

📉 Conversion Realist

Lens: does this copy actually move someone toward the action, or just sound nice? Look for a weak
or buried call-to-action, benefit statements that describe the product instead of the outcome for
the reader, no urgency or reason to act now, and copy that's optimized for sounding clever over
being scannable/skimmable. Ask "if someone skims this in 8 seconds, do they know exactly what to do
next and why?"

🛡️ Brand Guardian

Lens: does this create risk or an inconsistent voice? Look for claims that could be read as
guarantees the business can't back (results, timelines, "guaranteed"), tone that clashes with how
the brand talks elsewhere, comparisons to competitors that could be legally or factually shaky, and
absolute language ("never," "always," "100%") that's one counterexample away from a complaint. Ask
"if a customer screenshots this line and holds the business to it literally, is that a problem?"

If a lens finds nothing after genuinely looking, note that plainly — but that should be rare on a
first draft.

Phase 2 — Cross-examination (the board argues)

Now show each lens the other two lenses' Phase 1 findings (never its own). For every finding from
another lens, each reviewer answers two questions in one line each:

1. Challenge: "Is this actually a risk given the full copy, or is it covered elsewhere /
   overstated?" If a reviewer can name a concrete reason a finding is a false positive (e.g. the
   objection is actually answered two lines later, or the claim is qualified elsewhere), the
   finding gets challenged.
2. Corroborate: "Does this finding also matter through my lens?" (e.g. an unsupported
   superlative the Skeptical Customer flagged might also be the exact absolute-language risk the
   Brand Guardian already noted — corroboration from a second, independent lens is a stronger
   signal than one lens's opinion alone.)

Do not let a lens skip this step or rubber-stamp everything as fine.

Phase 3 — Board verdict

Merge everything into one report. Tag every surviving finding:

• CONFIRMED — no lens challenged it, or a challenge was raised but not substantiated with a
  concrete reason.
• CORROBORATED — flagged independently or corroborated by more than one lens. Treat these as
  the highest-priority findings in the report.
• DISPUTED — a lens raised a concrete, specific reason to doubt it. Include the finding and
  the challenge side by side so the marketer makes the final call, rather than silently dropping
  it.
• Drop nothing silently. A finding that was successfully challenged still gets listed, marked
  DISPUTED.

End with one Ship recommendation line: e.g. "Rewrite first — 2 CORROBORATED findings (unanswered
price objection, weak CTA), fix those before shipping" or "Ship after fixing 1 CONFIRMED
brand-risk claim" or "Ship as-is — no CORROBORATED or CONFIRMED blockers, DISPUTED items are
informational only."

Output format

## Phase 1 — Independent findings
### 🕵️ Skeptical Customer
- ...
### 📉 Conversion Realist
- ...
### 🛡️ Brand Guardian
- ...

## Phase 2 — Cross-examination
- [Skeptical Customer #1] challenged by Conversion Realist: "..." / corroborated by Brand Guardian: "..."
- ...

## Phase 3 — Board verdict
1. **[CORROBORATED]** ... — rewrite: ...
2. **[CONFIRMED]** ... — rewrite: ...
3. **[DISPUTED]** ... — challenge: "..." (your call)

**Ship recommendation:** ...

Handling sensitive info in the copy

If the copy references real pricing, customer names, or unreleased product details, treat that as
context only — do not echo it back beyond what's needed to explain a finding. This Skill sends the
text you paste as-is to the model; redact anything you'd rather not share before pasting.