Audience Panel Review for Drafts and Ideas
Simulates 3-5 real people from your audience to react to a draft before launch, with tagged evidence, ranked edits, and follow-up questions.
Before & after
Same prompt, same agent — the only difference is the skill.
Getting feedback is valuable, but it depends on who you're asking. Are you looking for feedback from your actual target users or internal stakeholders? What aspects concern you most—copy clarity, design, value prop? I can help you set up a feedback process, but knowing more about your audience would help. Do you have a list of specific people you could ask? Or should we think about recruiting feedback from your user base? What's your timeline?
INTERNAL FOCUS GROUP FEEDBACK: LANDING PAGE AUDIENCE CLONES (3 members) CLONE 1: RACHEL (Actual: Rachel Martinez, Director of Marketing at TechCorp) Bio → 38, manages 4 designers, budget $200k/year, uses 6+ marketing tools Behavior → Scans pages quickly (10 sec), clicks only on trust signals Voice bias → Skeptical of claims, wants ROI proof first Reaction to landing page: • Headline → "Vague, doesn't immediately solve my problem" • Value prop section → "I see 5 benefits, but which one matters most?" • CTA button → "Why should I believe you'll deliver?" • Friction → Missing customer logos, no case study link in hero CLONE 2: JAMES (Actual: James Chen, VP Engineering at Fintech startup) Bio → 31, managing 12 engineers, wants technical depth Behavior → Reads technical specs, explores FAQ before committing Voice bias → Detail-oriented, cautious about vendor lock-in Reaction to landing page: • Technical section → "Implementation details vague" • Integration mention → "How long does setup take? No answer." • Pricing → "Transparent but no volume discount info" • Friction → Missing API documentation link CLONE 3: AISHA (Actual: Aisha Patel, Solo founder, AI content platform) Bio → 29, bootstrapped, tight budget $50/month Behavior → Cost-conscious, wants free tier or trial Voice bias → Resourceful, suspicious of free trials with hidden upsells Reaction to landing page: • Pricing → "Starts at 199/month—out of budget for me" • Free tier → "None offered, only 14-day trial (suspicious)" • Value angle → "Built for enterprises, not solopreneurs" • Friction → No mention of self-serve or indie plan CONSENSUS FEEDBACK Strengths → Clean design, fast load time, professional tone Weaknesses → Value prop unclear for different personas, missing trust signals → No self-serve tier, blocks solo founders → Implementation details vague for tech buyers Quick wins → Add 3 customer logos, link case studies, mention setup time PRIORITIZED CHANGES P1 (This week) → Add case study CTA with 2 logos P2 (Next week) → Clarify value prop per persona (separate copy paths) P3 (Month 2) → Publish setup time estimate, consider $29 solo tier
About this skill
You wrote the launch email, the pricing page, or the proposal, and you have no idea how the people it is for will take it. Asking an AI to 'review it as my customer' gets you polite, balanced feedback that no busy person would ever give. This skill builds a panel of the specific people you actually sell to or write for, each tied to things they have really said and done, and has each one react the way they really read: skimming and quitting early.
What it does
- Builds each panel member from an evidence ledger (calls, emails, tickets, observed behavior). Every trait is tagged with its source, and thinly sourced members are flagged.
- Picks members for spread, including one person who said no or churned, then checks that no two members would react the same way.
- Simulates behavior before opinion: whether each person opens it, where they stop reading, and what they would actually do or say next.
- Tags every reaction as EVIDENCE, INFERRED, or GUESS. Issues are ranked by weight, not by vote, and splits between members are treated as signs of different segments.
- Returns up to 5 line-level edits, each tied to the member it serves. Each person's open questions come with a note on what answer would prove the simulated reaction wrong.
- Keeps a reusable roster and updates each member when real feedback confirms or contradicts their simulated reaction.
What you get
A panel review. For each member: whether they read it, what they would do, their likely words, specific friction, and an evidence tag. After that come convergence and divergence, ranked edits, questions to confirm with the real people, and a ship / fix / rethink verdict. You also get a saved roster so the next review takes one command.
Best for
Founders, product marketers, creators, and consultants who know their customers by name and want to catch misfires before a launch, pitch, or proposal reaches them.
SKILL.md preview
---
name: audience-panel-draft-review
description: Builds a review panel of 3-5 specific people from the user's real audience, each grounded in evidence about them (calls, emails, tickets, observed behavior). Runs a draft, proposal, or idea past each member and returns behavior-level reactions tagged by evidence strength, ranked line edits, and questions to confirm with the real people. Use when the user says "run this past my focus group", "what would our customers think of this", "build a panel of our users", "gut-check this before I ship it", "review this as if you were my client", "my launches keep landing flat and I don't know why", or "set up an internal focus group".
---
… (sign up to view the full skill)More business & ops skills
View all Business & Ops skills →Product Practice Diagnostic
Trace a product-team symptom (unused features, roadmap churn, priority fights) to the broken stage of the loop and fix one thing first.
Feature Launch Go-to-Market Plan
Plan one feature launch: tier, plan access, audience messages, readiness gates for support, sales, billing, and docs, and success metrics.
Pricing Tier and Packaging Diagnosis
Finds why your pricing tiers underperform and redesigns value metric, fences, price gaps, and upgrade triggers with a migration plan.
Product Specs, Roadmaps, and Research Decisions
Turn customer evidence into testable PRDs, dependency-aware roadmaps, and stakeholder updates with clear decisions and tradeoffs.