Back to Details

customer-panel-of-experts

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Customer Panel of Experts

客户专家面板

Put your customers in the room before you spend money or burn trust. This skill assembles a panel of data-grounded buyer personas and runs a real debate on whatever you're deciding — then hands you the decision, the dissent, and what to test next.
It is the flagship of the panel family. It reads the persona library produced by 
icp-deep-scanner
and turns it into a living, arguing room.
在你投入资金或消耗客户信任之前，先让你的客户参与进来。此Skill会组建一个基于数据的买家角色面板，针对你要做的任何决策展开真实辩论，然后为你提供决策建议、不同意见以及下一步的测试方向。
它是面板系列的旗舰工具。它读取
icp-deep-scanner
生成的角色库，并将其转化为一个充满真实观点、互相辩论的虚拟会议室。

When to use it

使用场景

  • "Should we raise prices 20%?" — and what each segment will actually do.
  • "Here's the launch campaign for {product}. Will it land?"
  • "We're killing {feature} and adding {feature}. Who revolts?"
  • "Pick between positioning A and positioning B."
  • Any high-stakes call where you'd normally guess what customers think.
  • “我们应该涨价20%吗？”——以及每个客户群体的实际反应。
  • “这是{产品}的推广活动方案，能成功吗？”
  • “我们要砍掉{功能A}并新增{功能B}，哪些客户会反对？”
  • “在定位A和定位B之间做出选择。”
  • 任何你通常需要猜测客户想法的高风险决策。

Step 0 — Get the personas

步骤0 — 获取买家角色

The panel is only as good as its members. In order of preference:
  1. Use an existing persona library. Look for 
    personas/
    and 
    icp-profile.md
    (output of 
    icp-deep-scanner
    ). Load every persona file and 
    personas/index.md
    .
  2. Generate one now. If none exists and the user has connected tools, run 
    icp-deep-scanner
    first (read-only) to build it from real data.
  3. Bootstrap from input. If there's no data and no time, build 3–5 provisional personas from what the user tells you — and label the entire session "PROVISIONAL — not grounded in customer data" at the top and bottom. Never let a guessed panel masquerade as a researched one.
面板的质量取决于其成员。优先级如下：
  1. 使用现有角色库：查找
    personas/
    目录和
    icp-profile.md
    文件（
    icp-deep-scanner
    的输出）。加载所有角色文件和
    personas/index.md
    。
  2. 立即生成角色库：如果没有现成的角色库且用户已连接工具，先运行
    icp-deep-scanner
    （只读模式），基于真实数据构建角色库。
  3. 根据输入快速构建：如果没有数据且时间紧迫，根据用户提供的信息构建3–5个临时角色——并在会话的开头和结尾明确标注**“临时版本——未基于客户数据”**。绝不能让猜测的面板伪装成经过调研的面板。

Data & security rules

数据与安全规则

  • Connecting tools is read-only. Never write to, send from, or modify a connected source. Confirm before any exception.
  • Personas are archetypes. Do not surface real customer names/emails/account IDs in the debate. Quotes must be scrubbed.
  • Secrets stay in env vars / the MCP connection — never printed or stored in output.
  • 工具连接为只读模式。绝不写入、发送或修改已连接的数据源。如有例外情况需提前确认。
  • 角色是典型用户原型。辩论中不得暴露真实客户的姓名/邮箱/账户ID。引用内容必须经过脱敏处理。
  • 机密信息保留在环境变量/MCP连接中——绝不打印或存储在输出结果里。

Step 1 — Frame the decision

步骤1 — 明确决策框架

Restate the decision crisply and lock the variables before debating:
  • The decision: one sentence, with the specific option(s) on the table.
  • What changes for the customer: price, workflow, access, expectation.
  • Success metric: what "this went well" means in numbers.
  • Reversibility: can we walk it back, and at what cost?
If the user's ask is vague ("is this a good idea?"), tighten it into a decision with options before proceeding.
清晰重述决策内容，并在辩论前锁定变量：
  • 决策内容：一句话表述，明确列出可供选择的具体方案。
  • 对客户的影响：价格、工作流程、权限、预期的变化。
  • 成功指标：用数字定义“决策成功”的标准。
  • 可逆性：是否可以撤销决策，以及撤销的成本。
如果用户的需求模糊（比如“这个主意好吗？”），先将其细化为带有明确选项的决策，再继续下一步。

Step 2 — Seat the panel

步骤2 — 组建面板

Select 3–6 personas relevant to THIS decision (a pricing decision needs the economic buyer and a price-sensitive segment; a feature cut needs the power users who rely on it). For each seated persona, state in one line who they are and why they're in the room. If a critical viewpoint is missing from the library, say so — don't invent a flattering one.
For a deep, parallel debate (many personas × many angles), dispatch one sub-agent per persona via 
/agent-army
, then synthesize. Otherwise run it inline.
选择3–6个与当前决策相关的角色（比如定价决策需要经济决策者和对价格敏感的客户群体；功能削减决策需要依赖该功能的核心用户）。对于每个入选的角色，用一句话说明其身份以及参与辩论的原因。如果角色库中缺少关键视角，要明确指出——不要编造一个迎合需求的角色。
如需进行深度并行辩论（多个角色从多个角度参与），可通过
/agent-army
为每个角色分配一个子Agent，然后综合结果。否则可直接在线上运行辩论。

Step 3 — Run the debate

步骤3 — 开展辩论

Each persona argues in character, from their real goals, pains, and language — not as a generic critic. Structure:
  1. Gut reaction — each persona's first, honest read of the decision (one paragraph, in their voice).
  2. Cross-examination — personas challenge each other. The economic buyer and the end user often want opposite things; let that tension play out. Surface where one persona's win is another's loss.
  3. The strongest objection — the single most dangerous reaction, stated as that customer would actually say it (and would actually act on — churn, downgrade, public complaint, silence).
  4. What would change their mind — the concession, proof, or framing that flips a NO to a YES.
Keep personas honest: include the ones who will hate it. A panel that all agrees is a panel you rigged.
每个角色都要符合其设定，基于真实目标、痛点和语言风格进行辩论——而非泛泛的批评。辩论结构如下：
  1. 第一反应：每个角色对决策的第一真实看法（一段文字，符合其语气）。
  2. 交叉质询：角色之间互相质疑。经济决策者和终端用户的需求往往相反；要让这种矛盾充分展现。明确指出某个角色的收益是另一个角色的损失的场景。
  3. 最强烈的反对意见：最具危险性的客户反应，用客户真实的表述方式呈现（且客户确实会据此采取行动——比如流失、降级、公开投诉、沉默抵制）。
  4. 如何改变他们的想法：能让反对者转变态度的让步、证据或表述方式。
保持角色的真实性：要包含那些会强烈反对的客户。全票通过的面板说明你刻意筛选了角色。

Step 4 — Synthesize the decision

步骤4 — 综合决策结果

markdown
undefined
markdown
undefined

Customer Panel — {Decision}

客户专家面板 — {决策内容}

Generated: {timestamp} · Panel: {persona list} · Grounding: {data-backed / PROVISIONAL}
生成时间: {时间戳} · 面板成员: {角色列表} · 数据基础: {基于真实数据 / 临时版本}

Recommendation: {GO / GO WITH CHANGES / NO / TEST FIRST}

建议: {执行 / 调整后执行 / 不执行 / 先测试}

One paragraph: what to do and why, in plain language.
一段文字：明确说明要做什么以及原因，语言通俗易懂。

Vote by persona

角色投票情况

| Persona | Verdict | Why | If it ships anyway, they will… |
| 角色 | verdict | 理由 | 如果决策执行，他们会… |

The objections that matter (ranked)

关键反对意见（按优先级排序）

  1. {Objection} — who raises it, how likely to act, blast radius, mitigation.
  1. {反对意见} — 提出者、行动可能性、影响范围、缓解措施。

What this changes about the plan

对原计划的调整

  • Concrete edits to the launch / price / product before you commit.
  • 在执行前对推广/定价/产品做出的具体修改。

What to test before betting the company

下一步测试建议

  • The cheapest experiment that would de-risk the biggest unknown.
  • 成本最低的实验，可最大程度降低最大的未知风险。

Confidence & blind spots

信心程度与盲区

  • Grounding strength, which personas are thin, which viewpoint is missing.
undefined
  • 数据基础的可靠性、哪些角色信息不足、缺少哪些视角。
undefined

Step 5 — Offer the next move

步骤5 — 提供后续行动建议

Offer to: rerun the panel against a revised plan, hand the strongest objection to 
prospect-panel-simulator
to test live messaging, route a pricing decision to 
pricing-change-strategist
, or escalate a full launch to 
product-launch-war-room
.
可提供以下选项：针对修订后的计划重新运行面板、将最强烈的反对意见交给
prospect-panel-simulator
测试实时话术、将定价决策转交给
pricing-change-strategist
、或将完整的发布计划升级到
product-launch-war-room
处理。

Guardrails recap

规则回顾

Grounded personas beat invented ones — and provisional panels say so loudly · read-only connections · no real PII in output · include the customers who'll hate it · every verdict ties to a persona's real motivation.
基于真实数据的角色优于虚构角色——临时版本需明确标注 · 只读连接 · 输出中不得包含真实个人身份信息 · 要包含会反对的客户 · 每个结论都要与角色的真实动机相关。