Community编程与开发github.com

真相血清

消费者座谈会模拟器。自动生成一组买家子代理(默认100个,--quick为20个),每个代理根据目标客户画像拥有不同的收入、年龄、购买行为和顾虑,逐一呈现相同的推销方案,模拟100个买家场景,统计谁买、谁不买以及原因。按细分市场汇总购买率、买家原话表述的拒绝原因、改变决策的关键因素以及价格敏感度测试结果。所有结果均标注为“模拟”:用于发现潜在顾虑和需要向真实买家提出的问题,绝不作为实际需求统计。

真相血清 是什么?

真相血清(truth-serum)是一个AI代理技能,专为Claude Code等AI编程助手设计,用于快速模拟消费者座谈会。它自动生成大量买家子代理(默认100个,可通过--quick参数缩减至20个),每个代理都拥有独特的收入、年龄、购买行为和顾虑,所有代理都基于用户定义的目标客户画像进行训练。该技能完整执行“推销→回应→分析”流程:用户首先定义目标客户画像(包括细分市场、行为模式和常见顾虑),然后撰写推销文案,系统会为每个买家分配角色卡片并逐一展示推销方案。最终生成详细报告,包括购买率、拒绝原因(买家原话)、改变决策的关键因素以及价格敏感度测试结果。所有结果均明确标注为“模拟”(SIMULATED),旨在发现潜在顾虑和优化问题,而非预测实际转化率。该技能适用于消费者市场分析,但也明确警告:对于面向少数企业的B2B场景,真实电话调研效果更佳。这是一个强有力的假设检验工具,但绝不能替代真实市场验证。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/peaknr35/shark-Tank-proof/tree/main/skills/truth-serum

Installed? Explore more 编程与开发 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

真相血清 是做什么的?

与其猜测买家会提出哪些顾虑,不如直接询问一百个模拟买家——每个都是一个扮演特定买家角色的子代理,这些角色源自你的目标客户。你是主持人。你永远不为买家做回答。

用途:发现潜在顾虑、细分市场、措辞优化以及需要向真实用户提出的问题。 非用途:需求预测。语言模型倾向于“赞同”,因此高购买率只是最佳情况,而非预测;它可以推翻一个计划,但绝不可能验证一个计划。

请先阅读 ${CLAUDE_SKILL_DIR}/../receipts/rules.md。

用户在 /truth-serum 后输入的内容:$ARGUMENTS

工具

所有记录工作通过本技能文件夹中的 panel.py 完成:

python3 "${CLAUDE_SKILL_DIR}/panel.py" <command>

下文中的 PANEL 即指上述命令。如果路径未展开,请使用 Claude Code 为此技能打印的基础目录。状态数据保存在 founder/panel/ 中。

步骤1:目标客户

写入 founder/customer.json(形状:参考本文件夹中的 customer.example.json):

  • business 和 target:用一句具体的话描述客户是谁。
  • segments:2 到 4 个细分群体,每个群体包含 share 和 income 范围 [low, high]。
  • behaviours:4 到 8 种购买行为,每种行为包含 share 和 how 描述(如:每日常客、寻找优惠、阅读每一条评论、忠实于某一竞争对手……)。
  • objections:这类买家真正会有的 4 到 8 个顾虑。
  • habits(可选):使买家形象更具体的日常情境描述。

将其建立在真实信息之上。使用用户对其客户的了解;如果 /ground-truth 已运行,则参考 founder/competitors.md 中的投诉内容。如果用户拥有真实的客户数据(founder/evidence/calls/ 中的通话记录、评价、调查回复),优先使用这些数据而非你的猜测,并明确指出哪些部分是猜测。

如果目标客户是少数企业用户(几百家公司,而非大众市场),请明确说明:五个真实电话调研比这个模拟座谈会更有价值,并优先提供 /receipts 及其通话指南。仅当需要打磨问题时才运行模拟。用几句话向用户展示客户画像,并在进行交易前允许用户修正——错误的客户画像会使整个模拟失效。

步骤2:推销方案

写入 founder/pitch.md:买家实际会看到的内容。产品、价格、获取渠道、限时优惠。三到六行简洁描述,无夸张表述,所有内容必须是企业能够实现的。每个买家看到的都是完全相同的内容。

步骤3:分配并运行

PANEL init --customer founder/customer.json --pitch founder/pitch.md --n 100
PANEL prompts

init 负责分配角色卡片(相同种子,相同卡片;种子会被记录)。prompts 为每个买家撰写简报,并按每批10人分组列出。对于每一批,通过Agent工具(在旧版Claude Code中称为Task)发送一条消息,为批次中的每个买家调用一次:

  • subagent_type:general-purpose
  • description:panel <id>
  • prompt:Read <brief path> and follow it exactly. It is your whole brief.

等待整批完成后再进行下一批。Claude Code 默认每次运行约10个工具调用,因此100个买家需要10个批次。最后一批完成后:

PANEL check      # 列出缺失或异常的回答
PANEL prompts    # 仅重写失败买家的简报;再次运行它们
PANEL tally

如果某个买家在其回复中直接打印了JSON而不是写入文件(这种情况可能发生),请使用 PANEL save <id> 并从stdin传入回复内容;save 会拒绝任何格式不正确的答案。连续失败两次的买家将被排除并计入结果中。你绝不可亲自为买家撰写答案。

在运行100个买家之前,告知用户这是100次子代理调用,并建议使用 --quick(20个买家)进行初步查看。子代理会将各自的文件写入 founder/panel/answers/;在默认权限模式下,每个文件需要单独批准,因此建议在运行过程中使用接受编辑模式(Shift+Tab)。

步骤4:向用户汇报结果

PANEL tally 会生成 founder/panel/results.md 和 results.json。向用户呈现以下内容:

  1. 残酷真相:买家放弃的最强原因,用一句话概括;同时提醒购买率是模拟结果,只是一个上限。
  2. 标题:“40 购买 · 60 放弃(模拟)”以及购买率。
  3. 谁买谁不买:差异最大的细分市场和购买行为行。
  4. 为什么放弃:前三名原因,每个原因附带一条买家原话。
  5. 能改变拒绝的因素:最常被提到的答案。
  6. 一句话建议:在花钱之前需要改变什么,以及哪个技能可以实现(定价、优惠、营销)。
  7. 走向真实用户:将前三名顾虑转化为真实通话中要提出的问题,风格参照 ${CLAUDE_SKILL_DIR}/../receipts/conversations.md(关注对方的过去,而非你的想法)。这才是模拟座谈会的真正价值所在。

然后将结果记录为 SIMULATED:

python3 "${CLAUDE_SKILL_DIR}/../receipts/ledger.py" add --kind demand --status SIMULATED --use PRIVATE --by truth-serum --claim "模拟座谈会购买率(种子 <S>)" --number "<购买数> 个 / <回答数> 个"

坦诚的局限,只说一次

这些都是模拟买家。它们擅长发现你未曾想到的顾虑、细分市场和措辞,但在预测真实转化率方面能力有限:语言模型倾向于“赞同”,因此请将购买率视为上限。在做出任何重大决策之前,务必通过真实用户进行验证(等待列表、预售、试点项目、带有定价的落地页)。绝不要将模拟座谈会称为“验证”、“市场调研”或“真实客户”,也不要在推销、广告、产品演示或资助申请中将模拟买家当作真实客户引用。

每位买家收到的简报

panel.py 将卡片填入固定模板(参见脚本中的 BRIEF):买家信息(姓名、年龄、细分市场、收入、购买行为、习惯、脑海中浮现的顾虑)、逐字呈现的推销方案、要求其不认同且不捏造事实的指令,以及要写入的确切JSON格式:是否购买、首月购买次数、拒绝代码、用买家自己的话表述的理由、主要顾虑、什么能改变其想法、以及四个价格敏感度回答(太便宜、划算、变贵、太贵)。绝对不单独编辑任何一个买家的简报。

输出

founder/customer.json、founder/pitch.md、founder/panel/(卡片、简报、回答、结果)。 下一步:/litmus 读取价格敏感度回答,/dealbreaker 和 /signal 读取顾虑信息。

Individual skills in this repo

This repo contains 5 individual skills — each has its own dedicated page.

burn-test

Your CFO. Builds the unit economics of a business before money is spent: what one unit earns after its direct costs, the real profit margin at the planned volume, the break-even point in units a day, year 1 month by month, the cash needed before it pays for itself, how long the startup spend takes to earn back, and what happens if the price drops, sales come in low or costs rise. Every number traces to an input the user can check. Use when the user says "find the profit margins", "do the numbers", "is this profitable", "break-even", "unit economics", "how much do I need to start", or "run the CFO".

dealbreaker

Builds an offer too good to refuse. Lists every problem the buyer hits on the way to the result they want, turns each into a solution, trims to what is cheap to deliver and valuable to the buyer, and stacks it with honest bonuses, a guarantee the CFO can afford, real urgency and a clear name. Scores it on the value equation (outcome, likelihood, time, effort) and re-tests it on a quick buyer panel. Use when the user says "make my offer better", "why won't people buy", "what should I include", "guarantee", "bonuses", "grand slam offer", or after the panel shows people passing.

handshake

Turns the founder folder into the thing that gets one real person to say yes to the next step: a one-page pilot offer for a customer, an NSF Project Pitch or grant answer for a funder, an investor or lender one-pager, a business case for a boss, or an invite for the people who will use it. Always writes the one-sentence, three-sentence and three-minute versions first. Builds only from claims in the evidence ledger that the audience may see, never from simulated buyers, and checks the finished pitch with the ledger before it goes out. Use when the user says "pitch this", "write a pilot offer", "one-pager", "grant pitch", "NSF pitch", "deck for", "email this customer", "business case", or "what do I send them".

kill-or-build

Your business planner. Compiles everything the other Shark Tank Proof skills wrote (the board's verdict, the competitors, the buyer panel, pricing, the offer, the CFO's numbers, marketing, brand, operations, the launch plan and the evidence ledger) into one business plan with a verdict at the top that is computed, never written by hand: Profitable (the numbers pass and a real buyer has paid, signed or booked), Unproven (works on paper, no real buyer yet), Not yet (with the failing numbers) or Incomplete. A simulated panel can fail a plan but never pass one. Adds an executive summary and a one-page version. Use when the user says "write my business plan", "put it all together", "is it profitable", "give me the plan", or at the end of the Shark Tank Proof pack.

shark-board

Your board of directors, built to disagree with you. Puts a business idea in front of a four-member board, each a sub-agent reading the idea through one published framework: the Offers lens (from Alex Hormozi's $100M Offers), the Monopoly lens (from Peter Thiel's Zero to One), the Product lens (from Walter Isaacson's biography of Steve Jobs) and the Evidence lens (from Rob Fitzpatrick's The Mom Test), which scores only what real people have done. Each member scores the idea, names what would kill it and the cheapest test that would prove it, and votes fund, fund with conditions, or pass. Use when the user says "test my business idea", "would this work", "pressure-test this", "what would a board say", "is this a good business", or starts the Shark Tank Proof pack on a new idea.

相关技能