Community程式設計與開發github.com

盈虧判定(Kill or Build)

你的商業計劃書統整器。將其他「鯊魚槽驗證」技能所產出的所有資料(評審團裁決、競爭者、買方座談小組、定價、提案、財務長數字、行銷、品牌、營運、上市計畫以及證據分類帳)彙整成一份商業計畫,並在頂端顯示自動計算得出的裁決(絕非手寫):獲利、未經驗證、尚未成功或不完整。模擬座談小組可以否決計畫,但絕不能通過計畫。另外會新增一份執行摘要和一頁式版本。當使用者說「幫我寫商業計畫」、「全部彙整」、「這能獲利嗎」、「給我計畫」,或是在「鯊魚槽驗證」系列結尾時使用。

盈虧判定(Kill or Build) 是什麼?

kill-or-build 是一項專為 AI 代理(如 Claude Code、Cursor)設計的技能,旨在自動產生誠實且可行的商業計畫。它會讀取「鯊魚槽驗證」套件中其他所有技能產生的結構化輸出——包含財務數字、競爭分析、買方座談小組結果、行銷策略等——並將其編譯成一份統一的商業計畫文件。這項技能的核心在其自動化裁決系統:根據嚴格的量化條件(單位利潤、年度營運利潤、產能內的損益兩平點、模擬買方轉換率,以及至少一項有真實買方付款、簽約或預訂的實際需求證據)來判定計畫為「獲利」、「未經驗證」、「尚未成功」或「不完整」。這確保了裁決是完全客觀且可追溯的,消除了人類在撰寫商業計畫時常見的主觀偏誤。kill-or-build 會產生三份關鍵文件:一份誠實的執行摘要(`summary.md`)、一份詳盡的完整商業計畫(`business-plan.md`),以及一份專為創辦人和親密合作夥伴設計的一頁式摘要(`one-pager.md`)。它還能與 /handshake 技能協作,用於為外部利害關係人(如客戶、投資者)建立更為審慎的摘要。這項技能對於任何需要將分散的驗證與市場研究自動整合成一份可執行且兼具批判性商業文件的開發者或創辦人來說,都至關重要。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/peaknr35/shark-Tank-proof/tree/main/skills/kill-or-build

Installed? Explore more 程式設計與開發 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

盈虧判定(kill-or-build)

最後一步。一份創辦人可以據以行動的文件,完全根據套件所發現的內容建構而成,並誠實揭露哪些部分是真實的。

請先閱讀 ${CLAUDE_SKILL_DIR}/../receipts/rules.md。

此資料夾中的工具:

python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder

步驟 1:檢視現有資料

python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder --check

此指令會輸出裁決結果以及每項檢查的狀態。以下為所有可供計算的檢查項目:

  1. 每個單位在扣除固定成本前能獲利(founder/numbers.json)。
  2. 第一年產生營業利潤。
  3. 若有提供產能資料,損益兩平點須在產能範圍內。
  4. 有足夠的模擬買方購買(founder/panel/results.json;預設比例為 25%,可使用 --min-buy-rate 變更並說明原因)。低的座談小組轉換率會使計畫失敗;高的轉換率則無法證明任何事情。
  5. 實際需求:在 founder/evidence/claims.csv 中至少有一項 MEASURED 的需求聲明(付款、訂金、已簽約試行、預訂)。

裁決結果:

裁決含義
不完整尚無數字:請提供 /burn-test
尚未成功某項檢查失敗;會列出失敗的項目編號
未經驗證紙上計算可行,但尚無真實買方承諾
獲利計算可行,且至少有一位真實買方承諾

請先執行 ledger.py summary,以便證據區塊為最新狀態:

python3 "${CLAUDE_SKILL_DIR}/../receipts/ledger.py" summary

如果沒有數字,裁決結果為「不完整」:提議執行 /burn-test。 列出其他遺漏的部分,以及能填補該部分的技能。請勿憑猜測自行填補遺漏的部分。

步驟 2:摘要

撰寫 founder/summary.md,長度約半頁,使用平實的文字,開頭必寫「殘酷的事實:」——這是此計畫最可能失敗的單一原因。

  • 用兩句話說明這項事業是什麼以及目標客戶是誰。
  • 裁決結果及其背後的三個數字(利潤率、損益兩平點、第一年狀況)。
  • 什麼是真實的:MEASURED 和 THEY SAID IT 聲明的數量,以及其內容。接著說明哪些部分仍屬猜測。
  • 模擬座談小組與評審團達成共識及意見分歧之處,並明確標示為模擬結果。
  • 最大的風險以及相應的應對措施。
  • 創辦人需要開始行動的事項(財務長提供的現金、上市計畫中的首次測試)。
  • 本週需要做的一件事。

如果裁決結果為「尚未成功」,摘要需以必須改變的事項以及可實施該改變的技能為開頭。如果為「未經驗證」,則需以本月能夠驗證或終結此計畫的唯一真實世界測試為開頭。切勿弱化任何失敗的檢查項目,也切勿將「未經驗證」的計畫撰寫得像是已通過驗證一般。

步驟 3:編譯

python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder

此指令會寫出 founder/business-plan.md:標題、裁決結果及其檢查項目、關鍵數字表格、商業構想,然後是套件產出的每個章節(摘要、評審團、競爭者、座談小組、定價、提案、數字、行銷、品牌、營運、上市),以及尚未完成的部分。

步驟 4:一頁式摘要

為創辦人及其緊密合作夥伴撰寫 founder/one-pager.md:問題、客戶、提案與價格、數字表格、真實證據(以及標示為模擬的座談小組結果)、資金用途,以及請求事項。數字必須與計畫書一模一樣。

對於外部人士(客戶、投資者、貸款機構),請勿寄送計畫書或此頁面:請執行 /handshake,它僅會根據該對象可以看到的聲明來建構內容,並檢查結果。

規則

  • 裁決結果來自 compile.py。切勿手寫「獲利」,切勿將失敗的數字四捨五入成通過的數字,也切勿稱「未經驗證」為「快成功了」。
  • 清楚說明一次:座談小組和評審團皆為模擬結果,數字均為預測值;唯有真實客戶和真實報價才能加以確認。此非財務、法律或稅務建議。
  • 如果使用者想要 PDF 或簡報,請提供匯出計畫書的選項,但應以 Markdown 作為唯一真實來源。

輸出

founder/summary.md、founder/business-plan.md、founder/one-pager.md。接著以一行告知使用者裁決結果、殘酷的事實,以及本週在真實世界中需要做的一件事。下一步:為需要說「好」的接收者執行 /handshake。

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".

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.

truth-serum

The consumer panel. Spins up a swarm of buyer sub-agents (default 100, --quick for 20) trained on the user's target customer, each with a different income, age, buying behaviour and objection, shows every one the same pitch, and runs the business through 100 buyer scenarios to see who buys, who doesn't, and why. Tallies the answers into buy rates by segment, the reasons people pass in their own words, what would flip a no, and price answers for litmus. Every result is labelled SIMULATED: it finds objections and the questions to ask real buyers, and never counts as demand. Use when the user says "would people buy this", "test it on customers", "run the consumer panel", "simulate buyers", "who is my customer", or "validate demand".

相關技能