Community程式設計與開發github.com

handshake (提案生成)

根據創辦人實際掌握的證據,為顧客、投資者或資助者等對象撰寫針對性的單頁提案,並確保內容真實可信、可直接寄送。

handshake (提案生成) 是什麼?

handshake 是一個專為創辦人設計的 AI 技能,其核心功能是將創辦人資料夾中的證據轉化為針對單一對象、單一行動(「是」)的具體提案,例如顧客試用、NSF 專案提案、投資者摘要或內部商業論證。它依賴於嚴格的證據帳本(ledger)系統,所有宣稱都必須來自已被驗證的資料,嚴禁使用虛擬買家或未經許可的資訊。handshake 支援多種平台(如 Claude Code),工作流程包含四個步驟:確認對象與目標、檢查帳本支援度、撰寫並附上引證(如 [c04])、以及最終掃描驗證。它的獨特之處在於強制誠實揭露不確定性,並明確列出提案中的差距(gaps),幫助創辦人在寄送前就能修正問題,最終產生可寄送的文件與後續行動清單。

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

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

handshake (提案生成) 是做什麼的?

計劃是為創辦人準備的。提案則是為一個人、一個「是」而寫的。這項技能從實際已知的事實出發,讓創辦人無需為一個無法證實的數字辯護,即可直接寄出。

使用者在 /handshake 後輸入的內容:$ARGUMENTS

先閱讀 ${CLAUDE_SKILL_DIR}/../receipts/rules.md。帳本工具:

python3 "${CLAUDE_SKILL_DIR}/../receipts/ledger.py" <gate | scan | summary>

以下,LEDGER 即指上述指令。

步驟 1:對象是誰,以及什麼「是」

若未指定,請詢問對象是誰以及創辦人希望得到的「是」。指明接收者:顧客、資助者、投資者、貸款機構、企業內部人員、或是產品的使用者。閱讀 ${CLAUDE_SKILL_DIR}/receivers.md 以了解該類接收者需要看到什麼。

如果對方提供了文件(如 RFP、徵求提案、電子郵件、職缺公告),請先閱讀,從中提取他們明確提出的要求,並儲存為 founder/opportunities/<name>.md(格式:${CLAUDE_SKILL_DIR}/../first-dollar/opportunity.md)。

將要求壓縮到最小、最實際的「是」(規則 7)。如果創辦人想向陌生人索取一筆大額預付款,請明確指出:一個基於對方自身數據、有時限的試用計畫,更有可能獲得同意;並同時提供兩種選項。

步驟 2:資料夾能支撐什麼

LEDGER check
LEDGER gate --audience <public | anonymised | permission>

根據提案的傳播方式選擇聽眾:public 用於可能被轉發的內容、anonymised 用於私密寄送、permission 僅在 founder/evidence/people.md 中每個 ASK FIRST 宣稱者都已同意時使用。

僅根據 gate 輸出的內容來建構提案。如果接收者需要的資料是資料夾無法支援的,請不要迴避:在輸出結尾的 Gaps(差距)段落下列出,並說明如何取得(/receipts 的任務 4 會深入處理)。切勿用猜測、引用面板意見或董事會觀點來填補差距。

如果關於需求的任何內容都未被 MEASURED(測量),提案應誠實地透過措辭表達:「我們正在尋找三家公司進行試用」,而不是「公司已排隊等候」。

步驟 3:撰寫

  1. 一句話版本、三句話版本、三分鐘大綱。
  2. 接收者所需的格式(來自 receivers.md)。如果對方提供了徵求提案或通話內容,請使用他們自己的標題來回答。遵守他們的限制(對 NSF 的章節計算字元數並標明)。
  3. 在工作草稿中,每個事實都引用其宣稱 ID,例如 [c04]。將 PLANNED(計畫中)的宣稱寫為目標(「我們預期」、「試用將測試」),絕不能寫成結果。
  4. 一個簡短的可能出錯的地方(What could go wrong)區段,使用平實的語言。接收者信任這一點。
  5. Gaps(差距):為了讓這份提案更強而有力所需要的內容,以及每項差距最便宜的取得方式。

將成果儲存為 founder/outputs/<YYYY-MM-DD>-<receiver>.md。

步驟 4:寄出前檢查

LEDGER scan founder/outputs/<file>.md --audience <the same audience>

scan 會拒絕任何接收者無法看到的引用宣稱(如 SIMULATED 或 PRIVATE 宣稱、未獲許可的 ASK FIRST),並標記那些沒有真實買家付款或簽約的證詞(「驗證過」、「已證明」、「強勁需求」)。修正它列出的每個問題,並重新執行直到完全乾淨。然後,如果創辦人需要,可以製作一份不含 [c..] ID 的可寄送副本,同時保留引用版本的草稿。

規則

  • 絕對不引用、計算或描述虛擬買家、董事會成員或模型輸出為真實顧客、使用者、顧問或市場研究。
  • 不得有虛構的顧問、合作夥伴、標誌、客戶名稱或數字。「會計領域的顧問」需要在 people.md 中有真實顧問的姓名,並已同意被列出。
  • 沒有來源的市場規模不可引用;否則應寫為附帶方法的估計值。
  • 寄送是創辦人的責任。草擬電子郵件或訊息,但不要實際寄出。

輸出

founder/outputs/<日期>-<接收者>.md(若需可另附乾淨副本),以及若有徵求提案或通話則有 founder/opportunities/<名稱>.md。結尾應包含一句話摘要、差距清單,以及下一步行動:本週應寄送給誰、以及對方回覆時應使用 /receipts 記錄什麼。

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.

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.

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