kill-or-build
/kill-or-build
Składa wyniki kolejnych analiz w jeden plan biznesowy, z werdyktem obliczonym z danych i dowodów.
- Autor
- peaknr35 ↗
- Repozytorium
- shark-Tank-proof ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 04.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 2
- Skrypty
- 1
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 04.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 1 skrypt w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: compile.py
Co robi i kiedy
Składa wyniki kolejnych analiz w jeden plan biznesowy, z werdyktem obliczonym z danych i dowodów.
Argumenty
/kill-or-build [--min-buy-rate 0.25]
Oryginalny opis (EN)
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-
Jak działa
- Handoff contract (stage 11 in founder/CONTEXT.md)
- Step 1: see what is there
- Step 2: the summary
- Step 3: compile
- Step 3b: the Ready, Fire, Aim answers
- Step 4: the one-pager
- Rules
- Output
Podgląd SKILL.md
---
name: kill-or-build
description: >-
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.
argument-hint: "[--min-buy-rate 0.25]"
---
# kill-or-build
The last step. One document a founder can act on, built only from what the
pack found, and honest about which parts are real.
Read `${CLAUDE_SKILL_DIR}/../receipts/rules.md` first.
Tool in this folder:
```bash
python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder
```
## Handoff contract (stage 11 in `founder/CONTEXT.md`)
This is where a simulated number would finally pass as a fact, by being added
up with real ones. Rule 10 in `rules.md` stops it: every number takes the
weakest label of anything it was computed from.
**Inputs**
| input | label |
| --- | --- |
| `founder/numbers.json` with its `sources` and item `claim` ids | each input's label, looked up in the ledger |
| `founder/evidence/claims.csv` | the labels themselves, and the `from` column of computed claims |
| `founder/panel/results.json` | always `SIMULATED` |
| `founder/handoff/06_burn-test.json` | what `/burn-test` handed on; if its labels differ from what the ledger gives now, the plan flags a stale handoff |
**Process:** `compile.py` reruns the CFO's math with the ledger, so every money
check carries the weakest label of its inputs, then computes the verdict.
**Outputs**
| output | label |
| --- | --- |
| each check in `founder/business-plan.md` | printed after it, with the input that set it: `[SIMULATED: price [c08]]` |
| the key numbers table | a "how we know" column |
| the verdict | Profitable only if no money check passes on a `SIMULATED` input |
| label leaks | a computed claim in the ledger that says more than its sources is listed under the verdict |
## Step 1: see what is there
```bash
python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder --check
```
prints the verdict and each check. The checks, all computed:
1. Each unit earns money before fixed costs (`founder/numbers.json`).
2. Year 1 makes an operating profit.
3. The break-even fits inside capacity, if a capacity was given.
4. Enough simulated buyers buy (`founder/panel/results.json`; default bar 25%,
change it with `--min-buy-rate` and say why). A low panel fails the plan; a
high panel proves nothing.
5. Real demand: at least one `MEASURED` demand claim in
`founder/evidence/claims.csv` (a payment, a deposit, a signed pilot, a
booking).
Checks 1 to 3 print their label. A check that passes on a `SIMULATED` input
(the usual case: the price came from the panel) can fail the plan but cannot
pass it, the same as check 4.
The verdicts:
| verdict | means |
| --- | --- |
| Incomplete | no numbers yet: offer `/burn-test` |
| Not yet | a check fails; each failure is listed with its number |
| Unproven | the math works on paper, but no real buyer has committed, a money check passes only on a simulated input, or the price or a cost is still an estimate (`PLANNED`) |
| Profitable | the math works, at least one real buyer committed, and the price and every cost are real: a sale, a quote, an invoice. Only the volumes (ramp, plan, selling days) may stay forecasts |
Run `ledger.py summary` first so the evidence section is current:
```bash
python3 "${CLAUDE_SKILL_DIR}/../receipts/ledger.py" summary
```
If there are no numbers, the verdict is Incomplete: offer to run `/burn-test`.
List the other missing sections with the skill that fills each. Do not fill a
missing section yourself from guesses.
## Step 2: the summary
Write `founder/summary.md`, half a page, plain words, opening with **The hard
truth:** the single most likely reason this fails.
- What the business is and who it is for, in two sentences.
- The verdict and the three numbers behind it (margin, break-even, year 1).
- What is real: the count of `MEASURED` and `THEY SAID IT` claims, and what
they are. Then what is still a guess.
- What the simulated panel and board agreed on, and where they disagreed,
labelled as simulated.
- The biggest risk and what will be done about it.
- What the founder needs to start (cash from the CFO, the first test from launch).
- The stage (Stage One unless yearly sales say otherwise) and what that
stage asks of the founder now: in Stage One, selling the first product,
most of their time on finding customers.
- The selling strategy in four lines: where the customers are, what they buy
first, at what price, with what words, each with its label.
- What a customer is worth and what it costs to win one (from `cfo.md`).
- The one thing to do this week.
If the verdict is Not yet, the summary leads with what has to change and which skill
changes it. If it is Unproven, it leads with the one real-world test that would
prove or kill it this month. Never soften a failing check, and never write an
Unproven plan as if it were a validated one.
## Step 3: compile
```bash
python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder
```
writes `founder/business-plan.md`: title, the verdict and its checks, the key numbers
table, the idea, then every section the pack produced (summary, board, competition,
panel, pricing, offer, numbers, marketing, brand, operations, launch), and what is
not done yet.
## Step 3b: the Ready, Fire, Aim answers
Rule 11 in `rules.md` (after Michael Masterson's *Ready, Fire, Aim*).
At the end of `founder/summary.md`, answer the seven questions from `/prove-it`
step 0 (good idea, feels right, feasible, affordable to test, tasks known,
people, Plan B) in one line each, from what the folder holds. A question the
folder cannot answer is the next job, not a pass.
## Step 4: the one-pager
Write `founder/one-pager.md` for the founder and close partners: the problem,
the customer, the offer and price, the numbers table, the real evidence (and
the panel, labelled simulated), what the money is for, and the ask. Same
numbers as the plan, word for word.
For anyone outside (a customer, a funder, a lender), do not send the plan or
this page: run `/handshake`, which builds only from claims that audience
may see and checks the result.
## Rules
- The verdict comes from `compile.py`. Never write Profitable by hand, never
round a failing number into a passing one, and never call Unproven "almost
there".
- Quote every number in the summary and one-pager with the label the plan
printed. A margin the plan marks `SIMULATED` is never written as the margin.
- Say once, clearly: the panel and board are simulated and the numbers are
projections; only real customers and real quotes confirm them. Not financial,
legal or tax advice.
- If the user wants a PDF or a deck, offer to export the plan, but keep the
markdown as the source of truth.
## Output
`founder/summary.md`, `founder/business-plan.md`, `founder/one-pager.md`. Then give
the user the verdict in one line, the hard truth, and the one real-world thing
to do this week. Next: `/handshake` for the receiver who has to say yes.
Pliki w paczce (2)
- SKILL.md 7 KB
- compile.py 18 KB
Wersje
W bazie nie ma innych skilli o nazwie kill-or-build.
Migawka bazy z 13.11.2026 · wersja paczki 2f9dd2879e54 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100founder-plan
Składa wyniki modułów założycielskich w jeden plan biznesowy z werdyktem liczonym z liczb: zyskowny, jeszcze nie lub niekompletny. - 100founder-plan
Składa wyniki pozostałych skilli founderowych w jeden biznesplan z werdyktem wyliczonym z liczb (Profitable, Not yet lub Incomplete), streszczeniem zarządczym i wersją jednostronicową. - 100startup-plan
Łączy wyniki pakietu startupowego w jeden plan biznesowy, a werdykt wylicza z danych zamiast wpisywać go ręcznie. - 100crowdstop-plan
Składa notatki zespołu w jeden plan biznesowy i pozwala liczbom wydać werdykt: gotowy, jeszcze nie lub niekompletny. - 100ambitious-founder
Łączy przegląd ambicji z testem pomysłu na biznes: konkurencja, symulowany panel kupujących i wycenę metodą Van Westendorp. - 100receipts
Prowadzi rejestr dowodów dla pakietu Shark Tank Proof: oznacza, skąd wiadomo każdą tezę i kto może ją zobaczyć, i wskazuje luki.