Business Plan Compiler

Founder plan

by Jakeschincariol · MIT license · ★ 322 on GitHub

Your business planner. Compiles everything the other founder skills wrote (the board's verdict, the competitors, the buyer panel, pricing, the offer, the CFO's numbers, marketing, brand, operations and the launch plan) into one business…

---
name: founder-plan
description: >-
  Your business planner. Compiles everything the other founder skills wrote (the
  board's verdict, the competitors, the buyer panel, pricing, the offer, the CFO's
  numbers, marketing, brand, operations and the launch plan) into one business
  plan with a verdict at the top that is computed from the numbers, never written
  by hand: Profitable, Not yet (with the failing numbers) or Incomplete. Adds an
  executive summary and a one-page version for a partner, lender or investor. 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 founder pack.
argument-hint: "[--min-buy-rate 0.25]"
---

# founder-plan

The last step. One document a founder can act on, or hand to a partner or a
lender, built only from what the pack found.

Overview

The last step. One document a founder can act on, or hand to a partner or a lender, built only from what the pack found.

Manual install (npx, ZIP)

Claude Codenpx skills add Jakeschincariol/founder-skill --skill founder-plan -g -a claude-code

Claude Code (degit)npx degit Jakeschincariol/founder-skill/skills/founder-plan#main ~/.claude/skills/founder-plan

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md3.3 KB

Read SKILL.md here

Jakeschincariol/main1 file shown

SKILL.md3.3 KB

Browse every file on GitHub↗

SKILL.md

Show the full text89 lines

founder-plan/SKILL.md89 lines · 3.3 KB

PreviewCode

Outline

RawView on GitHub

founder-plan

The last step. One document a founder can act on, or hand to a partner or a lender, built only from what the pack found.

Tool in this folder:

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

Step 1: see what is there

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

prints the verdict and each check. The checks, all computed:

Each unit earns money before fixed costs (founder/numbers.json).
Year 1 makes an operating profit.
The break-even fits inside capacity, if a capacity was given.
Enough simulated buyers buy (founder/panel/results.json; default bar 25%, change it with --min-buy-rate and say why).

If there are no numbers, the verdict is Incomplete: offer to run /founder-cfo. 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:

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 the buyer panel and the board agreed on, and where they disagreed.
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 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. Never soften a failing check.

Step 3: compile

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.

Write founder/one-pager.md for someone deciding in two minutes: the problem, the customer, the offer and price, the numbers table, the evidence (panel result, competitor gap, any real test), what the money is for, and the ask. Same numbers as the plan, word for word.

Rules

The verdict comes from compile.py. Never write Profitable by hand, and never round a failing number into a passing one.
Say once, clearly: the panel is simulated buyers and the numbers are projections; 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 and the one thing to do this week.

1	---
2	name: founder-plan
3	description: >-
4	Your business planner. Compiles everything the other founder skills wrote (the
5	board's verdict, the competitors, the buyer panel, pricing, the offer, the CFO's
6	numbers, marketing, brand, operations and the launch plan) into one business
7	plan with a verdict at the top that is computed from the numbers, never written
8	by hand: Profitable, Not yet (with the failing numbers) or Incomplete. Adds an
9	executive summary and a one-page version for a partner, lender or investor. Use
10	when the user says "write my business plan", "put it all together", "is it
11	profitable", "give me the plan", or at the end of the founder pack.
12	argument-hint: "[--min-buy-rate 0.25]"
13	---
14
15	# founder-plan
16
17	The last step. One document a founder can act on, or hand to a partner or a
18	lender, built only from what the pack found.
19
20	Tool in this folder:
21
22	```bash
23	python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder
24	```
25
26	## Step 1: see what is there
27
28	```bash
29	python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder --check
30	```
31
32	prints the verdict and each check. The checks, all computed:
33
34	1. Each unit earns money before fixed costs (`founder/numbers.json`).
35	2. Year 1 makes an operating profit.
36	3. The break-even fits inside capacity, if a capacity was given.
37	4. Enough simulated buyers buy (`founder/panel/results.json`; default bar 25%,
38	change it with `--min-buy-rate` and say why).
39
40	If there are no numbers, the verdict is Incomplete: offer to run `/founder-cfo`.
41	List the other missing sections with the skill that fills each. Do not fill a
42	missing section yourself from guesses.
43
44	## Step 2: the summary
45
46	Write `founder/summary.md`, half a page, plain words:
47
48	- What the business is and who it is for, in two sentences.
49	- The verdict and the three numbers behind it (margin, break-even, year 1).
50	- What the buyer panel and the board agreed on, and where they disagreed.
51	- The biggest risk and what will be done about it.
52	- What the founder needs to start (cash from the CFO, the first test from launch).
53	- The one thing to do this week.
54
55	If the verdict is Not yet, the summary leads with what has to change and which skill
56	changes it. Never soften a failing check.
57
58	## Step 3: compile
59
60	```bash
61	python3 "${CLAUDE_SKILL_DIR}/compile.py" --dir founder
62	```
63
64	writes `founder/business-plan.md`: title, the verdict and its checks, the key numbers
65	table, the idea, then every section the pack produced (summary, board, competition,
66	panel, pricing, offer, numbers, marketing, brand, operations, launch), and what is
67	not done yet.
68
69	## Step 4: the one-pager
70
71	Write `founder/one-pager.md` for someone deciding in two minutes: the problem, the
72	customer, the offer and price, the numbers table, the evidence (panel result,
73	competitor gap, any real test), what the money is for, and the ask. Same numbers as
74	the plan, word for word.
75
76	## Rules
77
78	- The verdict comes from `compile.py`. Never write Profitable by hand, and never
79	round a failing number into a passing one.
80	- Say once, clearly: the panel is simulated buyers and the numbers are projections;
81	real customers and real quotes confirm them. Not financial, legal or tax advice.
82	- If the user wants a PDF or a deck, offer to export the plan, but keep the
83	markdown as the source of truth.
84
85	## Output
86
87	`founder/summary.md`, `founder/business-plan.md`, `founder/one-pager.md`. Then give
88	the user the verdict in one line and the one thing to do this week.
89