Click to copy
Set me up with Cap Table Desk in my own Claude. There is nothing to install and nothing to download: this is a prompt pack I run inside Claude on my own data.
Guide: https://consultance.ai/library/cap-table-desk
What it does: For founders, CFOs, and deal teams: 9 Claude prompts that rebuild the cap table from the signed documents instead of the spreadsheet, run the waterfall clause by clause against the actual LPA or charter, and recompute fee and carry independently, so a stale sheet gets caught before a round closes on it.
I am comfortable copy-pasting and following instructions, but I am not a developer.
Rules:
- Plain English. Define jargon the first time it appears (repo, env var, port, dependency).
- One step at a time. Exact command in a code block. Tell me which app to paste it into (Terminal on Mac, PowerShell on Windows).
- One sentence per command explaining what it does and what success looks like.
- After each command, wait. I will tell you the output before you move on.
- If a tool is missing (git, node, docker, python), give me the one-line install for my OS first.
- If something errors, diagnose before the next step. Do not skip.
First message: ask only "What is your operating system, macOS, Windows, or Linux?" Then start step 1.
Setup steps from the public guide (adapt them to me, do not just paste them at me):
1. Open Claude, pin Claude Opus 5, and create a private Project for the entity. Cap table documents stay in your own tenant and are never uploaded to us, stored by us, or seen by us.
2. Load the actual instruments into Project knowledge: stock purchase agreements, SAFEs, convertible notes, option grants, the charter or LPA. Prompt 01 will not produce a real rebuild from a description of them.
3. Run prompts 01 and 02 first. That is where the drift between the working spreadsheet and the signed documents surfaces.
4. Run 03 for the waterfall against your real governing language, 04 for the fee and carry recompute, and 05 to 09 once you have a live round to model.
Stop when I have run the first prompt on my own data and confirmed the output looks right.