agentleFS
JakeschincariolJakeschincariol/seed-skill/seed-dataroom/SKILL.md

seed-dataroom

Skill51 starsChanged 11 days agoMITView on GitHub

Data Room Builder. Assembles the data room investors ask for and tells you what is missing. Lays out the nine standard folders (01 Company, 02 Pitch deck, 03 Financials, 04 Market, 05 Product, 06 Team, 07 Legal, 08 Cap table, 09 Customers), checks the files against a 25-item checklist (present, missing, or stale by the date in the file name or its last change), writes seed/dataroom/INDEX.md describing every file, and lists what to share before a term sheet and what only after one. Flags what must never be in a data room: passwords, keys, ID documents, raw customer lists. It never uploads or shares anything. Use when the user says "build my data room", "what goes in a data room", "what am I missing for diligence", "the investor asked for the data room", "what can I share now", "make an index of my documents", or after a /seed-closer call goes well or /seed-terms reads a term sheet.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every command takes --dir (default ./seed) and --today.

    line 40
  2. Distinctive:

    Never uploads, shares or emails a file, and never opens one's contents.

    line 113
  3. Distinctive:

    Never creates a document to fill a gap: a missing item stays missing until the user provides it.

    line 114
  4. Distinctive:

    Never promises that a complete data room gets a deal closed.

    line 116

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

seed-dataroom

The Data Room Builder gets the documents in order before an investor asks for them, so the answer to "can you send the data room?" is a link the same day, not a week of digging. It sets up the standard folders, checks what is there against the list investors work through, warns when a file is too old to send (a cap table from last quarter, metrics from June), and writes an index so the investor can find everything. It also keeps the sequence straight: the deck and the model go out after a first meeting; the cap table, contracts and bank statements wait for a signed term sheet.

${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).

python3 "${CLAUDE_SKILL_DIR}/dataroom.py" init                        # the nine folders in seed/dataroom/
python3 "${CLAUDE_SKILL_DIR}/dataroom.py" check --today 2026-10-26    # present / missing / stale
python3 "${CLAUDE_SKILL_DIR}/dataroom.py" check --stage before        # only what goes out before a term sheet
python3 "${CLAUDE_SKILL_DIR}/dataroom.py" index                       # writes seed/dataroom/INDEX.md
python3 "${CLAUDE_SKILL_DIR}/dataroom.py" share-list --stage before   # what to send now, and what waits

Every command takes --dir (default ./seed) and --today; check and share-list take --json.

What it reads and writes

filewhat
seed/dataroom/01 Company/ ... 09 Customers/the folders init creates; the user (or Claude, on request) puts files in them
seed/config.jsonthe startup's name, for the index title (optional)
seed/dataroom/INDEX.mdwritten by index: every file, what it is, its date, size, and when to share it

The checklist

folderbefore a term sheetafter a signed term sheet
01 Companyone-pager (90 days), business plan (90)
02 Pitch deckthe deck as a PDF (90)
03 Financialsthe 36-month model (60), use of funds (90)historical P&L and balance sheet (45), bank statements (45)
04 Marketmarket sizing (180), competitor analysis (90)
05 Producta demo (90), traction and KPIs (45), roadmap (120)
06 Teamfounder bios (365)org chart and hiring plan (180), IP assignments
07 Legalincorporation and bylaws, board consents, IP, material contracts
08 Cap tablethe cap table (30), signed SAFEs and notes, the option plan
09 Customerstestimonials and reviews (180)references (180), waitlist, pilots and LOIs as counts (90)

The number is how many days old a file can be before it is stale. A file matches an item when its name has one of the item's keywords ("deck", "cap table", "model" ...) and it sits in that item's folder. Its date is the date in the name (Cap table 2026-10-01.xlsx, Metrics 2026-10.pdf) when there is one, else the day it was last changed, read in UTC so the computer's time zone never moves it.

Rules

  • Files that look like a password, a key or token, a personal ID document, or a raw customer list are flagged "DO NOT SHARE" and left out of the index. Share counts of customers, never their names and emails.
  • Files outside the nine folders are listed as loose; files the checklist does not know are listed as "other" (they still go in the index).
  • Nothing is shared by this skill. The user picks the tool (Google Drive, Dropbox, DocSend, Notion) and who gets the link. Prefer one view-only link per investor; ask for an NDA before the "after" folders.

Steps

  1. dataroom.py init. Tell the user what goes in each folder.
  2. Fill it from the pack: /seed-deck's seed/deck.html printed to PDF into 02 Pitch deck, /seed-plan's seed/plan.md into 01 Company, /seed-model's export into 03 Financials, /seed-market and /seed-scout's results into 04 Market. The rest (legal, bank, cap table) comes from the user; ask, never invent a document.
  3. dataroom.py check. Read back what is missing and what is stale, most urgent first (the stage the user is at). Remove anything flagged DO NOT SHARE before going further.
  4. dataroom.py index once the "before" items are in.
  5. dataroom.py share-list --stage before when an investor asks after a first call; --stage after once a term sheet is signed (/seed-terms). The user shares the link themselves.

Example: the reel

Leashly (fictional) after the Northlight call on Thursday, Nov 5. The room has the one-pager, the business plan, the 10-slide deck, the model, the use of funds for the $1.5M seed, the market sizing (APPA's $158B and 71M dog homes) and the Rover / Wag! competitor analysis. check --stage before shows 9 of 12 items present, the traction metrics from June stale (147 days, limit 45), and the roadmap and testimonials missing. A stray customer list export.csv is flagged DO NOT SHARE. Fix those three, run index, and the deck-to-demo half of the room is ready to send to Maya the same day; the cap table (86 days old, limit 30) gets refreshed before any term sheet.

What it never does

  • Never uploads, shares or emails a file, and never opens one's contents.
  • Never creates a document to fill a gap: a missing item stays missing until the user provides it.
  • Never promises that a complete data room gets a deal closed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.