data-room-builder
Skill0 starsChanged 4 months agoMITView on GitHub
Use when a founder needs to prepare materials for investor due diligence. Triggers on "set up a data room", "what goes in a data room", "diligence checklist", "prepare for due diligence", "investors asked for our data room". Builds the organized, staged room that makes diligence fast and confidence-building.
In this repository19 other files it gives its agents.
- cap-table-managerSkill
- due-diligence-checklistSkill
- financial-plannerSkill
- fundraise-closing-mechanicsSkill
- fundraise-readiness-auditSkill
- fundraise-team-hiringSkill
- fundraising-narrativeSkill
- fundraising-stage-selectorSkill
- investor-pipeline-crmSkill
- investor-targetingSkill
- investor-update-writerSkill
- market-sizingSkill
- pitch-deck-builderSkill
- pitch-practice-coachSkill
- safe-vs-priced-roundSkill
- series-a-readinessSkill
- term-sheet-explainerSkill
- term-sheet-negotiationSkill
- vc-pitch-emailSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 53
Keep an index document at the root so a partner can navigate without asking.
- Distinctive: line 70
Every metric in the room reconciles to the deck and the model to the decimal, with one named source of truth per number.
- Distinctive: line 74
Every file is labeled and dated.
≈ “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.
Files
Data Room Builder
The data room is where momentum goes to die or to accelerate. A messy, slow-to-assemble room signals an undisciplined company and gives a wavering investor a reason to drift. A clean, staged room signals "this founder runs a tight ship" and shortens the path to wired funds.
When to use this skill
Build it during [[fundraise-readiness-audit]] (you should be able to produce it in days - 3 to 5 working days is the standard for a seed-stage company with clean books), and stage it for sharing once a term sheet is near. Confirmatory diligence runs against it; see [[fundraise-closing-mechanics]].
Structure the room in tiers
Share progressively - not everything goes out on the first call.
Tier 1 - shared early (builds confidence)
- Pitch deck and the one-page narrative memo.
- Key metrics dashboard with definitions (so numbers are not disputed later).
- Market sizing with assumptions ([[market-sizing]]).
Tier 2 - shared at serious interest / pre-term-sheet
- Financials: historical P&L covering at least the trailing 24 months (monthly granularity), the model/projections ([[financial-planner]]), monthly burn and runway.
- Metrics detail: cohort/retention curves, CAC by channel, pipeline.
- Cap table: fully-diluted, plus prior SAFEs/notes ([[cap-table-manager]]).
- Product: roadmap, architecture overview, security posture.
Tier 3 - confirmatory diligence (post-term-sheet)
- Corporate: incorporation docs, board consents, prior financing docs.
- IP: assignment agreements for every founder and contractor.
- Customers: top contracts (any customer over ~10% of revenue gets extra scrutiny - have those contracts and their renewal terms ready), churn detail, references.
- People: org chart, key employee agreements, option grants.
- Legal: any litigation, regulatory exposure, material contracts.
Operating rules
- One source of truth per number. The metric in the deck, the data room, and your mouth must match to the decimal.
- Label and date every file. A folder named "Final_v3_real" loses you trust.
- Track who has access and what tier they are in; close access within a week of a deal dying - a stale open room is a leak waiting to happen.
- Keep an index document at the root so a partner can navigate without asking.
- Respond to any diligence document request within 24-48 hours. Slower than that reads as "they don't have it" and stalls the deal clock; confirmatory diligence should run 2-4 weeks, and slow responses are the usual reason it doesn't.
Anti-patterns
- Dumping everything on day one - it overwhelms and surfaces issues out of context.
- A number in diligence that contradicts the deck. This is the single fastest way to lose a deal; reconcile before you share.
- A room you cannot assemble until week three of diligence. Build it before you raise, not during.
Quality bar
- Every metric in the room reconciles to the deck and the model to the decimal, with one named source of truth per number.
- The full Tier 1-3 structure exists before outreach starts, with a have / need / drafting status on every item.
- Every file is labeled and dated; the root index lets a partner find any document without asking.
- Access is logged per person per tier, and there is a plan to revoke it when a deal dies.
Deliverable
A tiered, indexed data room (folder structure plus a contents checklist marking have / need / drafting), with every metric reconciled to a single source and an access-tracking plan for the raise.
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
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.

