agentleFS
agentdynarqagentdynarq/founder-skills/skills/investor-update/SKILL.md

investor-update

Skill0 starsChanged 4 months agoMITView on GitHub

Draft concise, honest investor updates from raw notes and metrics. Use when the user wants to write a monthly or quarterly investor update, report progress to investors or advisors, or asks how to communicate with their cap table.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    Distinctive

    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. Distinctive:

    Write investor updates that busy investors actually read: short, numbers-first, honest about problems, and ending with specific asks.

    line 8
  2. Very specific:

    If the user cannot supply a number, write [TODO: figure] in its place.

    line 19
  3. Distinctive:

    Keep the full update under 600 words.

    line 23
  4. Distinctive:

    No adjectives doing the work of numbers ("massive growth" is banned.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Investor Update

Write investor updates that busy investors actually read: short, numbers-first, honest about problems, and ending with specific asks.

Before writing

Collect from the user (ask if missing, never invent):

  1. Period covered and the previous period's numbers for comparison
  2. Core metrics: revenue or usage, growth rate, burn, runway in months
  3. One to three highlights and at least one lowlight
  4. Specific asks (intros, hiring, feedback)

If the user cannot supply a number, write [TODO: figure] in its place. Never estimate or fabricate a metric.

Structure

Keep the full update under 600 words.

Subject: [Company] Update: [Month Year]

TL;DR: One sentence on the state of the business.

METRICS
- MRR: $X (+Y% vs last month)
- Active users: X (+Y%)
- Burn: $X/mo, Runway: X months
Show the same metrics every update so trends are visible.

HIGHLIGHTS
2-3 bullets. Concrete outcomes, not activity. "Closed 3 pilots"
beats "had many promising conversations."

LOWLIGHTS
1-2 bullets. What went wrong or slower than planned, and what
you are doing about it. Updates without lowlights read as spin.

ASKS
Specific and answerable in one reply. "Intro to a payments PM
at Stripe" beats "any advice welcome."

Thanks for the support.
[Name]

Rules

  • Numbers before narrative. Investors scan metrics first.
  • Same metric set every period. Changing definitions between updates destroys trust.
  • Lowlights are mandatory. A founder who reports only wins gets less help.
  • One ask per line, each one forwardable as-is.
  • No adjectives doing the work of numbers ("massive growth" is banned; "+41% MoM" is not).
  • Consistent cadence matters more than polish. Monthly is the default.

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.