agentleFS
jtmuller5jtmuller5/small-business-skills/skills/grow/SKILL.md

grow

Skill0 starsChanged 2 months agoMITView on GitHub

Decide honestly whether to grow, improve, or leave it alone — and if growing, what breaks first. Use when a business works but the owner is tired, when demand exceeds time, when someone is considering hiring, or when they are asking whether to expand. Also use when cash is tight and the next three months need to be laid out week by week — "I might not make payroll", "will I run out before the big invoice lands".

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. quantumaikr/quant.cpp★ 403same name
    2. jackguo709/devloop★ 2same name
    3. LazyerIJ/self-clone★ 2same name
    4. T4LEL/Claude-Arsenal★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 10

    Distinctive

    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
  1. Distinctive:

    Ask what they actually want from this business, and ask it directly: *more money, more time, or something more interesting to do?* Those …

    line 23
  2. Distinctive:

    If those answers are vague, the answer is a contractor for a defined piece of work, and say so.

    line 63
  3. Distinctive:

    If they came here because money is tight rather than because they want to expand, start here and skip everything above.

    line 68
  4. Distinctive:

    Run this before agreeing to any growth plan, and make it concrete:

    line 75
  5. Distinctive:

    If the thirteen-week view goes negative at any point, that is the plan for this quarter and growth is next quarter's conversation.

    line 82
  6. Distinctive:

    Do not assume growth is the goal.

    line 93
  7. Distinctive:

    Do not recommend hiring before the process is written down.

    line 94
  8. Distinctive:

    Do not let revenue growth stand in for profit growth.

    line 95
  9. Distinctive:

    Do not plan expansion over a thirteen-week cash view that dips below zero.

    line 96
  10. Distinctive:

    Do not talk someone out of "leave it alone" if that is what they want.

    line 97

“Common” is measured: kept by at least 6 in 10 of the 3 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

Grow

Your job is to make sure the choice is a choice. Most owners arrive here assuming bigger is the only direction, and for a lot of small businesses it is the worst of the three available.

Put all three options on the table

Say them out loud, in this order, and take each seriously:

  • Bigger. More customers, more revenue, usually more people and more overhead. More risk and, at least for a while, more hours.
  • Better. Same size, higher prices, better customers, less work per pound. Often the highest return and almost always the least discussed.
  • Leave it alone. It works, it pays, it fits their life. This is a legitimate and frequently correct answer, and an advisor who cannot say it is not an advisor.

Ask what they actually want from this business, and ask it directly: more money, more time, or something more interesting to do? Those three lead to different answers and people rarely separate them unprompted.

Before growing anything, find what breaks

Walk the current operation and find the constraint. There is always exactly one:

  • Their own hours. Then growth means delegation or price, and nothing else.
  • Demand. Then growth is a marketing question, and market is the skill.
  • Cash. Then growth is dangerous — a growing business consumes cash before it produces it, and profitable businesses fail this way routinely.
  • Delivery capacity. Then growth means process or people.
  • One customer being most of the revenue. Then growth means diversifying before anything else, because that is not a growth problem, it is an exposure.

Say which one it is and say the number that shows it. Do not attempt to fix more than one at a time.

If the constraint is their hours

In order, cheapest first:

  1. Raise the price. Fewer customers, same money, less work. Almost always available and almost always resisted.
  2. Stop serving the worst customers. Identify them by profit per hour, not by revenue. The list usually surprises the owner.
  3. Write down the process for the thing done most often. This has to exist before anyone can be hired anyway, and it frequently removes a third of the work by itself.
  4. Then hire or subcontract — starting with the work they are worst at or like least, not the work that looks most junior.

If hiring

Be blunt about what it costs: the salary is roughly half of it once tax, tools, management time and the productivity dip are counted. Ask what specific work is handed over on day one, and whether there is three months of it. Ask what the cash position looks like if the person does not pay for themselves for two quarters.

If those answers are vague, the answer is a contractor for a defined piece of work, and say so.

Cash before ambition

If they came here because money is tight rather than because they want to expand, start here and skip everything above. Do not ask what they want from the business while they are counting weeks. Build the thirteen-week view first, find the week it goes negative, and work backwards from that week: what can be invoiced sooner, what can be delayed, what can be cut without ending the business. Then come back to the rest of this skill once there is a number of weeks on the table.

Run this before agreeing to any growth plan, and make it concrete:

  • money in and money out, week by week, thirteen weeks ahead
  • what happens if the largest customer pays thirty days late
  • what happens if the busiest month arrives with the same overheads and no invoices paid yet

If the thirteen-week view goes negative at any point, that is the plan for this quarter and growth is next quarter's conversation.

What to hand back

growth.md: what they want from the business in their own words, the constraint with the number that proves it, the three options assessed honestly, the recommendation, and the thirteen-week cash view.

Do not

  • Do not assume growth is the goal.
  • Do not recommend hiring before the process is written down.
  • Do not let revenue growth stand in for profit growth. Ask for profit per hour.
  • Do not plan expansion over a thirteen-week cash view that dips below zero.
  • Do not talk someone out of "leave it alone" if that is what they want. That is someone with a working business and a life, which is the point.

Next

Back to market if the constraint is demand, sell if it is price, and offer if what they are selling has quietly stopped matching what people want.

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.