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

market

Skill0 starsChanged 2 months agoMITView on GitHub

Pick one marketing channel on evidence and work it properly, instead of doing a little of everything. Use when nobody knows the business exists, when someone asks "should I be on TikTok", or when they are already posting everywhere and getting nothing.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use market-ads, market-audit and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 7

    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:

    Do not start from the list of platforms.

    line 14
  2. Distinctive:

    Before anything is posted, agree:

    line 24
  3. Distinctive:

    Do not recommend being everywhere.

    line 90
  4. Distinctive:

    Do not judge a channel before twelve weeks, and do not defend one after twenty-four if the numbers are bad.

    line 91
  5. Distinctive:

    Do not measure impressions.

    line 93
  6. Distinctive:

    Do not recommend paid ads before something converts organically.

    line 94
  7. Distinctive:

    Do not write a content calendar for six months.

    line 95

“Common” is measured: kept by at least 6 in 10 of the 12 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

Market

Your job is to get them from five channels done badly to one channel done properly. Almost every small business marketing problem is a concentration problem, not a creativity problem.

Start from where the customer already is

Do not start from the list of platforms. Start from the validation notes: where did these people say they go, what do they read, who do they already trust? A channel is only correct if the customer is on it, the format suits what is being sold, and the owner can sustain it. All three.

Score the three or four plausible channels against those and say which one wins. Give a reason, not a ranking.

Say what "properly" means, in numbers

Before anything is posted, agree:

  • how often, and for how long — twelve weeks minimum before judging it
  • what would count as working: enquiries, not impressions
  • the smallest measurement that is honest, usually "how did you hear about us", asked of every customer

Marketing without a "how did you hear about us" question is marketing that cannot be evaluated, and it is the cheapest instrument available.

Channels, and what each actually costs

Be honest about the cost in hours, because for a small business time is the binding constraint, not money:

  • Direct outreach — fastest evidence, hardest emotionally, works at small volumes. Best when the customer is identifiable and the sale is worth more than a few hundred.
  • Search — slow, compounding, real. Needs patience and a reason for the page to exist. Not a channel for a business that needs customers this month.
  • A platform audience — high effort, high variance, has to be sustained. Ask how many posts they will genuinely make in a month before recommending it.
  • Partnerships and referrals — usually the highest return for services and usually the most neglected. Who already sells to this customer without competing? That list is short and reachable.
  • Local and physical — underrated for anything with a geography. Cheap, and the competition is thin.
  • Paid ads — only after something already converts. Advertising an offer that does not convert buys the same failure faster.

Make the plan small enough to actually happen

One channel. One repeated action. A frequency they can hold on a bad week, not a good one. Write the first four weeks out concretely — the specific posts, the specific people to contact, the specific partners to approach, by name where possible.

A plan that says "post consistently on LinkedIn" produces nothing. A plan that says "Tuesday: post the pricing teardown; Thursday: message these six people" produces something.

Write the first things

Draft the actual first pieces, in their voice from brand. Not templates — finished drafts they can send or post today. The gap between a plan and a sent message is where most marketing dies.

Review honestly at twelve weeks

Then, and not before, compare against what was agreed:

  • how many enquiries, from where
  • how many became customers
  • hours spent, and what those hours would have produced elsewhere

Then either continue, adjust one thing, or stop and pick a different channel. Do not add a second channel while the first is unproven. Say that explicitly, because the instinct when something is not working is to do more things.

What to hand back

marketing.md: the chosen channel and the evidence for it, what would count as working, the four-week concrete plan, the drafted first pieces, and the review date in the calendar.

Do not

  • Do not recommend being everywhere.
  • Do not judge a channel before twelve weeks, and do not defend one after twenty-four if the numbers are bad.
  • Do not measure impressions.
  • Do not recommend paid ads before something converts organically.
  • Do not write a content calendar for six months. Four weeks, then look.

Next

sell, because traffic that does not convert is worse than no traffic — it feels like progress.

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.