agentleFS
cwhited26cwhited26/pocket-agent-starter-skills/skills/research/vertical-landscape-scan/SKILL.md

vertical-landscape-scan

Skill0 starsChanged 4 months agoMITView on GitHub

Turn a handful of sources into a one-page read on a market or vertical — players, pricing, gaps, and where the opening is. Entering a new vertical, sizing an opportunity, or briefing the owner before a decision about a market they don't know yet.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  1. Distinctive:

    Read several sources, not one — a single page gives you one company's spin, not the market.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

One-Page Market Scan

A market scan is a one-page answer to "what's the lay of the land and where's the opening?" Pull from several sources, then compress to the players, the pricing reality, the gap, and the move.

The technique

  • Read several sources, not one — a single page gives you one company's spin, not the market.
  • Map the players in a line each: who they are, who they serve, what they charge. No essays.
  • Find the pricing reality across them — the real range, not any one headline number.
  • Name the gap: who's underserved, what nobody's doing well, where the complaints cluster.
  • End with the opening — the one move the gap suggests — and keep the whole thing to a page someone reads standing up.

Do this, not that

Do: "Roofing-measurement SaaS: three real players, $79–$299/mo, all aimed at big firms. Gap: nothing priced or simple enough for a 2–3 truck shop, and they all hide the supplement language solo operators actually need. Opening: a stripped, cheap tier for small contractors. Sources: 4 pricing pages + 2 forum threads, pulled today."

Don't: Hand over ten pages of raw notes per competitor with no synthesis, no pricing comparison, and no answer to the only question that matters — where's the opening.

Why this works

The owner is making a decision, not writing a thesis. Ten pages of raw research pushes the synthesis work back onto them, which is the part they wanted done. A one-page scan that names the players, the pricing, the gap, and the move is something they can act on in a meeting — and pulling from several sources is what keeps it from being one competitor's marketing repeated back as fact.

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.