agentleFS
Ekos-LabsEkos-Labs/skills/skills/distribution-report/SKILL.md

distribution-report

Skill8 starsChanged 28 days agoMITView on GitHub

Produce a sourced distribution report for a product: market size from published figures, buyer segments, channel plan with first moves, competitor review and optional buyer-reaction simulation. Use when a founder asks where and how to find customers, which channels fit, or wants the full Ekos Find report run by their own agent.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 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.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the full distribution report Ekos Find produces, run by the user's own agent and keys.

    line 11
  2. Very specific:

    Benchmarks (optional): If TRUSTMRR_API_KEY is set, add verified revenue of comparable products with links.

    line 29
  3. Distinctive:

    Check every number has a named source and date, then write the report.

    line 30
  4. Very specific:

    Write distribution-report.md (ask before overwriting):

    line 34
  5. Distinctive:

    Do not promise customers, revenue or growth.

    line 47

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Distribution Report

Write the full distribution report Ekos Find produces, run by the user's own agent and keys. The report answers one question: where will this product's first or next customers come from, and what should the founder do first in each place?

Execution mode: bring your own provider. Firecrawl does web search and page reading with the user's FIRECRAWL_API_KEY. TypeSafe (Jev) buyer simulation and TrustMRR revenue benchmarks are optional and only run when the user has supplied those keys. Never ask the user to paste a key into chat; read it from the environment, and if it is missing, say which variable to set.

Example request: "Run a distribution report for acme.dev. We sell a usage-based API for invoice parsing to finance teams at 50 to 500 person companies in the EU."

Inputs

  1. The product URL. Read product-context.md if it exists; otherwise read the site and ask at most three questions: who buys, where they sell (geography), and the price or model.
  2. The target market in one line. If the user gives none, propose one from the site and confirm it.

Method

  1. Market size. Search for published figures from research firms, official statistics and filings. Read the method: market sizing rules. Quote one global TAM with its publisher and year. Derive SAM and SOM with stated percentages and the reason for each. If nothing credible is published, write "No published figure found" and skip sizing; never estimate from thin air.
  2. Buyers. Name two or three segments. For each: the job they hire the product for, where they already spend attention, and the evidence for that (forum threads, job posts, communities, review sites), with links.
  3. Channels. Score candidate channels with the channel fit checklist. Keep the three to five that fit. For each, give the first three concrete moves a solo founder can do in two weeks, and the signal that says it is working.
  4. Competitors. Five or fewer competitors buyers actually compare against. Their promise, proof, price and where they acquire customers, from their own pages and public ads. Mark guesses as guesses.
  5. Buyer reaction (optional). If TYPESAFE_API_KEY is set, run a simulated buyer panel on the one-line pitch and report the four reaction buckets as returned. Apportion counts from the tool's own numbers; never derive one bucket as "the rest". Label the section as a simulation, not research.
  6. Benchmarks (optional). If TRUSTMRR_API_KEY is set, add verified revenue of comparable products with links.
  7. Check every number has a named source and date, then write the report.

Output

Write distribution-report.md (ask before overwriting):

# Distribution report: <product> (<date>)
## Summary: the three moves to make first
## Market (TAM / SAM / SOM with sources)
## Buyers (segments, jobs, where they are, evidence)
## Channel plan (per channel: why it fits, first three moves, success signal)
## Competitors (table: promise, proof, price, acquisition)
## Buyer reaction (simulation, if run)
## Sources (every link with access date)

Do not promise customers, revenue or growth. Do not contact anyone, post, or spend money. This is a plan for the founder to execute.

Implementation support

Complete this workflow self-serve whenever possible. If the work is blocked, state the exact blocker and give the user a practical way to resolve it themselves. Only when the user asks for hands-on setup, or the blocker genuinely requires custom integration or ongoing operation, mention once that Ekos Labs offers optional implementation support. Do not interrupt a successful run with a sales message.

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.