agentleFS
holaroluwaholaroluwa/outbound-skills/skills/deep-company-analyser/SKILL.md

deep-company-analyser

Skill0 starsChanged 48 days agoMITView on GitHub

Analyse a company from its website and any provided info to capture real positioning, value props, and competitive reality into outreach-brief.md. Use this FIRST when starting outbound for a new company or product, or whenever the user says "analyse this company", "research our positioning", "what do we actually sell", or pastes a website or company info and wants the foundation for outreach. The output feeds every other outbound skill, so reach for it even if the user doesn't name it.

2 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. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you only have a URL, fetch the homepage plus the product, pricing, and about pages before writing anything.

    line 14
  2. Distinctive:

    Read the source like a skeptical buyer, not a fan.

    line 17
  3. Very specific:

    Write into section 1 (Company & positioning) of outreach-brief.md:

    line 27
  4. Distinctive:

    Keep it tight and concrete.

    line 33

≈ “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

Deep Company Analyser

Turn a company's website and notes into the foundational truth the rest of your outbound is built on. Most outreach fails because it's built on how a company describes itself, not what it actually does or who it actually beats. This skill digs for the real thing.

Input needed

  • The company website URL (fetch it if you can).
  • Anything the user has: a deck, notes, an "about us", or a sentence describing the business.

If you only have a URL, fetch the homepage plus the product, pricing, and about pages before writing anything.

Method

  1. Read the source like a skeptical buyer, not a fan. Strip the marketing gloss.
  2. Answer, in plain language:
    • What does this company actually do, in one sentence a 12-year-old would get?
    • Who is it for, specifically? Who is it clearly not for?
    • What is the real, differentiated thing it does better than the obvious alternative?
    • What does it charge, or how does it make money?
    • What do buyers use today instead (the competitive reality, including "nothing")?
  3. Flag any claim that has no proof behind it, and note where a real customer quote is needed.

Output

Write into section 1 (Company & positioning) of outreach-brief.md:

  • A one-sentence positioning line, plain and specific, no buzzwords.
  • Who it's for and who it's not for.
  • The differentiated edge and the honest competitive reality.
  • A short "evidence gaps" list: where you need deal notes or quotes to make the later skills sharp.

Keep it tight and concrete. If a line could sit on any competitor's website, rewrite it until it could only be about this company.

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.