agentleFS
styfinitystyfinity/claude-marketing-department/skills/positioning-workshop/SKILL.md

positioning-workshop

Skill6 starsChanged 4 months agoMITView on GitHub

Runs a guided positioning pass — real alternatives, true differences, the value each difference creates and who cares most, then the position sentence — and stress-tests the result against the competitors in your brief before saving it. Use when nobody can say who it is for and why it wins in one breath, or when every deal turns into a price comparison.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use company-intel.

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.
  • varunk130Skill

    company-intel

    Deep research on any company by scanning their public website to extract customers, partners, case studies, testimonials, key metrics, and competitive positioning. Produces a polished 1-slide PowerPoint summary. Use when: research a company, find customers, who are their customers, company research, company overview, customer list, company intel, customer logos, competitive research on company, scan website for customers.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Update Positioning & message in marketing-brief.md with the position line and its argument, and flag the downstream sections (offer, …

    line 25
  2. Very specific:

    If no true difference survives step 2, say so plainly and route to /marketing:offer-builder — the fix is the offer, not braver wordsmithing.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 8 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

Positioning Workshop — the sentence everything else hangs on

Positioning is the decision the rest of marketing inherits. Get it wrong and the ads, the funnel, and the sales calls all fight uphill carrying a claim buyers cannot place. This workshop builds the position from what is verifiably true — starting from what buyers would do instead of you, not from what the company wishes were special — and refuses to output a sentence a competitor could claim tomorrow.

Inputs

  • The product and who buys it today, plus any positioning attempts already made: $ARGUMENTS
  • From marketing-brief.md if present: the customer section (pains, desired outcomes, language bank), The competitors with their claimed positions, and any existing position line to pressure-test rather than replace blind.

Do this

  1. List the real alternatives — what buyers actually do instead of buying you. Include "do nothing", "spreadsheet and gritted teeth", and "hire someone", not just named competitors. The alternative frames the whole argument.
  2. List the differences that are true: capabilities, attributes, or a way of working that you have and the alternatives lack. Kill every difference the customer does not care about, however proud the team is of it.
  3. For each surviving difference, connect difference → value → who cares most. A difference only matters through the value it creates, and every value has a segment that feels it hardest.
  4. Draft three candidate position sentences in the brief's format:
    • For {WHO}, against {ALTERNATIVE}, we are the one that {DIFFERENCE}, proven by {PROOF}.
  5. Stress-test each candidate against the competitor claims in the brief (inside Claude Code, positioning-decoder can map those claims and positioning-strategist can run the challenge):
    • Could any competitor say this sentence tomorrow without lying? Then it is a slogan, not a position.
    • Could a sceptical buyer check the proof in ten minutes? If not, it is decoration.
  6. Pick the winner and write the argument behind it — why this WHO, why this alternative frame, why this difference beats the others considered. Keep the two rejected candidates with one line each on why they lost.
  7. Update Positioning & message in marketing-brief.md with the position line and its argument, and flag the downstream sections (offer, message map, channels) that now need re-checking against it.

Output

The position sentence, the argument behind it, and the two rejected candidates with reasons — written into the Positioning & message section of marketing-brief.md, plus the list of brief sections to re-check against the new position.

Rules

  • Build from what is verifiably true. A difference without existing proof goes on the product roadmap, not into the sentence.
  • A position a competitor can honestly claim is not a position. Re-test until the sentence excludes them.
  • Proof must be checkable — a number, a named mechanism, a demonstrable result. Adjectives are not proof.
  • Narrower wins. A sentence that makes a tenth of the market say "this is exactly for me" beats one that makes all of it nod politely.
  • If no true difference survives step 2, say so plainly and route to /marketing:offer-builder — the fix is the offer, not braver wordsmithing.

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.