agentleFS
styfinitystyfinity/claude-marketing-department/skills/battlecard/SKILL.md

battlecard

Skill6 starsChanged 4 months agoMITView on GitHub

Builds a one-page sales battlecard for a single competitor — when you win, when you lose, landmine questions to plant early, and objection-by-objection handling with evidence grades. Use before deals where this competitor keeps showing up.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Battlecard — win the deals they show up in

Deals against a competitor are lost on framing, not features. The prospect hears a story that makes you the risky choice, and your side improvises a rebuttal. A battlecard hands your side the framing first: where you genuinely win, where you honestly lose, and the questions that expose the gap — every claim graded by how well you actually know it.

Inputs

  • The competitor, and everything known about head-to-head deals: $ARGUMENTS
  • From marketing-brief.md if present: this competitor's entry under The competitors (offer, claimed position, weaknesses), positioning & message, the offer, and objections & beliefs. If the competitor entry is thin, run /marketing:competitor-teardown first — a battlecard built on guesswork loses politely.

Do this

  1. Assemble the intelligence from the brief and $ARGUMENTS: their offer, pricing, positioning claims, typical buyer, and how past deals against them actually went. Grade every item — verified, reported, or assumed — and carry the grades onto the card.
  2. Write "when we win": the 3–5 deal conditions where you are genuinely the better choice, each tied to a concrete capability or model difference, not an adjective.
  3. Write "when we lose": the honest conditions where they win. This section is what makes sellers trust the rest of the card — and it stops them chasing bad-fit deals with overpromises.
  4. Plant the landmines: 3–5 questions the seller seeds early that this competitor answers badly. Each rests on a verified weakness — a landmine built on a false premise detonates on your own seller mid-demo.
  5. Write the objection handling for what this competitor's presence puts in the room ("they're cheaper", "they already do X"):
    • The direct answer, one sentence, no wind-up.
    • The reframe to the criterion that actually decides the deal.
    • The proof point from the brief that makes the reframe stick.
  6. Set the talk track rule: two lines on how to speak about them — specific, respectful, never trash-talk. Trash-talk reads as fear.
  7. Update the brief. Fold any new intelligence into this competitor's entry under The competitors, dated, so the next deal starts from the current picture.

Output

A one-page battlecard: their pitch in one line, our counter in one line, when we win, when we lose, landmines, objection handling, and the talk track rule — every claim carrying its evidence grade.

Rules

  • Evidence over invention: never fabricate a competitor weakness. One false landmine costs the seller's trust in the whole card.
  • "When we lose" is mandatory. A card that says you always win is a card sellers ignore.
  • Grades travel with claims. A seller must know verified from assumed before repeating anything to a prospect.
  • Refresh the card when reality changes — a pricing move, a launch, a new tier — not on a schedule.
  • One page, always. A battlecard that cannot be scanned mid-call is a research document.

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.