agentleFS
matteotittamatteotitta/genesys-skills/skills/battlecards/SKILL.md

battlecards

Skill53 starsChanged 5 days agoMITView on GitHub

Builds a sales battlecard against one competitor: when you win and lose, how to position, objection handling, landmines and proof points, kept to what a rep can use on a call. Use when asked for a battlecard, competitive sales sheet or how to sell against X.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. growthack88/growth-marketing-os★ 11751% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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 inputs are missing: Ask which competitor(s). If no intel is available, research the competitor's website, pricing page and reviews first.

    line 57
  2. Distinctive:

    Every battlecard contains these sections — in this order, no exceptions:

    line 76
  3. Distinctive:

    Never invent competitor claims: Only use verified data with sources.

    line 97
  4. Distinctive:

    Never guess competitor pricing: Use verified data or mark "[CONFIRM: pricing]".

    line 99
  5. Distinctive:

    Missing landmines: Only covers strengths, forgets to include questions that expose competitor weaknesses → Landmines are the most valuable …

    line 111
  6. Very specific:

    Fallback (no live research): use whatever competitor and win/loss notes the user provides, and mark gaps as [UNAVAILABLE].

    line 120

≈ “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

Battlecards

Quick-reference competitive intelligence battlecards for live sales conversations. Designed to be scanned in 30 seconds during a call. Supports batch generation for multiple competitors with confidence-level sourcing on every claim.

The body of this file holds decision-grade context (when to invoke, inputs, structure, anti-hallucination guardrails, gotchas). Step-by-step process, output template, quality gates, and feedback loops live in the premium reference.


Claude Code triggers

Invoke this skill when user says:

  • "Create battlecard for [competitor]"
  • "Competitive battlecard"
  • "How to win against [competitor]"
  • "Competitive intel for sales"
  • "Battlecards for [product]"
  • "Sales battlecard"
  • "Counter-positioning against [competitor]"
  • "Competitive one-pager" (if focus is on win/lose scenarios)

Do NOT invoke when the user wants deep competitor research, a sales deck, a demo script, or a feature comparison only.


Input requirements

Required inputs

InputDescriptionSource
Competitor name(s)Which competitor(s) to create battlecards forUser specifies
Your product contextWhat you sell, key capabilitiesUser, product-messaging, or URL

Optional inputs (improve quality)

InputHow it helps
Competitor notes or a prior dossierPre-researched intel (funding, features, positioning)
Win/loss notesWhen we win/lose patterns with evidence
Product messagingCounter-positioning based on your value props
Positioning contextStrategic anchors for competitive framing
Competitor URLsFor live research if no prior research exists
Sales call transcriptsReal objections and competitive mentions

Input validation checklist

Before proceeding, verify:

  • Competitor(s) confirmed
  • Your product's key differentiators known
  • At least one intel source available (research, URL, or docs)

If inputs are missing: Ask which competitor(s). If no intel is available, research the competitor's website, pricing page and reviews first.


Process at a glance

PhasePurposeOutput
1. Competitor selectionConfirm scope (single vs batch)Confirmed competitor list
2. Intel gatheringPull from your notes + call transcripts + web researchIntel dossier per competitor
3. Battlecard generationFill template, add confidence levels, write talk tracks + landminesDraft battlecard(s)
4. Validation & deliveryVerify sources, format for deliveryFinal battlecard(s)

Full step-by-step (with checkpoints, confidence framework, workflow sequences, GDrive export commands) in the premium reference.


Battlecard structure (decision-grade)

Every battlecard contains these sections — in this order, no exceptions:

  1. Quick facts — Founded, funding, employees, target market, pricing model, starting price (side-by-side table)
  2. When we win — 3 specific scenarios + verbatim customer proof point
  3. When we lose — 2+ honest losing scenarios + mitigation actions
  4. Their pitch — Verbatim competitor language + key claims
  5. Counter-positioning — Scripted "when they say X, we say Y" responses
  6. Feature comparison — Honest table with winner-per-row
  7. Landmines to plant — 3+ discovery questions that expose competitor weaknesses
  8. Objection handling — Common objections with proof-pointed responses
  9. Red flags — When to walk away (qualification-out criteria)
  10. Sources — Every claim with URL + access date + confidence

Full template with field-level guidance in the premium reference. Output wrapper format and iteration prompts in the premium reference.


Anti-hallucination guardrails

Critical for sales credibility:

  1. Never invent competitor claims. Only use verified data with sources.
  2. Never fabricate customer quotes. Verbatim only or mark "[PLACEHOLDER: need customer quote]".
  3. Never guess competitor pricing. Use verified data or mark "[CONFIRM: pricing]".
  4. Mark confidence levels on all competitive intel (High/Medium/Low/UNVERIFIED).
  5. Cite sources for all factual claims with access dates.
  6. Acknowledge gaps rather than fill with plausible content.
  7. Be honest about weaknesses. "When we lose" builds credibility with sales team.

Gotchas

  • Fabricated competitor pricing: Invents pricing tiers when pricing page is gated or not found → Mark pricing as [UNAVAILABLE] and note where to find it (sales call, demo request). Never guess.
  • Generic objection handlers: Produces "we're more reliable" instead of specific counter-arguments → Every objection handler must reference a concrete differentiator or proof point.
  • Missing landmines: Only covers strengths, forgets to include questions that expose competitor weaknesses → Landmines are the most valuable section for sales reps. 3-5 questions per competitor minimum.
  • Stale competitive data: Uses old competitor positioning without checking current website → Always scrape competitor website at time of battlecard creation. Note access date.

MCP data integration

Pulls fresh: the competitor's website, pricing page and review sites at the time you build the card.

Fallback (no live research): use whatever competitor and win/loss notes the user provides, and mark gaps as [UNAVAILABLE].

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.