# Battlecards

> Battlecards

- Skill: `matteotitta/battlecards` (Agent Skill)
- Install (CLI): `npx skillmds@latest add matteotitta/battlecards`
- Raw SKILL.md: https://api.skillmd.com/api/skills/matteotitta/battlecards/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: matteotitta (https://skillmd.com/u/matteotitta)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/matteotitta/battlecards

---


# 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.

---

## Doctrine inherited (Step 7 — 0626 rollout)

Output complies with:

- [`output-tenets.md`](../../../../rules/output-tenets.md) — the seven tenets
- [`output-simplicity.md`](../../../../rules/output-simplicity.md) — length caps, three-layer source placement, robot-tells ban
- [`doc-output-structure.md`](../../../../rules/doc-output-structure.md) — GDoc/Notion structural defaults
- Step 6 calibration: see [[feedback_execution_doctrine_refinements_step6]]

**Refinements applied to this skill:**

| Code | Refinement | How it lands in battlecards |
|---|---|---|
| **R1** | Source placement (three layers) | Battlecards are **internal-reference** (rep-facing). Inline `[VERIFIED:...]` tags stay — auditability matters more than polish for sales QA. Working markdown keeps citations inline. Published Notion playbook can move them to a per-card toggle if reps prefer the cleaner read. |
| **R2** | Single-doc-with-toggles | Multi-competitor battlecard packs ship as **one doc with one toggle per competitor** — not 8 separate files. Reps scan the index, expand the competitor that came up on the call. |
| **R3** | Product-update tone | Capability framing in win themes — "we ship X" not "we are thrilled to announce." Reps repeat what they see. |
| **R9** | Action-oriented section names | "Win themes / Landmines to plant / Objection handlers / Counter-positioning" — already verb-led. Preserve. |

---

## 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:**
- User wants deep competitor research → Use `/competitor-research` skill
- User wants sales deck → Use `/sales-deck` skill
- User wants demo script → Use `/demo-script` skill
- User wants competitive feature comparison only → Use `/competitor-research` skill

---

## Input requirements

### Required inputs

| Input | Description | Source |
|-------|-------------|--------|
| **Competitor name(s)** | Which competitor(s) to create battlecards for | User specifies |
| **Your product context** | What you sell, key capabilities | User, product-messaging, or URL |

### Optional inputs (improve quality)

| Input | How it helps |
|-------|--------------|
| competitor-research output | Pre-researched intel (funding, features, positioning) |
| win-loss-analysis output | When we win/lose patterns with evidence |
| Product messaging | Counter-positioning based on your value props |
| Positioning context | Strategic anchors for competitive framing |
| Competitor URLs | For live research if no prior research exists |
| Sales call transcripts | Real 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). Offer to run competitor-research first if no intel available.

---

## Process at a glance

| Phase | Purpose | Output |
|-------|---------|--------|
| 1. Competitor selection | Confirm scope (single vs batch) | Confirmed competitor list |
| 2. Intel gathering | Pull from research + win-loss + web research | Intel dossier per competitor |
| 3. Battlecard generation | Fill template, add confidence levels, write talk tracks + landmines | Draft battlecard(s) |
| 4. Validation & delivery | Verify sources, format for delivery | Final 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.

---

## Integration with other skills

### Upstream skills (provide inputs)

| Skill | What it provides | Required? |
|-------|------------------|-----------|
| **competitor-research** | Company facts, positioning, features, pricing | Recommended |
| **win-loss-analysis** | Win/loss patterns, objections, proof points | Recommended |
| **product-messaging** | Your value props for counter-positioning | Recommended |
| **positioning** | Strategic competitive anchors | Optional |

### Downstream skills (consume outputs)

| Skill | How it uses battlecards |
|-------|-------------------------|
| **sales-deck** | Differentiation slide content |
| **demo-script** | Objection handling during demos |
| **outreach-emails** | Competitive displacement email content |

---

## MCP data integration

**Level:** 2 — PM Execution (inherits upstream, no unique pulls)

**Inherits from:** competitor-research, win-loss-analysis, product-messaging

**Pulls fresh:** NONE — all data comes from upstream. Battlecards synthesize existing competitor research and win-loss patterns.

**Fallback (no MCP):** Use competitor-research and win-loss-analysis outputs directly. If upstream skills haven't run, trigger them first before running battlecards.

---

## Final ship gate

Run `/premortem --output` before ship. See [`/premortem` skill](../../../meta/orchestration/premortem/SKILL.md) for the 5 execution domains (will-it-resonate / will-it-convert / will-it-stay-on-brand / will-stakeholder-push-back / will-it-degrade-over-time) and output template.

Then run `/scope-guardian-reviewer` — the client-deliverable ship gate: scope-creep check on proposals/SOWs (pm-loop.md).

Trivial-case escape: `## Premortem\nNo failure modes — trivial change` satisfies the contract for genuinely trivial outputs.

---