Skip to main content
skill CX Codex

battle-card-builder · deanpeters — Claude Code skill for evidence-backed competitive battle cards

battle-card-builder builds a sales battle card from public evidence: pricing pages, reviews, release notes. Every claim gets a source URL, date, and a Fact/Inference/Assumption label.

CC-BY-SA-4.0 1,300 installs ★ 8,115 updated 2026-10-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add deanpeters/Product-Manager-Skills --skill battle-card-builder -a claude-code
Open on GitHub

What battle-card-builder does

This skill assembles a field-action card for deals where one competitor keeps showing up. The agent digs through pricing pages, reviews, release notes and customer stories, then drafts a card a rep can open mid-conversation. The card is sized for a thirty-second read; depth lands in the appendix.

Every claim carries a source URL, a date, and a Fact, Inference or Assumption label. That is the point: most battle cards are unlabeled inference, and a rep pays for that when a claim collapses in front of a hostile audience. The skill forbids inventing features, pricing, market share, customer wins, roadmap items and quotes.

The card schema is fixed: a thirty-second summary, a "Say This" section capped at four sourced talking points, trap questions with documented answers, "Watch Out For", a pricing snapshot, a "Do Not Say" list, and an evidence table in the appendix. After the draft the agent offers exactly four next steps: pressure-test the card, build one for a second competitor, set up a watch skill to keep it current, or compress it for mobile.

If a competitive snapshot or watch report already sits in the session, the skill uses it as the evidence base and searches only for gaps and material older than one quarter. Starting empty, it asks at most three questions: product and competitor, segment and buyer, triggering objection. Unanswered questions become labeled assumptions.

A run takes 20–35 minutes, so budget for that before you kick it off mid-deal.

What it helps with

  • assemble a competitor card from public sources
  • label every claim with a URL, date and evidence type
  • separate facts from inferences and assumptions
  • write trap questions with documented answers
  • refresh a stale card in 20–35 minutes

Example prompts for the agent

  • Use the competitive-research-snapshot in this session and draft a battle card for an enterprise deal
  • Rebuild the card for Competitor B: re-check anything older than one quarter, reuse the rest from the report

How to install battle-card-builder

1Skills CLI (Vercel)

npx skills add deanpeters/Product-Manager-Skills --skill battle-card-builder -a claude-code

2Manually: put the files in place

~/.claude/skills/battle-card-builder/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/battle-card-builder/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about battle-card-builder

How do I install battle-card-builder in Claude Code?

Run npx skills add deanpeters/Product-Manager-Skills --skill battle-card-builder -a claude-code. The skill file lands at ~/.claude/skills/battle-card-builder/SKILL.md.

What does battle-card-builder do?

It researches a competitor from public sources and drafts a sales battle card: talking points, trap questions, pricing, risks. Every claim gets a source URL, date, and a Fact/Inference/Assumption label.

How is this different from a normal battle card?

Typical cards are full of unlabeled inference. This skill requires a source and a label on every claim, and it explicitly bans inventing features, prices and quotes. A rep can defend every line before saying it out loud.

Similar skills

All skills for Agent setup: memory, context, orchestration →

battle-card-builder by other authors comes first.

battle-card-builder travisjneuman battle-card-builder builds sales battle cards, competitive comparisons, and structured objection scripts using an 8-part framework. CX Codex +1 137installs pp-youtube Justin pp-youtube — a skill for Claude Code, Cursor, Codex and other agents that keeps a local SQLite databank of tracked YouTube channels, fed through the YouTube Data API v3. CX Codex +1 423installs competitor-profiling coreyhaines31 The competitor-profiling skill for Claude Code, Codex, and Cursor builds dated competitor profiles. Use it to examine rivals’ pricing, positioning, features, reviews, and SEO. CX Codex +1 107,300installs battle Manavarya Singh battle puts two sites head to head and produces one shareable HTML card with scores across eight dimensions, bar-by-bar, plus a verdict line. CX Codex +1 ★ 5,183repo stars onboarding-user SupercmoHQ The onboarding-user skill builds a company profile from its website and identifies competitors. Use it when setting up a brand for future sessions. CX Codex +1 ★ 331repo stars outliers Melvynx The outliers Claude Code skill finds Instagram Reels and TikTok videos that outperform an account’s usual view count. A request for competitor research or remake ideas triggers a ranking and script drafts. CX Codex +1 1,600installs brand-mention-monitoring arcmira The brand-mention-monitoring Claude Code skill tracks brand mentions across YouTube shows and podcasts. Ask it to compare competitors, find quotes, or set up alerts. CX Codex +1 1,300installs

From the same set76

The whole set →
incoming-request-advisor incoming-request-advisor is a Claude Code skill that breaks down incoming messages to find the underlying job-to-be-done. Runs when handling executive escalations, Slack pings, or vague mandates. CX Codex +1 1,400installs agent-orchestration-advisor agent-orchestration-advisor is a Claude Code skill for designing multi-agent workflows, splitting complex tasks across parallel specialized agents with defined boundaries and handoff points. CX Codex +1 1,400installs competitive-intel-watch competitive-intel-watch diffs competitor activity against a prior research snapshot and logs only actionable shifts. Flags outdated battle cards and pricing notes without regenerating full reports. CX Codex +1 1,300installs ansoff-matrix This skill maps growth options to the Ansoff Matrix, weighs their risk, and proposes a sequence. Use it to assess where a company or product could grow next. CX Codex +1 1,300installs autonomous-investigation autonomous-investigation sets the rules for research skills that run while you are away: question budget, a search plan, and Fact/Inference/Assumption labels on every claim. CX Codex +1 1,300installs competitive-analysis-process competitive-analysis-process orchestrates competitor research through a structured six-stage workflow tied to strategic choices. It produces battle cards, matrices, and threat assessments. CX Codex +1 1,300installs competitive-research-snapshot competitive-research-snapshot builds a cited competitive snapshot with a comparison matrix and decision implications. Use it when positioning, roadmap, or deal work needs evidence. CX Codex +1 1,300installs market-landscape-scan market-landscape-scan — a skill for Claude Code, Codex, Cursor, GitHub Copilot and Gemini CLI that maps market segments, players, substitutes and whitespace with labeled evidence. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open