Skip to content

deanpeters/Product-Manager-Skills / plugins/pm-define/skills/battle-card-builder

battle-card-builder

Verified

Research and draft a competitive battle card from public evidence — every claim labeled and sourced. Use when a rep needs a field-action card, not a research report.

FileKindSize
SKILL.mdskill md10.6 KB
examples/sample-industrial.mdmarkdown6.5 KB
examples/sample.mdmarkdown5.9 KB
template.mdmarkdown2.2 KB

template.md

View on GitHub
# Battle Card Template

Copy this to draft a field-action battle card. A battle card is the artifact a rep opens
**mid-deal** — it must fit thirty seconds, and every claim must survive being said out loud to a
hostile audience. Every claim therefore carries a source URL, a date, and a
**Fact/Inference/Assumption** label. Depth goes in the appendix, never on the card.

Section order is stable: `competitive-intel-watch` update flags name these sections when they go
stale.

## Template

```markdown
# Battle Card: [Your Product] vs [Competitor]
**As-of date:** [YYYY-MM-DD — a card without one is a liability wearing a logo]
**Deal context:** [segment, buyer]

## 1. Thirty-Second Read
- **They win when:** [1-2 bullets, labeled]
- **We win when:** [1-2 bullets, labeled]
- **The one thing to say:** [a single defensible sentence]

## 2. Say This
- [Talking point] — [evidence: URL, date, label]
- [Max 4; every one sourced — an unsourced talking point is folklore with formatting]

## 3. Ask This (trap questions)
- "[Question whose documented answer favors us]" — [the documented answer: URL, label]
- [Max 3. Never ask what you cannot evidence — if the answer isn't in the appendix table,
  the question doesn't ship]

## 4. Watch Out For
- [Their strength a rep should not walk into] — [URL, label]
- [Their likely counter to our pitch] — [Inference, basis]

## 5. Pricing & Packaging Snapshot
- [Their tiers/pricing as published] — [URL, as-of date]
- [Where "contact sales" hides the number] — [labeled]

## 6. Do Not Say
- [Claims we cannot evidence, or that invite a counter — this section protects the rep
  from the team's own folklore; write down which beloved claims are dead]

## Appendix: Evidence Table
| Claim | Label | Source | Date |
|---|---|---|---|
| | | | |

### Assumptions to Validate
- [Assumption 1]
- [Assumption 2]
- [Assumption 3]
```

## Quality checks before you call it done

- Sections 1-6 fit one screen; anything longer belongs in the appendix
- Every trap question's documented answer appears in the evidence table
- "Do Not Say" is populated — an empty one usually means nobody audited the team's folklore
- The as-of date is set and a watch cadence exists to feed this card update flags — cards rot at
  the speed pricing pages change
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall