gooseworks-ai/goose-skills / skills/marketing/research-competitors
research-competitors
VerifiedCompetitor research: what every main rival is running, launching, charging and saying now, what works for them, and what that means for you. Use when the marketer asks for competitor research or a teardown, "what ads are my competitors running", "how do they price", "find gaps and angles", "what changed this week" (a weekly watch), or "X just launched / shut down / cut prices" (react now). Also builds a sales battlecard, checks a competitor page's tools/pixels, or studies who engages with their LinkedIn posts. Delivers a readable report saved to the brand, so the next run reports what changed. Never copies their words or disparages them. Not for what people say about you or your market — use research-market; not for who your buyers are — use research-audience.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.7 KB |
| references/angles-and-gaps.md | markdown | 7.4 KB |
| references/battlecard.md | markdown | 3.8 KB |
| references/focused-outputs.md | markdown | 2.7 KB |
| references/linkedin-engagers.md | markdown | 6.3 KB |
| references/page-technology.md | markdown | 2.7 KB |
| references/reading-ads-honestly.md | markdown | 8.6 KB |
| references/report-format.md | markdown | 10.0 KB |
| references/research-spec.md | markdown | 34.5 KB |
| references/rival-craft.md | markdown | 16.0 KB |
| references/run-memory.md | markdown | 6.6 KB |
| references/watch-and-react.md | markdown | 12.7 KB |
| skill.meta.json | config | 5.5 KB |
| tests/examples/2026-10-22/battlecard.md | markdown | 5.5 KB |
| tests/examples/2026-10-22/engagement-report.md | markdown | 3.7 KB |
| tests/examples/2026-10-22/engagers.csv | other | 1.7 KB |
| tests/examples/2026-10-22/excluded.csv | other | 1.0 KB |
| tests/examples/2026-10-22/technology.md | markdown | 3.2 KB |
| tests/fixtures/engagers.csv | other | 1.9 KB |
| tests/fixtures/focused-evidence.md | markdown | 3.8 KB |
| tests/fixtures/page-source.html | other | 614 B |
| tests/test-by-hand.md | markdown | 7.5 KB |
references/battlecard.md
View on GitHub# Human version
A battlecard is the short sheet a salesperson can use before a competitive call. It turns the rival research into fair comparisons, useful questions and answers to real objections, with proof beside each claim.
---
# Agent version
## Build the card
1. **Frame the deal.** Use the named rival, product, buyer group and deal situation from the ask/brain. With no deal context, use the saved lead buyer, label that assumption and make confirming it a closing decision. Read the rival record, our product facts and approved claims, the audience report/objection evidence and any owner-supplied win/loss notes. Public complaints are objection hypotheses; only actual deal evidence establishes win/loss patterns.
2. **Close the comparison gaps.** Recheck the rival's current product/pricing pages for the capabilities and typical-buyer price used on the card. Use the same unit and use case on both sides; show required tiers and hidden costs. Include a strength of theirs and a situation in which they fit better. Unknown capability means unknown, not absent. Use the existing rival-pass for missing dimensions only (`../../research-competitors-rival-pass/SKILL.md`); do not run a whole category study.
3. **Write usable answers.** For each evidenced objection: buyer's words/source → acknowledge the trade-off → our supported difference → proof or a fair evaluation question. Questions ask the buyer to test a real requirement; they never presume a rival cannot meet it. Draft two short email/chat replies for common competitive moments. Reuse the brand voice and approved offers; do not invent a switch discount, customer result or migration service.
4. **Claims check.** Apply the `claims-gate` skill (`../../claims-gate/SKILL.md`) to our promises and every comparative sales line. Named comparisons also need the marketer's sign-off and dated like-for-like evidence. Show unapproved lines as clearly marked draft proposals, outside the copy-ready answers; give a safe product-fact answer where possible. Ask for the smallest needed sign-off at the end. A customer's approval is not independent proof of a rival's limitation.
## Output
Follow write-report's summary, decisions and final checks. The usable sales sheet should fit about one page (roughly 600–900 words before the evidence appendix):
- **In short / 30-second reference:** who each product fits; where we win and lose; the best opening question; how sure and the key evidence limit.
- **Decisions for you:** deal assumption and comparative lines needing approval, only when present.
- **Deal fit:** win / lose / close situations, with evidence or explicitly labelled hypothesis. No fabricated win-rate.
- **Evaluation questions:** 3–5 questions tied to the buyer's real requirements; what each answer would change.
- **Objections and responses:** at least three distinct, sourced objections, or every supported one with “evidence is thin” said plainly. Provide finished responses, not directions to write responses.
- **Feature and typical-buyer cost comparison:** our and their status, date/source, honest unknowns and trade-offs.
- **Two short replies:** “we use them already” and “why choose you?”; adapt when the evidence supports different moments.
- **What to do / What we're not doing / What we couldn't check / Sources:** keep these brief. The appendix maps each comparison to dated evidence and approval status.
## Completion check
A salesperson can use the opening question and at least one safe finished response without doing the research again. Every brand/comparative promise has a proof and approval status; current pricing has one scenario and units; where the rival wins is visible. Any unknown is honest, not a disguised weakness. Missing proof is named in Decisions, and the card is labelled draft if the copy-ready comparison still needs sign-off. Save/deliver through focused-outputs.md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |