coreyhaines31/marketingskills / skills/reverse-engineer-marketing
reverse-engineer-marketing
VerifiedWhen the user wants to know how another company grew and what to copy, or asks what a competitor did and when: a dated log of their moves against their traffic from public data, archives, job posts, reviews, and their funnel, compared with the user's data, ending in plays routed to other skills. Also finds where competitors are weak. For a snapshot profile, see competitor-profiling. For comparison pages, see competitors.
references/landscape.md
View on GitHub# Landscape Mode
Compare three to five competitors side by side before tearing any one of them down. A single teardown shows what one company did. A landscape shows what the whole category does, which plays are table stakes, which are one company's bet, and where nobody is playing.
## Contents
- When to run it
- Run the comparison
- Read the matrix
- Add the paid and hand-read columns
- Pick who to tear down
- The landscape deliverable
---
## When to Run It
- The user names several competitors, or asks "what is everyone in my category doing?"
- Before a full teardown, to pick the company most worth studying.
- When the user has no clear lead competitor and needs to see the field first.
Use three to five competitors. Fewer than three gives no pattern; more than six becomes noise.
## Run the Comparison
```bash
node <skill-dir>/scripts/teardown.mjs compare a.com b.com c.com --you yours.com --out teardowns/landscape/matrix.csv
```
For each domain, `compare` reads, all for free:
- **Homepage scripts:** ad pixels, analytics, testing, referral, and lifecycle tools (from `stack`'s signatures, current homepage only)
- **DNS:** marketing email platforms, ad and social account verifications, and the platforms behind marketing subdomains
- **Sitemap:** page families with 10 or more pages (templates, integrations, compare, customers, a localized site)
- **Hiring:** the marketing channels on a public Greenhouse, Lever, or Ashby board (from `jobs`)
It returns:
| Field | Meaning |
|---|---|
| `everyone` | Signals every competitor shows. Table stakes in this category |
| `most` | Signals at least half of them show |
| `only_one` | Signals one company shows and the rest don't. Each is a bet, worth checking in a full teardown |
| `you_missing` | Signals at least half of them show and the user doesn't (needs `--you`) |
| `you_unchecked` | Gaps in a source that couldn't be read for the user's site (homepage, sitemap, or job board). Unknown, not missing: check by hand |
| `you_only` | Signals the user shows and no competitor does |
| `profiles` | Per company: headline, likely industry, sitemap size, top page families, open roles by function |
The CSV is the full matrix: one row per signal, one column per domain.
## Read the Matrix
- **Table stakes the user lacks** are the first gaps to close, but only when they make sense for the user's stage. Every competitor running a Meta pixel says the channel is normal here, not that the user should start tomorrow.
- **One company's bet** is the most interesting row. Check whether that company is growing faster than the rest (same-vendor traffic estimates, or `adoption` for developer tools). A bet plus faster growth is the teardown to run first.
- **Nobody does it** is an open lane or a dead end. A missing page family might be untapped search demand, or it might have been tried and dropped. Check `sitemap-growth` or Wayback for a family that once existed and was removed, and check search volume, before calling it an opportunity.
- **Hiring rows lead the rest.** A competitor hiring for SEO or partnerships today will show those page families or programs in three to six months.
- **Signals are Observed; strategy is Inferred.** "Has a Meta pixel" is Observed. "Runs Meta ads" needs the ad library. "Meta ads drive their growth" needs a full teardown.
## Add the Paid and Hand-Read Columns
`compare` covers what's free and fast. Add these columns by hand or with the user's tools, labeled with source and date:
| Column | Source |
|---|---|
| Traffic estimate and 12-month trend | One vendor for every company (DataForSEO, Semrush, Ahrefs, or Similarweb) |
| Non-brand share and top page family by traffic | The same SEO tool |
| Active ads per network | `sc-ads` or the ad library links from `ads` |
| AI answer share of voice | The prompt tracker from stage 2, same prompt set for all |
| Pricing: entry price, free plan, trial | Each pricing page, on the same date |
| Review count and rating | `reviews` for app stores; G2, Capterra, or Trustpilot by hand |
| Positioning | The `headline` from each profile, side by side |
## Pick Who to Tear Down
Rank the competitors by: growth rate (same vendor), the number of `only_one` bets they hold, and closeness to the user's buyer. Recommend one company for a full teardown and say why in one line.
## The Landscape Deliverable
`teardowns/landscape/landscape.md`:
1. **The field:** one line per company with headline, traffic trend, and open roles
2. **Table stakes:** what everyone does, and which of these the user lacks
3. **Bets:** each company's unique signals, with whether that company is growing faster
4. **Open lanes:** what nobody does, each checked against search demand and Wayback
5. **Where each one is weak:** the top complaint or gap per company (see [weak-spots.md](weak-spots.md))
6. **Recommendation:** the company to tear down first, and the one gap to close this month, with the skill that runs it
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |