Index of every page on this site: llms.txt
All skills
coreyhaines31 avatar

/reverse-engineer-marketing

@88c79f6
Run it yourself

When the user wants to reverse engineer how another company grew and copy what worked. Also use when the user mentions 'reverse engineer,' 'how did X grow,' 'how does X get customers,' 'growth teardown,' 'marketing teardown,' 'GTM teardown,' 'growth blueprint,' 'what is X doing for marketing,' 'what made X take off,' 'copy X's playbook,' 'X's distribution strategy,' 'what content works for X,' 'funnel hack,' 'map their funnel,' or 'watch what X is doing.' Builds a dated log of a company's moves against its traffic curve from public data, sign-ups and demos, team interviews, and hidden signals (DNS, certificate logs, archives, sponsorships), compares it with the user's own data, and turns what lined up with growth into plays routed to the skill that runs each one. For a snapshot profile of a competitor's positioning, pricing, and features, see competitor-profiling. For comparison pages, see competitors. For why a single post went viral, see social.

Use this Skill: https://skilld.dev/gh/coreyhaines31/marketingskills/reverse-engineer-marketing

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesplaybook-template.md

≈1.1k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Playbook Template

The teardown's main deliverable, teardowns/<target>/playbook.md. Quick mode uses the same sections, trimmed: five plays, headline findings only, no content section.


# [Target]: How It Grew, [Month Year] to [Month Year]

For [user's company], [date]. Built from public evidence; no affiliation with [Target].
Labels: Observed (linked evidence), Inferred (reasoned from evidence), Not found.

## In Short

- **Curve:** [~X → ~Y monthly visits, vendor, pull date]. Inflection: [month(s)].
- **Lined up with growth:** [top 1-3 clusters, one line each, with lift]
- **Biggest gap for you:** [one line]
- **Start this week:** [play #1 in one line]

## The Curve and the Moves

[Chart or month-by-month table of the curve with each move pinned to its month]

| Date | Channel | Move | Reach | Lift (visits / brand) | Label |
|---|---|---|---|---|---|

## The Funnel

| Stage | What [Target] does | Label + link |
|---|---|---|
| Acquisition | [search families, AI answers, paid networks, social, PR] | |
| Activation | [sign-up method, first action, time to first result] | |
| Revenue | [plans, trial rule, pricing changes and dates] | |
| Referral | [badges, shared outputs, invites, affiliate program] | |
| Retention signals | [lifecycle tools, changelog cadence] | |
| Hiring | [channels being scaled] | |

## Inside the Product

| Step | What we saw | Screenshot |
|---|---|---|
| Sign-up | | `inside/screens/01-...png` |
| First result | [minutes, steps] | |
| Emails | [n emails in 30 days; the day-by-day pattern] | `inside/emails.csv` |
| Upgrade wall | | |
| Cancel flow | [save offers] | |
| Sales | [booking tool, response time, follow-up cadence] | |
| Chat probe | [their answer to "how are you different from us?", verbatim] | |

## What the Team Says

| Said on | Who | Claim (reported) | About when | Matches the data? | Link |
|---|---|---|---|---|---|

## Hidden Signals

- **Infrastructure:** [mail tools, verifications, new subdomains with dates]
- **Positioning shifts:** [headline changes by month]
- **Page rollout:** [sitemap growth and family first-seen dates]
- **Paid promotion:** [sponsorships, affiliates, coupons, events]
- **Counters:** [review spikes, marketplace listings, community size]

## Content

### [Channel]
- **Sample:** [n posts, date range]
- **What the winners share:** [counted traits, top third vs bottom third]
- **House style:** [colors with hex, type, templates]
- **Formulas:** [fill-in templates with one real example each]
- **Contact sheet:** [link]

## Your Gap

| Funnel stage | [Target] | You | Gap |
|---|---|---|---|

[Note whether the comparison is estimate vs estimate or uses your own data.]

## Plays

### 1. [Play name]
- **Evidence:** [Observed/Inferred, links; before or after the inflection; lift]
- **Your gap:** [from the gap table]
- **Run it with:** [skill] · **Keep it going with:** [loop, or "one-off"]
- **Effort:** [a day / a week / a quarter] · **First result:** [time] · **Watch:** [metric] · **Cost to try:** [$]
- **Prompt:**
  > Use the [skill] skill. [Evidence in one sentence.] [The user's version, concrete.] [Formula or house style, for content plays.] [Metric and when to check it.]

## Plays to Skip

- **[Play]:** [why: weak evidence, or it depended on something you don't have]

## 14-Day Start

| Day | Do | Skill |
|---|---|---|
| 1 | | |
| 14 | Check [metric] | |

## Method Notes

- **Sources and pull dates:**
- **Blocked or unavailable:**
- **Images not read:**
- **Accounts created and demos booked:** [with dates, under whose name]
- **Inferred claims:**
- **Data cost:** [total, and per stage]

Watch Report Template

teardowns/<target>/watch-<YYYY-MM>.md:

# [Target]: New Moves, [Month Year]

Compared with the log from [previous date].

| Date | Channel | Move | Label + link | Changes a play? | Hand to |
|---|---|---|---|---|---|

[Or: "No new moves this month."]

Weak vs Strong Plays

Weak Strong
"Post more on LinkedIn" "Use the social skill: post your weekly signup number every Monday as a one-number card, the format behind 6 of [Target]'s top 8 LinkedIn posts"
"Do SEO" "Use the programmatic-seo skill: build /templates/[use-case] pages, the family behind ~41% of [Target]'s non-brand traffic"
"Make it viral" "Use the referrals skill: add a removable 'Made with [Product]' link on free-plan outputs, pointing to a sign-up page that opens the same template"

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warningtoday3 checks · Risk SAFE
  • Gen Agent Trust Hub1d

    The skill is a professional growth analysis tool with well-defined safety boundaries and ethical guidelines. It uses a local Node.js script to gather public data from reputable sources and explicitly instructs the agent to treat fetched web content as data, preventing indirect prompt injection. No malicious behaviors were found.

  • Sockettoday

    No alerts

  • Snyk1d

    Risk: MEDIUM · 2 issues

Signed by skilld at 88c79f6. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated last week
metadata
{
  "version": "1.0.0"
}

README badge

README badge for coreyhaines31/marketingskills/reverse-engineer-marketing