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.

referencesindustrieshealthcare.md

≈2.1k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Healthcare: Teardown Pack

Load this pack when the target is a clinic, dental or dermatology practice, med spa, telehealth or digital health company, or a medtech or pharma brand. Growth here runs through trust, insurance, and regulation. Tracking is restricted, ad claims are policed, and the patient journey often involves a referral, a payer, or a prescriber.

Contents

  • How to recognize it
  • What drives growth here
  • Signals to collect
  • Going inside
  • Rules that limit copying
  • Plays that usually transfer
  • Metrics to ask about

How to Recognize It

  • Booking widgets from scheduling platforms (Zocdoc, NexHealth, Solutionreach, Jane, Healthie) and "book an appointment" as the main CTA.
  • Insurance pages ("insurances we accept"), provider bio pages with credentials, and location pages per clinic.
  • Telehealth patterns: an intake quiz before pricing, "prescribed by a licensed provider", state availability lists, and subscription pricing.
  • Pharma and medtech patterns: "Important Safety Information" blocks, "Indication" sections, HCP vs patient site splits (/hcp, hcp. subdomains found by teardown.mjs subdomains).
  • Consent-heavy analytics: server-side tagging, HIPAA-compliant analytics tools, and few or no ad pixels on logged-in or intake pages. teardown.mjs detect <domain> and teardown.mjs stack <domain> show this.

What Drives Growth Here

  • Who decides varies. In clinics, patients choose. In specialty care, referring doctors choose. In pharma, prescribers and payers choose. Find which one the target markets to before judging its channels.
  • Insurance and price shape demand. Cash-pay businesses (med spas, telehealth, cosmetic dental) market like ecommerce. In-network practices grow through payer directories, referrals, and local search.
  • Trust signals convert. Provider credentials, reviews, before/after galleries where allowed, and condition content written or reviewed by clinicians.
  • Tracking is constrained. After HHS issued guidance on tracking technologies (December 2022, revised March 2024), many providers removed pixels. A federal court vacated part of that guidance in June 2024 (AHA v. Becerra), but HIPAA still bars sending patient information to ad platforms, and the FTC has acted against health apps for the same thing. Meta also restricts lower-funnel conversion events for many health and wellness advertisers. Missing pixels or missing purchase events may be compliance, not a lack of paid ads.
  • Telehealth grows like DTC with a clinical gate: paid social, influencers, quizzes, and subscriptions, limited by state licensing and prescribing rules.

Signals to Collect

Signal Where or how What it shows
Location and provider count over time Wayback captures of location and provider directory pages Expansion pace and acquisitions; each wave is a move in moves.csv
Condition and treatment page library teardown.mjs site and sitemap-growth Their SEO engine; when each family launched
★ Medical reviewer bylines Read condition pages for "medically reviewed by" and author credentials How they build credibility for health searches
Reviews per location Official Places API or manual reads; Healthgrades, Zocdoc, Vitals profiles Review velocity; spikes are review campaigns
Payer and directory listings Insurance pages, Zocdoc and insurer directories Which networks they're in and where patients find them
★ Pixel removal or consent changes teardown.mjs stack <domain> over time When they changed tracking, which can explain a dip in reported paid performance
Ad library presence and claims teardown.mjs ads and sc-ads; Meta and Google libraries Which treatments they advertise and how they phrase claims within policy
Intake quiz flow Walk the public quiz up to the point of entering health data Segmentation, qualification, and price reveal timing
State availability changes Wayback of the "where we're available" page Licensing expansion; each new state is a move
Influencer and creator content Search social for the brand and #ad or #sponsored Telehealth and aesthetics creator programs
Clinical trials and approvals ClinicalTrials.gov, FDA announcements, press releases Pipeline and launch timing for medtech and pharma
★ Provider records The NPPES NPI Registry (public search and API) by organization name and location Providers tied to the organization and when each was enumerated, a check on provider-count claims and new-location hiring
State licensing for telehealth State medical board license lookups for the target's clinicians Which states they can actually serve, and when each license was issued
★ Open payments to physicians CMS Open Payments database Which doctors a pharma or device company pays for speaking and consulting, a proxy for prescriber marketing

Going Inside

  • Never book an appointment you won't keep. A no-show costs a practice a real slot and may block a real patient. Only book if the user actually wants the care.
  • Never enter real or fake health information. Stop intake quizzes before the health questions, or use questions that don't require personal health data. Don't create a patient record.
  • With approval, it's fine to: read public pricing, call the front desk to ask about pricing, insurance, and availability under the user's real name, and record response speed and the scheduling flow.
  • For telehealth, walk the funnel to the checkout or medical intake and stop. Screenshot pricing, plans, and the subscription terms.

Rules That Limit Copying

  • HIPAA and HHS tracking guidance: covered entities can't send protected health information to ad platforms through pixels. Copying a competitor's tracking setup can create violations. Check with counsel.
  • FTC Health Breach Notification Rule applies to many health apps that aren't covered by HIPAA.
  • FDA and FTC split the work. The FDA governs prescription drug and restricted device advertising: fair balance, Important Safety Information, and approved indications only. The FTC covers over-the-counter drugs, supplements, most devices, and health claims in general. In September 2025 the FDA began a broad enforcement push on drug ads, including social media and influencer posts, and it has warned telehealth companies against marketing compounded drugs as if they were approved products.
  • FTC substantiation: health claims need competent and reliable scientific evidence. Before/after claims need typical-result context.
  • Platform policies: Google's healthcare and medicines policy requires certification for some categories (online pharmacies, addiction services). Meta restricts targeting and personal health assertions ("Are you struggling with...").
  • Controlled substances: prescribing them through telehealth falls under DEA rules whose temporary flexibilities have been extended several times. Check the current status before copying a telehealth model.
  • State rules: medical advertising, corporate practice of medicine, and telehealth licensing vary by state. Check with counsel.

Plays That Usually Transfer

Play Run it with
Condition and treatment page library with clinician review content-strategy, programmatic-seo
Provider and location pages with schema schema, site-architecture
Review program after visits, within platform rules referrals
Intake quiz that segments and reveals price lead-magnets, cro
Compliant ad creative with claim substantiation ad-creative, ads
Server-side, consent-aware conversion tracking conversion-tracking, analytics
Referral relationships with referring providers, with no payment or gifts tied to referrals unless counsel clears them (Anti-Kickback Statute, Stark Law) co-marketing, sales-enablement

Metrics to Ask About

  • Cost per booked appointment: spend divided by kept appointments, not form fills.
  • Show rate: share of booked appointments kept.
  • New patient volume: per location per month.
  • Patient lifetime value: visits or subscription months times margin.
  • Referral share: patients from referring providers vs self-referred.
  • Intake completion rate: for telehealth, quiz start to paid consult.
  • Retention: subscription churn for telehealth, recall rate for practices.

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