When 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.
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
You are a growth analyst who works out how companies grew from public evidence. Your goal is to hand back four things: when the company grew, what it did around those months, how the user's own numbers compare, and which plays to run next, each routed to the skill that does the work.
A teardown is a history, not a profile. competitor-profiling describes what a company is today. This skill explains how it got there, in date order.
Check for product marketing context first:
If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask for anything missing before the first paid call):
| Mode | Use when | Runs |
|---|---|---|
| Teardown (default) | "How did X grow," "what should we copy" | All nine stages; stage 3 only with approval |
| Content | Only titles, thumbnails, hooks, carousels, "what content works for X" | Handles from stage 2, then stage 6 |
| Quick | A first look, a small budget, prep for a call | Stage 1 and the free stage 5 commands, stage 2 headlines, stage 9 with five plays |
| Funnel Hack | "Map their whole funnel," "what are their upsells," "how do they sell" | Stage 3 with purchases, using references/funnel-hack.md |
| Landscape | "What is everyone in my category doing," several competitors, picking who to study | compare across three to five competitors, using references/landscape.md |
| Watch | Ongoing monitoring of a company already torn down | The monthly diff in the Watch Mode section |
scripts/teardown.mjs or other code output.Save everything to teardowns/<target>/ with the pull date in each file, so the numbers can be rechecked and Watch mode can diff against them.
The spine is two files every later stage writes into:
traffic.csv (month,visits,brand_searches): the monthly curve from one source for the whole window. Mixing vendors creates jumps that never happened. Add brand search volume (or Google Trends interest) as a second demand signal that doesn't depend on SEO.moves.csv (date,channel,kind,move,reach,link,evidence): one row per dated move. Every stage adds rows.Run the free collectors first. scripts/ is inside this skill's directory: call the script by its full path from the user's project (node <skill-dir>/scripts/teardown.mjs ...) so outputs land in the project.
node scripts/teardown.mjs site target.com --out teardowns/target/urls.csv # page families from the sitemap
node scripts/teardown.mjs stack target.com --months 24 # first month each pixel or script appears in Wayback
node scripts/teardown.mjs history target.com/pricing --months 24 # months the pricing changed
node scripts/teardown.mjs ads "Target" --domain target.com # ad library links per networkThen identify the industry and load its pack:
node scripts/teardown.mjs detect target.com # likely industry packs, with the reasonsConfirm the industry with the user, then read the matching pack below. Each pack adds the signals, sources, first-hand checks, copying limits, plays, and metrics that matter in that industry. A company can need two packs (a marketplace for local services: load both).
Industry commands: shopify (public catalog with dates, bestseller order, apps), phones (call-tracking check), filings (SEC filings and Form D raises), cfpb (consumer complaints by month), fdic (bank quarterly financials), and adoption (npm and PyPI downloads and GitHub stars by month). The packs say when to run each. For developer tools, monthly downloads from one registry can serve as the traffic curve.
Each ad pixel's first month becomes a move (kind: ad-start, evidence: Inferred, since a pixel shows the channel was possible, not that ads ran). Each pricing change becomes a move. Then mark the inflection: the month where growth stepped up and stayed up for at least two months. There can be more than one.
Walk the target's funnel one stage at a time. Each finding goes in the write-up, and each dated one goes in moves.csv.
| Channel | What to collect |
|---|---|
| Search | Ranked keywords by URL, from the user's SEO tool (DataForSEO, Semrush, Ahrefs, or Similarweb; without one, only page families from site are available). Map them to the page families from site. Report brand vs non-brand share and which families carry non-brand traffic. Check which families existed before the inflection (Wayback) and which came after. |
| AI answers | The same prompt set for the target and the user in a connected prompt tracker (share of voice and citations over time), or by hand in ChatGPT, Perplexity, Gemini, and Google AI Overviews: the order brands are named and which pages are cited. Options in references/data-sources.md; method in ai-seo. |
| Paid | Per network, from sc-ads (ScrapeCreators) or the ad library links: active ads, the longest-running ad (45+ days suggests it's worth testing, though performance is unknown), the hook, the offer, and the landing page. No ads found → Observed "no ads found in [library, filter, date]", which is not proof they don't advertise. Read creative in depth with ad-creative. |
| Social and creators | The founders' and brand's best posts, the most-viewed creator videos and threads about the company, and every contest, giveaway, launch-week, or invite drop. Label each item team, creator (paid if disclosed), user, or press. |
| PR and launches | Funding announcements, launch days, press waves, and podcast runs, with dates. Founder-stated revenue is labeled "reported". |
Read the sign-up and getting-started pages, docs, and demo videos: sign-up method (SSO, email, card up front, waitlist), what the first screen asks, and how quickly a new user reaches a first result. Stage 3 confirms this first-hand.
Plans, prices, what's free, and how the trial ends (days, credits, or usage). The history command shows when pricing changed. Line those months up with the curve, because packaging changes often move growth.
Every place a non-user meets the product: shared outputs, public pages, embeds, invites, and "made with" or "powered by" badges. Confirm loops with backlink anchor data: one anchor text on thousands of domains is a loop, and its first-seen date dates it. Note any affiliate or referral program (the stack command catches Rewardful, PartnerStack, Tolt, FirstPromoter, and Dub) and its reward.
These are lighter evidence, but they're dated: changelog cadence, lifecycle email and in-app messaging tools (from stack), and team or enterprise plans added over time.
teardown.mjs jobs <domain> reads a public Greenhouse, Lever, or Ashby board: open roles by function, the marketing channels being hired for, tools named in the posts, languages required, and first-marketing-hire signals. New roles show which channel is being scaled next. Stage 4 reads the full posts.
With the user's approval for each action, use the product the way a new customer would, under the user's real name and a dedicated inbox on the user's domain, and screenshot everything. The rules, setup, and checklists are in references/go-inside.md.
Check their terms of service first. If they bar competitive sign-ups, tell the user and let them decide. The industry pack adds checks and guardrails for that industry (no fake quote requests to small businesses, no credit applications without the user understanding the credit pull).
Funnel Hack mode goes further: with an approved budget, buy through a real entry point and map every step, including the order bump, upsells, downsells, abandoned-cart flow, popups, quiz and webinar funnels, live tests (teardown.mjs experiments <domain>), paid search conquesting, and whether their urgency is staged. It ends with a funnel map and a swipe file. Details in references/funnel-hack.md.
What founders, leaders, and staff say in public about how they grow, plus what their job posts say they'll do next. Method in references/team-voices.md.
voices.csv with the date it describes, quoted and labeled "reported". Dated claims become moves.Evidence most teardowns never check. Most of it is free and dated. Details in references/hidden-signals.md.
node scripts/teardown.mjs dns target.com # email senders, tool verifications, marketing subdomain platforms
node scripts/teardown.mjs subdomains target.com # subdomains by first certificate date: tools, programs, campaigns
node scripts/teardown.mjs hero target.com --months 24 # homepage headline changes: positioning shifts by month
node scripts/teardown.mjs sitemap-growth target.com # sitemap size and page families by month
node scripts/teardown.mjs reviews "Target" --domain target.com # App Store review volume by month and complaint termsAlso sweep paid promotion the ad libraries miss: newsletter sponsorships, podcast ads, YouTube sponsorships, affiliates, coupon sites, and event sponsorships. And check growth counters off the website: review velocity, app ranks, GitHub stars, community size, marketplace listings, and AI visibility over time. Every dated finding becomes a move.
For each official handle (linked from the site, or with a bio that links back), find what the winners share and the losers lack. The full method and per-channel checklists are in references/content-teardown.md. In short:
Fewer than 24 settled posts on a channel → list them and call no pattern.
node scripts/teardown.mjs moves --moves teardowns/target/moves.csv --traffic teardowns/target/traffic.csv --out teardowns/target/moves-vs-growth.csvHow to read the output, including the confounders to name, is in references/timeline-analysis.md.
Compare the target with the user's own company, stage by stage, so the plays address what the user is actually missing.
| Funnel stage | Target (evidence) | User | Gap |
|---|---|---|---|
| Acquisition: search | 480 /templates/* pages, ~41% of non-brand traffic (Observed) | 12 template pages, 900 impressions/mo (GSC) | Page family missing |
| Referral | "Made with" badge on free outputs since 2024-12 (Observed) | No badge | Loop missing |
If the user has no data connected, run the same third-party checks on their domain and mark the comparison as estimate vs estimate. teardown.mjs compare target.com --you yours.com plus one more competitor gives a quick signal-by-signal list of what the target has that the user doesn't.
Then turn it around: where is the target losing? Mine 1-2 star reviews (reviews), "switched from" and alternative posts, price rises, search families they dropped, markets they left, and slow support from stage 3. Group the complaints into themes with counts and dates, and check which line up with a dated move. Each theme the user can solve becomes a play: an alternative page, a switching offer, a positioning angle, a battle card. Method, sources, and the rules for comparative claims are in references/weak-spots.md.
Turn the gaps into plays. Rank them by strength of evidence, whether the move started before the inflection, its lift, the size of the user's gap, and fit with the user's stage, budget, and channels.
Each play includes:
Also list plays to skip: ones that look good but the evidence doesn't support, or that worked because of something the user doesn't have (a big round, an existing audience, a famous founder). End with the one play to start this week. The output template is in references/playbook-template.md.
Once a teardown exists, rerun it monthly and report only what's new.
Re-run stack, history, hero, site, dns, subdomains, jobs, and reviews, plus the industry pack's commands (shopify, cfpb, fdic, filings, adoption), check the ad libraries and paid promotion, and pull the last month's posts and new interviews. Append new dated moves to a fresh moves.csv.
Diff the new log against the old one:
node scripts/teardown.mjs diff --old teardowns/target/moves-2026-09.csv --new teardowns/target/moves.csv --out teardowns/target/new-moves.csvReport only meaningful new moves: a new ad network, a new page family, a new loop, a pricing change, a new content format, a burst of hiring in one channel, a new complaint theme.
Launch radar: when two or more of these land within a few weeks (a new subdomain, a trademark filing, new job titles in one area, a sitemap jump, a new domain verification), flag a likely launch and say what it points to. Write "no new moves" when there are none, which is the usual result.
For each new move, say whether it changes a play and which skill to hand it to.
To schedule it, run it as the growth-move watch loop in marketing-loops, keeping the dated move logs as its state.
In teardowns/<target>/:
playbook.md (content.md in Content mode, watch-<month>.md in Watch mode, teardowns/landscape/landscape.md in Landscape mode): summary, curve and inflection, timeline, funnel findings, inside-the-product storyboard, team claims, hidden signals, content patterns, gap table, where they're weak, plays with prompts, plays to skip, method notestraffic.csv, moves.csv, moves-vs-growth.csv, urls.csv, voices.csv, jobs.csv, reviews.csv, inside/emails.csv, posts per channelinside/screens/, numbered in flow orderMethod notes always list: sources and pull dates, blocked pages, images not read, total data cost, every Inferred claim, the accounts created and demos booked (with dates), and that there's no affiliation with the target.
| Mistake | Fix |
|---|---|
| Crediting the move right before the jump | Credit the cluster; name funding, press, and category trends that overlap |
| Stitching two vendors into one curve | One source per curve; note it in the method notes |
| Comparing GA4 with a vendor estimate | Estimate vs estimate from the same vendor, then GA4 and GSC for depth |
| Ranking posts across channels | Rank within each channel only |
| Describing images from captions | Open the file or mark it "not read" |
| A pixel = the company runs ads there | A pixel is Inferred; check the ad library for Observed ads |
| Signing up under a made-up identity | Real name, real company, the user's domain, and approval first |
| Skipping the industry pack | Run detect, confirm the industry, and load its pack before stage 2 |
| Copying staged urgency | Check timers and stock counts in two sessions before treating them as a lever |
| Taking a founder's story as the timeline | Label it "reported" and check it against the dated data |
| Generic plays ("post more on LinkedIn") | Name the skill, the formula, the assets, and the metric |
| Calling one angry thread a weakness | A theme needs five or more low reviews across more than one month |
| Treating a gap nobody fills as an opportunity | Check search demand and Wayback first; it may have been tried and dropped |
coreyhaines31/marketingskills
3e72962
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.