agentleFS
fjilvvifjilvvi/growthlens/skills/competitor-teardown/SKILL.md

competitor-teardown

Skill2 starsChanged 5 months agoMITView on GitHub

Full teardown of a competitor from their public website — positioning, target audience, offer and value ladder, pricing signals, funnel, acquisition channels, and social proof — ending with their likely strategy and where they are exposed. Use when the user shares a competitor's URL or asks to "analyze", "research", "break down", "do a teardown of", or "size up" a competitor or a rival product.

13 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you only have a brand name and can't confirm the official domain, ask.

    line 42
  2. Distinctive:

    No invented metrics, funding, or headcount.

    line 109

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Competitor Teardown

Turn a competitor's website into a structured intelligence report: how they position, what they sell, how they get customers, and where they're weak.

What it does

Produces a complete competitor profile from public information only. It reads the competitor's site the way a strategist would — homepage, product/pricing/about pages, blog, and footer — and reconstructs their positioning, offer, funnel, and go-to-market, then judges where they are strong and where they are exposed.

When to use this skill

  • "Here's a competitor: <url> — break them down."
  • "Research <company> for me."
  • "How does <competitor> position themselves / make money / get traffic?"
  • Building a battlecard, a market map, or prepping a strategy session.

Inputs needed

  • Required: the competitor's primary URL (homepage). If the user names a company without a URL, find the official site first and confirm it.
  • Helpful: the user's own product/positioning (to make the comparison relevant), the market/niche, and any specific question ("focus on pricing").
  • If you only have a brand name and can't confirm the official domain, ask.

Method

Work through the teardown framework — the nine lenses below. For each, capture what's observable and flag what you're inferring.

  1. Snapshot — company, category, one-line "what they do", apparent stage/size (team page, funding mentions, customer logos).
  2. Positioning — the promise in the hero section, the category they claim, who they say it's for, and the primary differentiator they lean on.
  3. Target audience / ICP — who the copy speaks to; segments and roles named.
  4. Offer & value ladder — products/plans, lead magnets, free tier/trial, core offer, upsells. Map the ladder from free → flagship.
  5. Pricing signals — published prices, packaging, billing terms, anchoring, discounts. If pricing is hidden, note that and what it implies.
  6. Funnel & conversion path — the steps from landing to purchase; primary CTA, friction, lead capture, demo/checkout flow.
  7. Acquisition channels — evidence of SEO (blog depth, topics), paid ads (landing-page patterns, UTM hints), social, partnerships, affiliates.
  8. Social proof & trust — testimonials, case studies, logos, reviews, guarantees, named results.
  9. Strengths & vulnerabilities — synthesize: what they do well, where the gaps are, and where a challenger could attack.

Visit the most informative pages (home, product, pricing, about, a few blog posts). Don't speculate beyond what the site supports.

Output format

# Competitor Teardown — <Company>

## TL;DR
- 3–5 sharp takeaways (positioning, who they target, how they monetize, biggest weakness)

## 1. Snapshot
| Field | Finding |
|-------|---------|
| Category | |
| What they do | |
| Apparent stage/size | |

## 2. Positioning
- Hero promise:
- Category claimed:
- Primary differentiator:

## 3. Target audience / ICP
## 4. Offer & value ladder
## 5. Pricing signals
## 6. Funnel & conversion path
## 7. Acquisition channels
## 8. Social proof & trust

## 9. Strengths & vulnerabilities
| Strengths | Vulnerabilities (where to attack) |
|-----------|-----------------------------------|

## Strategic read
2–3 sentences: their apparent strategy and the single best opening against them.

Quality bar

  • Mark every claim as observed (on the site) or inferred (your read).
  • No invented metrics, funding, or headcount. "Not disclosed" is a valid answer.
  • The "vulnerabilities" must be specific and actionable, not "could improve UX".
  • Analyze the company, not its employees as individuals.

Common mistakes to avoid

  • Summarizing the homepage instead of reconstructing the strategy.
  • Treating marketing copy as fact (a claimed differentiator ≠ a real one).
  • Ending with a list of features instead of a strategic read.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.