agentsclimarketplace

Competitor teardown

Skill saurabhshuklagrowisto/saurabh-ai-systems/claude-skills/competitor-teardown

AI architect for GTM and martech. I design and ship production agentic systems for B2B sales and marketing: lead scraping and scoring with an eval gated learning loop, autonomous CRM enrichment, ABM pipelines, live dashboards that refresh themselves, MCP servers and Claude skills. Built at Growisto.

Install
npx -y skills add saurabhshuklagrowisto/saurabh-ai-systems --skill competitor-teardown

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Turns a messy competitive landscape into a scored positioning matrix and a recommended wedge. Takes your brand plus 2-5 competitors and a set of buyer-decision dimensions, each scored 0-5 per player, and returns where you win, where you lose, the category whitespace nobody owns, and the sharpest wedge to position on. Use before writing positioning or messaging, before a launch, or when a rep keeps losing deals to the same competitor and you need to know why.

SKILL.md

2.4 KB, as published. Nobody here has run it

Competitor Teardown Skill

Most competitive analysis is a wall of prose nobody acts on. This skill forces the landscape into a scored matrix and then answers the only three questions that matter: where do we win, where do we lose, and what is the wedge no one else can copy.

When to use

  • Before writing positioning or homepage messaging.
  • Before a launch, to pick the angle competitors cannot easily counter.
  • When deals keep slipping to one competitor and you need to see the pattern.

When NOT to use

  • For feature checklists to hand to product — this is about buyer-decision positioning, not a spec sheet.
  • With only your own opinion as input — score dimensions from real buyer evidence (reviews, sales-call notes, win/loss), not gut feel.

Method

  1. Pick the dimensions a buyer actually decides on (not every feature — the 5-8 that move a deal).
  2. Score every player 0-5 on each dimension, from evidence.
  3. The engine returns:
    • Wins — dimensions where you lead.
    • Losses — dimensions where a competitor leads you.
    • Whitespace — dimensions the whole category scores low on (own it before anyone does).
    • Wedge — the single dimension where you are strong and the field is weak: your sharpest positioning.

Inputs

{
  "brand": "YourBrand",
  "competitors": ["Rival A", "Rival B"],
  "dimensions": [
    {"name": "Time to value", "weight": 3, "scores": {"YourBrand": 5, "Rival A": 2, "Rival B": 3}}
  ]
}

weight (1-3) reflects how much the dimension moves a buyer.

Output (JSON)

ranking[] (weighted total per player), wins[], losses[], whitespace[], and a single recommended wedge with the reason.

Run it

python scripts/teardown_score.py          # built-in sample
python scripts/teardown_score.py in.json  # your own landscape

Zero dependencies, no API keys. Deterministic scoring in scripts/teardown_score.py.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.