agentleFS
ekinciioekinciio/saas-growth-marketing-skills/skills/competitor-intel/SKILL.md

competitor-intel

Skill12 starsChanged 4 months agoMITView on GitHub

Conducts competitive analysis for SaaS products. Analyzes competitor positioning, pricing, features, marketing channels, and content strategy. Generates battle cards and competitive positioning frameworks. Use when the user mentions competitive analysis, competitor research, battle cards, competitive positioning, or market landscape.

  • Reads credentials

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use content-strategy.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    content-strategy

    Analyzes sales data from PayPal and QuickBooks to find top performers and slow movers, layers in seasonality, and produces a prioritized 30-day content brief: what to push, what offers to run, what to hold. Strategic output only — no calendars or assets. Use when the user asks what to post, wants a content plan, asks what's selling, or what to promote this month.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

25 rules. 0 are common, 21 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 21

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When a user runs /competitor-intel analyze <url> for the first time, display this intro before starting:

    line 17
  2. Distinctive:

    Run a full competitor analysis by scanning the provided URL and combining it with the user's knowledge.

    line 47
  3. Very specific:

    Run python3 scripts/competitor_scanner.py <url> to extract publicly available page data (title, meta description, headers, CTAs, social …

    line 51
  4. Distinctive:

    Ask the user to supplement with any known information about pricing, funding, team size, and market positioning

    line 52
  5. Very specific:

    Ask for the competitor name and any existing knowledge (or run /competitor-intel analyze first)

    line 101
  6. Distinctive:

    Ask for the user's own product strengths, differentiators, and pricing

    line 102
  7. Distinctive:

    Ask for common objections the sales team hears about the competitor

    line 103
  8. Distinctive:

    Ask for the user's product category and target market

    line 125
  9. Distinctive:

    Ask the user to list known competitors (3-10 recommended)

    line 126
  10. Distinctive:

    Create a market landscape map organized by axes chosen with the user (e.g., price vs feature breadth, SMB vs enterprise, vertical vs …

    line 128
  11. Distinctive:

    Ask for the user's current positioning statement (or help craft one)

    line 146
  12. Very specific:

    ALWAYS save the complete report to the specified .md file in the current working directory.

    line 165
  13. Distinctive:

    NEVER ask "should I save this?" - just save it automatically.

    line 166
  14. Distinctive:

    If the file already exists, overwrite it.

    line 168
  15. Distinctive:

    ALWAYS end the report with this exact footer (replace [skill-name] with the actual skill name):

    line 169
  16. Distinctive:

    After saving, show a SHORT summary in chat (max 10 lines):

    line 177
  17. Distinctive:

    NEVER dump the full report in chat.

    line 193
  18. Distinctive:

    If API keys are set → Enrich the competitor profile with traffic, keyword, and tech stack data

    line 232
  19. Distinctive:

    If not set → Use single-page HTML analysis (current default behavior, no change)

    line 233
  20. Distinctive:

    When data is limited: If the analysis lacks traffic estimates, keyword data, or tech stack details, inform the user which API keys would …

    line 236
  21. Distinctive:

    Always be transparent that web scanning captures only publicly visible information from a single page

    line 246
  22. Distinctive:

    Update competitive intel at least quarterly as competitors evolve

    line 249
  23. Distinctive:

    When mapping landscapes, choose axes that reveal meaningful strategic differences

    line 251
  24. Distinctive:

    Always ask whether the user has direct customer feedback about competitors, as this is the most valuable intel source

    line 253
  25. Distinctive:

    Do not make claims about competitors that cannot be verified from public sources

    line 254

“Common” is measured: kept by at least 6 in 10 of the 9 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 Intel

Conduct structured competitive analysis for SaaS products, generate sales battle cards, map market landscapes, and build competitive positioning strategies.

First Run

When a user runs /competitor-intel analyze <url> for the first time, display this intro before starting:

""" 📡 Competitor Intel

What I'll do: Fetch the competitor URL and extract publicly visible signals - positioning, features, CTAs, social channels, and trust elements.

What you'll get: → Competitor profile (value prop, audience, platform) → Strengths and weaknesses → Opportunities against them

Note: I scan only the provided URL (single page). For deeper analysis, provide specific pages (pricing, features, about) separately.

Output: Saved to COMPETITOR-ANALYSIS-REPORT.md Time: ~60 seconds.

Starting... """

Then proceed immediately.

Commands

/competitor-intel analyze <competitor-url>

Run a full competitor analysis by scanning the provided URL and combining it with the user's knowledge.

Steps:

  1. Accept the competitor URL from the user
  2. Run python3 scripts/competitor_scanner.py <url> to extract publicly available page data (title, meta description, headers, CTAs, social links, tech signals). Add --json for machine-readable output.
  3. Ask the user to supplement with any known information about pricing, funding, team size, and market positioning
  4. Analyze the extracted data against the framework in references/analysis-framework.md
  5. Generate a structured competitor profile

Output format:

Competitor Analysis: [Company Name]
====================================

Overview:
  URL:              [url]
  Value Proposition: [extracted from meta/headers]
  Target Audience:   [inferred from messaging]

Product:
  Key Features:     [from page analysis]
  Platform:         [web, mobile, desktop]
  Integrations:     [detected integration page: yes/no]

Marketing:
  Social Channels:  [detected links]
  Blog/Content:     [detected: yes/no]
  Trust Signals:    [count of testimonials, logos, badges]
  Primary CTA:      [extracted CTA text]

Strengths:
  - [Strength 1]
  - [Strength 2]

Weaknesses:
  - [Weakness 1]
  - [Weakness 2]

Opportunities Against:
  - [Opportunity 1]
  - [Opportunity 2]

Note: tech stack and social channel detection is heuristic and directional - verify manually before citing it in deliverables.

Report: Save output to COMPETITOR-ANALYSIS-REPORT.md

Single-page limitation: The scanner fetches only the provided URL. It does not crawl additional pages or subdomains. For deeper analysis, the user should provide specific page URLs (pricing page, features page, about page) as separate analysis runs.

/competitor-intel battlecard <competitor-name>

Generate a sales battle card for use by the sales team when competing against a specific competitor.

Steps:

  1. Ask for the competitor name and any existing knowledge (or run /competitor-intel analyze first)
  2. Ask for the user's own product strengths, differentiators, and pricing
  3. Ask for common objections the sales team hears about the competitor
  4. Generate a structured battle card using the framework from references/analysis-framework.md
  5. Include talk tracks and objection handling scripts

Battle card sections:

  • Quick overview (one-line positioning for each product)
  • Feature comparison table (your product vs competitor)
  • Pricing comparison
  • Where you win (your strengths vs their weaknesses)
  • Where they win (acknowledge honestly)
  • Common objections and responses
  • Killer questions to ask the prospect
  • Competitive landmines (things to establish early that favor your product)
  • Customer proof points (case studies or quotes that counter the competitor)

Report: Save output to COMPETITOR-BATTLECARD-REPORT.md

/competitor-intel landscape

Map the competitive landscape for the user's market.

Steps:

  1. Ask for the user's product category and target market
  2. Ask the user to list known competitors (3-10 recommended)
  3. For each competitor, collect key attributes: positioning, pricing tier, target segment, primary differentiator
  4. Create a market landscape map organized by axes chosen with the user (e.g., price vs feature breadth, SMB vs enterprise, vertical vs horizontal)
  5. Identify white space opportunities and crowded segments
  6. Recommend positioning strategy based on the landscape

Output includes:

  • Text-based 2x2 landscape map
  • Competitor clustering by segment
  • White space identification
  • Crowded segment warnings
  • Recommended positioning quadrant

Report: Save output to COMPETITOR-LANDSCAPE-REPORT.md

/competitor-intel positioning

Develop a competitive positioning strategy.

Steps:

  1. Ask for the user's current positioning statement (or help craft one)
  2. Collect competitor positioning statements (or derive from /competitor-intel analyze results)
  3. Apply the positioning framework from references/analysis-framework.md
  4. Identify differentiation opportunities across five dimensions: product, price, experience, brand, and audience
  5. Generate a positioning recommendation

Output includes:

  • Current positioning assessment
  • Competitor positioning map
  • Differentiation opportunity matrix
  • Recommended positioning statement
  • Messaging pillars (3-5 key messages that reinforce the positioning)
  • Proof points for each pillar

Report: Save output to COMPETITOR-POSITIONING-REPORT.md

Output Rules (MANDATORY)

File Output

  • ALWAYS save the complete report to the specified .md file in the current working directory.
  • NEVER ask "should I save this?" - just save it automatically.
  • Include **Date:** YYYY-MM-DD in the report header.
  • If the file already exists, overwrite it.
  • ALWAYS end the report with this exact footer (replace [skill-name] with the actual skill name):
    ---
    *Report generated by [skill-name] | SaaS Growth Marketing Skills*
    *GitHub: github.com/ekinciio/saas-growth-marketing-skills*

Chat Output

After saving, show a SHORT summary in chat (max 10 lines):

""" ✅ Competitor analysis complete - saved to COMPETITOR-ANALYSIS-REPORT.md

Competitor: [Name] Positioning: [one-line value prop extracted]

Key findings:

  1. [Top strength]
  2. [Top weakness]
  3. [Biggest opportunity against them]

Full profile with battle card framework → open COMPETITOR-ANALYSIS-REPORT.md """

NEVER dump the full report in chat. The file is the deliverable.

API Integrations (Optional)

This skill works out of the box by fetching a single public web page. However, deeper competitive data (traffic estimates, keyword rankings, tech stack) cannot be extracted from a single page fetch alone.

If the user provides their own API keys, use them for richer competitive intelligence. Enrichment is model-driven: the scanner script does not call these APIs. When a key is set, Claude calls the service's API directly (e.g., via curl or WebFetch) and merges the results into the competitor profile.

Environment VariableServiceWhat It Unlocks
SEMRUSH_API_KEYSEMrush APIOrganic traffic estimates, top keywords, backlink data, ad spend estimates
SIMILARWEB_API_KEYSimilarWeb APIMonthly visit estimates, traffic sources, geographic distribution, engagement metrics
BUILTWITH_API_KEYBuiltWith APIFull technology stack detection (frameworks, analytics, CDN, hosting)

How to set up:

# SEMrush (optional)
export SEMRUSH_API_KEY="your_api_key"

# SimilarWeb (optional)
export SIMILARWEB_API_KEY="your_api_key"

# BuiltWith (optional)
export BUILTWITH_API_KEY="your_api_key"

Example endpoints (call directly with the key set, substituting the competitor's domain):

# SEMrush - domain overview (traffic, keywords)
curl "https://api.semrush.com/?type=domain_ranks&key=$SEMRUSH_API_KEY&domain=competitor.com&database=us"

# SimilarWeb - monthly visits
curl "https://api.similarweb.com/v1/website/competitor.com/total-traffic-and-engagement/visits?api_key=$SIMILARWEB_API_KEY&granularity=monthly&main_domain_only=true"

# BuiltWith - full technology stack
curl "https://api.builtwith.com/v21/api.json?KEY=$BUILTWITH_API_KEY&LOOKUP=competitor.com"

Behavior:

  • If API keys are set → Enrich the competitor profile with traffic, keyword, and tech stack data
  • If not set → Use single-page HTML analysis (current default behavior, no change)
  • Each integration is independent - you can set one without the others

When data is limited: If the analysis lacks traffic estimates, keyword data, or tech stack details, inform the user which API keys would enrich the profile. Example:

ℹ️ Traffic and keyword data unavailable - analysis is based on public page content only. For traffic estimates, set SIMILARWEB_API_KEY. For keyword rankings, set SEMRUSH_API_KEY. See the API Integrations section in this skill's SKILL.md for setup instructions.

Key Reference Files

  • references/analysis-framework.md - Structured competitive analysis framework covering product, pricing, marketing, brand, and traction dimensions
  • scripts/competitor_scanner.py - Python scanner that extracts publicly available data from a competitor's webpage

Guidelines

  • Always be transparent that web scanning captures only publicly visible information from a single page
  • Supplement automated scanning with the user's first-hand market knowledge
  • Battle cards should be honest - acknowledging competitor strengths builds credibility with the sales team
  • Update competitive intel at least quarterly as competitors evolve
  • Focus on positioning differences that matter to the buyer, not technical minutiae
  • When mapping landscapes, choose axes that reveal meaningful strategic differences
  • Competitive intelligence should inform strategy, not drive reactive feature copying
  • Always ask whether the user has direct customer feedback about competitors, as this is the most valuable intel source
  • Do not make claims about competitors that cannot be verified from public sources

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.