Market research

Skill tuliosousapro/SaaS-blueprint/skills/market-research

Deep web research skill using Firecrawl MCP. Use when estimating market size (TAM/SAM/SOM), analyzing trends, or scraping competitors. For competitor teardowns, see competitor-analysis.From its SKILL.md

Install

npx -y skills add tuliosousapro/SaaS-blueprint --skill market-research

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

4 stars4 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.

SKILL.md

3.1 KB, 737 tokens by cl100k_base, as published. Nobody here has run it

Market Research Skill

When to Use

During Phase 0 (Idea) → Market Research, Competitor Analysis, Opportunity Mapping
During Phase 1 (Validation) → Demand Testing
Any time you need structured intelligence about a market, niche, or competitor

Tools Required

Tool	Purpose
`firecrawl_search`	Web search for market data, trends, competitors
`firecrawl_scrape`	Extract structured data from specific pages
`firecrawl_extract`	Pull pricing, features, positioning from competitor sites
`firecrawl_map`	Discover all pages on a competitor's site

Instructions

1. Define Research Scope

Before starting any research, clarify with the user:

Market/Industry: What space are we researching?
Geography: Global, US, EU, LATAM, specific country?
Depth: Quick scan (30 min) or deep dive (2+ hours)?
Focus: TAM estimation, competitor landscape, trend signals, or all three?

2. TAM/SAM/SOM Estimation

Execute these searches in parallel:

firecrawl_search: "{industry} market size 2024 2025 report"
firecrawl_search: "{industry} SaaS revenue growth forecast"
firecrawl_search: "{niche} total addressable market"

Structure the output as:

Metric	Value	Source	Confidence
TAM	$X B	{source}	High/Med/Low
SAM	$X M	{source}	High/Med/Low
SOM	$X M	{source}	High/Med/Low

3. Competitor Landscape

For each competitor identified:

firecrawl_extract:
  urls: ["{competitor_url}"]
  prompt: "Extract: company name, tagline, pricing tiers, key features, target audience, tech stack indicators"
  schema: {
    name: string,
    tagline: string,
    pricing: [{ tier: string, price: string, features: [string] }],
    target_audience: string,
    key_features: [string]
  }

Compile into a comparison matrix:

Feature	Competitor A	Competitor B	Competitor C	Our Opportunity

4. Trend Analysis

Search for:

firecrawl_search: "{industry} trends 2025 2026"
firecrawl_search: "{niche} emerging technology"
firecrawl_search: "{industry} pain points users complain"

Categorize trends as:

Tailwinds (market forces working in our favor)
Headwinds (forces working against us)
Wildcards (unpredictable but high-impact)

5. Output Format

Save all research to the relevant PLAYBOOK.md directory as RESEARCH.md with:

Executive Summary (3 sentences max)
TAM/SAM/SOM table
Competitor matrix
Trend analysis (tailwinds/headwinds/wildcards)
Key insight + recommended action
Sources list with URLs

Quality Gates

Minimum 3 independent sources for any TAM claim
Competitor data must be scraped, not assumed
All monetary values must include year and currency
Trends must be dated (no stale 2022 data presented as current)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most research analysis skills give in 737 tokens

Counted across 1,213 of the 2,113 authors here whose files we hold, read 2026-09-06

Cite sources for every important claimin 47 of 1213, across 38 files
Separate facts from inferences and recommendationsin 21 of 1213, across 12 files
Write findings to a markdown filein 19 of 1213
Label every insight with a confidence levelin 18 of 1213, across 8 files
Read product marketing context before asking questionsin 18 of 1213, across 8 files
Rank themes by frequency and intensityin 16 of 1213, across 6 files
Establish research mode before proceedingin 16 of 1213, across 6 files
Segment survey responses by customer tier or tenurein 16 of 1213, across 6 files
Categorize support tickets before analyzingin 16 of 1213, across 6 files
Weight research sources from the last twelve monthsin 16 of 1213, across 6 files
Use at least five data points per segmentin 15 of 1213, across 5 files
Extract verbatim quotes for all research findingsin 15 of 1213, across 5 files

Said here and by no other author read

Execute market size searches in parallel
Extract competitor data using structured schemas
Compile competitor data into a comparison matrix
Categorize trends into tailwinds headwinds and wildcards
Verify TAM claims with three independent sources
Scrape competitor data instead of assuming

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.