market-research
Skill208 starsChanged 3 months agoMITView on GitHub
Find the right market, extract real customer pain, and validate demand before building an offer. Use when you have an idea but no market, the niche feels too broad, or the offer is not converting. Generates micro-niches, scores them, extracts pain language, and creates a validation test plan — outputs MARKET_RESEARCH.md.
118 other projects use a version of this.
Adopted by
Most recently taken up by
- hmohammed7/claude-skillstheir own version, first seen Nov 16, 2026
- fatihkan/baditheir own version, first seen Nov 16, 2026
- aya-taleb/mimic-skillstheir own version, first seen Nov 15, 2026
- aya-taleb/entrepreneur-skillstheir own version, first seen Nov 15, 2026
- thiefdroppers/cyber-investigator-skillstheir own version, first seen Nov 15, 2026
- Cure-Consulting-Group/ProductEngineeringSkillstheir own version, first seen Nov 12, 2026
Used with
Projects with it also use everything-claude-code, everything-claude-code-conventions and 10 more.
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.
InfopibeSkilleverything-claude-code
Also in 9 projects that use this
mryeastcodeSkilleverything-claude-code-conventions
Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
Also in 8 projects that use this
InfopibeSkillinvestor-materials
Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.
Also in 22 projects that use this
shawnpangSkillcompetitor-monitoring
When the user wants to set up ongoing tracking of competitor activity — pricing changes, feature launches, hiring signals, content, or public mentions. Also use when the user mentions "track competitors", "what are competitors doing", "competitor alerts", or "market watch".
Also in 3 projects that use this
niloykumarbarmanSkillagent-sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
Also in 7 projects that use this
CodeWithBehnamSkilldmux-workflows
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
Also in 15 projects that use this
- +1 more from Infopibe
Other versions118 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 118
- affaan-m/ECC★ 246ksame name
- xu-xiang/everything-claude-code-zh★ 1.9ksame name
- CatCatUncle/openworkbuddy★ 413same name
- shawnpang/startup-founder-skills★ 331same name
- loulanyue/awesome-claude-notes★ 272same name
- okikusan-public/stock_skills★ 134same name
- cohen-liel/hivemind★ 108same name
- extruct-ai/gtm-skills★ 108same name
- tpavanipradeep/everything-claude-code★ 104same name
- mturac/everything-openai-codex★ 89same name
108 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-offerSkill
- bonus-stackSkill
- business-modelSkill
- create-pluginSkill
- dfy-dwy-diySkill
- effort-reductionSkill
- hormozi-hooksSkill
- hormozi-offerSkill
- hormozi-pitchSkill
- idea-to-productSkill
- landing-page-copySkill
- objection-destroyerSkill
- offer-anglesSkill
- pricing-strategySkill
- productizeSkill
- value-acceleratorSkill
- value-perceptionSkill
The file
Files
Skill: Market Research & Demand (Starving Crowd Engine)
Purpose
Find the right market, extract real pain, and validate demand before building an offer.
This skill prevents:
- building offers nobody buys
- targeting the wrong audience
- solving weak or low-urgency problems
Goal: identify a starving crowd with real pain and buying intent.
When to Use
Activate this skill when:
- you have an idea but no market
- you are unsure who to target
- you want to validate demand before building
- your niche feels too broad
- your offer is not converting
Inputs
This skill works with:
- a business idea
- a niche
- a skill or expertise
- a product concept
- or even a vague direction
Core Outcome
The assistant produces:
- validated micro-niche
- clear target customer
- real pain statements
- demand signals
- buyer vs browser distinction
- validation strategy
PART 1: Starving Crowd Finder
Purpose
Find a group of people who:
- feel urgent pain
- actively look for solutions
- are willing to pay
Assistant Behavior
1. Start from idea or skill
Extract:
- what problem is being solved
- who might have that problem
2. Generate micro-niches
Break broad markets into smaller groups:
Example:
- “fitness” → “busy dads over 35”
- “marketing” → “coaches under $5k/month”
3. Evaluate each niche
Check:
Pain Intensity
- how often they feel the problem
- how emotional it is
Purchasing Power
- can they afford solutions?
Accessibility
- can you reach them easily?
Growth
- is the market growing?
4. Score each niche
Score 1–10:
- pain
- money
- reachability
- growth
5. Select best niche
Choose:
- highest combined score
- strongest pain + ability to pay
Output Format
# MARKET_SELECTION.md
## 1. Idea
- Description
## 2. Micro-Niches
- Niche 1
- Niche 2
- Niche 3
## 3. Niche Scoring
- Pain:
- Money:
- Reach:
- Growth:
## 4. Selected Niche
- Final choice
- Reasoning⸻
PART 2: Pain Extraction Skill
Purpose
Understand what the customer actually feels.
⸻
Assistant Behavior
- Identify core problems
List: • main frustrations • repeated struggles • emotional pain
⸻
- Extract real language
Simulate or gather: • how customers describe the problem • informal phrasing • emotional expressions
⸻
- Create pain bullets
Types:
Surface Pain • obvious problems
Deeper Pain • emotional impact
Hidden Pain • fears, doubts, frustrations
⸻
- Generate “midnight thoughts”
What they think when: • stressed • frustrated • alone
⸻
Output Format
# CUSTOMER_PAIN.md
## 1. Core Problems
- Problem 1
- Problem 2
## 2. Raw Language
- Phrases customers use
## 3. Pain Bullets
- Surface pain
- Deeper pain
- Hidden pain
## 4. Emotional Triggers
- Fear
- Frustration
- Desire
## 5. Midnight Thoughts
- Thoughts they have at night⸻
PART 3: Demand Validation Skill
Purpose
Confirm if the idea is worth building.
⸻
Assistant Behavior
- Identify demand signals
Look for: • people asking questions • existing competitors • paid solutions already in market • repeated complaints
⸻
- Classify audience
Split:
Buyers • already spend money • actively search for solutions
Browsers • interested but not paying
⸻
- Evaluate demand strength
Score: • urgency • willingness to pay • competition level
⸻
- Suggest validation tests
⸻
Pre-Sell Test • offer before building • gauge interest
⸻
Fake Door Test • landing page + CTA • measure clicks
⸻
Content Test • post hooks • track engagement
⸻
- Create validation plan
Define: • what to test • how to test • success criteria
⸻
Output Format
# DEMAND_VALIDATION.md
## 1. Demand Signals
- Evidence found
## 2. Buyer vs Browser
- Buyers:
- Browsers:
## 3. Demand Score
- Urgency:
- Willingness to pay:
- Competition:
## 4. Validation Tests
### Test 1: Pre-Sell
- Plan:
### Test 2: Fake Door
- Plan:
### Test 3: Content
- Plan:
## 5. Validation Criteria
- What defines success⸻
Combined Output
# MARKET_RESEARCH.md
## 1. Selected Market
- Niche
- Reasoning
## 2. Customer Pain
- Pain bullets
- Emotional triggers
- Midnight thoughts
## 3. Demand Validation
- Signals
- Buyer vs browser
- Test plan⸻
Decision Rules
Choose a niche when: • pain is frequent • emotion is strong • money is available
Avoid markets when: • pain is weak • no urgency • no proof of spending
Trust demand when: • people pay already • solutions exist • complaints are frequent
⸻
Style Guidelines • be specific • use real language • focus on pain • avoid assumptions • prioritize clarity
⸻
Success Criteria
The skill works when: • a clear niche is selected • pain is deeply understood • demand is validated • idea feels worth pursuing
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
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.

