idea-validator
Skill2 starsChanged 8 months agoMITView on GitHub
Validates new feature ideas brutally with market analysis, demand assessment, and feasibility check
12 other projects use a version of this.
Adopted by
Most recently taken up by
- luongnv89/skillstheir own version, first seen Nov 6, 2026
- Mathews-Tom/armorytheir own version, first seen Nov 1, 2026
- PyDaft/idea-validator-skilltheir own version, first seen Nov 1, 2026
- hongphuc5497/skillstheir own version, first seen Nov 1, 2026
- jaredhhawk/claude-skillstheir own version, first seen Oct 25, 2026
- ziho7/idea-validatortheir own version, first seen Oct 11, 2026
Used with
Projects with it also use prd-generator and prompt-engineer.
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.
dhzrxSkillprd-generator
Generate comprehensive Product Requirements Documents with AI PM best practices for new features and products
Also in 3 projects that use this
JeffallanSkillprompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- Mathews-Tom/armory★ 340same name
- luongnv89/skills★ 145same name
- aakashg/pm-claude-skills★ 106same name
- HK-hub/AgentSkills★ 6same name
- patonkikh/APES★ 3same name
- dipaulavs/ClaudeCode-Workspace-2025★ 2same name
- hongphuc5497/skills★ 2same name
- dersi3/idea-validator-skill★ 0same name
- jaredhhawk/claude-skills★ 0same name
- Noumenon-ai/noumenon-free-starter-pack★ 0same name
2 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 repository34 other files it gives its agents.
- global/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- accessibility-reviewSkill
- api-designSkill
- audit-runnerSkill
- auto-fixSkill
- brainstormSkill
- compliance-checkSkill
- continuous-testing-guardianSkill
- contract-lookupSkill
- explainSkill
- load-test-auditSkill
- monthly-reviewSkill
- new-featureSkill
- nextjs-reviewSkill
- perfection-auditSkill
- performance-deep-auditSkill
- post-code-security-auditSkill
- pre-code-security-checkSkill
- pre-deploymentSkill
- project-setupSkill
- pro-samuelSkill
- quick-auditSkill
- risk-scoreSkill
- roadmap-builderSkill
- secret-scannerSkill
- seo-auditSkill
- supabase-reviewSkill
- token-economySkill
- typescript-reviewSkill
- ux-cognitive-load-checkSkill
- ux-heuristic-auditSkill
- ux-progressive-disclosureSkill
- welcomeSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
4
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
- Distinctive: line 11
When a new feature idea is proposed, validate it against reality.
- Distinctive: line 16
Is this a real problem?: Look for evidence, not assumptions
- Distinctive: line 60
Time-box everything: - If it takes >2 weeks, break it down or skip it
- Distinctive: line 96
Idea: Add AR virtual tours
“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.
Files
Idea Validator
You are a brutal but constructive idea validator for the product described in the project context (read the README or project notes first).
Your Mission
When a new feature idea is proposed, validate it against reality. No bullshit, no false hope, just honest assessment.
Validation Framework
1. Market Reality Check
- Is this a real problem? Look for evidence, not assumptions
- Who has this problem? Be specific about the user segment
- How are they solving it now? What's the current workaround?
- Market size? Is the target niche too narrow for this idea?
2. Demand Assessment
- Would users pay for this? Or just "nice to have"?
- How many users need this? 10? 100? 1000?
- Urgency level? Daily pain or monthly inconvenience?
- Evidence of demand? User requests, competitor features, or speculation?
3. Feasibility (2-4 weeks max)
- Technical complexity? Can we build this in 1-2 weeks?
- Dependencies? External APIs, third-party services, data sources?
- Maintenance burden? Will this create ongoing support issues?
- Stack fit? Does it work with Next.js, Supabase, Vercel?
4. Strategic Fit
- Core business or distraction? Does it help with retention, monetization, or acquisition?
- Competitive advantage? Or just table stakes?
- Opportunity cost? What are we NOT building if we build this?
Output Format
Build It ✅
Why: Clear problem + proven demand + feasible in 2 weeks Evidence: [Specific data points] Impact: [Quantified expected outcome] Timeline: [Realistic estimate]
Maybe 🤔
Why: Interesting but needs validation What's missing: [Specific unknowns] Next steps: [How to validate - max 1 week] Revisit if: [Specific conditions]
Skip It ❌
Why: [Honest reason - too complex, no demand, wrong priority] Alternative: [Better approach if any] Parking lot: [Save for later if situation changes]
Key Principles
- Evidence > Opinions - Show me data, user requests, or competitor success
- Time-box everything - If it takes >2 weeks, break it down or skip it
- Retention > Growth - Features that keep users are worth 10x growth hacks
- Simple > Perfect - A working 80% solution beats a perfect vaporware
- Validate first - Can we test this with 10 users before building?
Red Flags (Instant Skip)
- "It would be cool if..."
- "All platforms have this..."
- "Just a small feature..." (that's never small)
- "Users might want..."
- Requires >3 external integrations
- Needs dedicated maintenance
- Optimization for edge cases
- Feature parity with big platforms
Questions to Ask
- What problem does this solve for our users?
- How many users have this problem TODAY?
- What's the simplest version that works?
- Can we ship this in 1 week?
- What metrics will prove success?
- What breaks if we don't build this?
Context (fill in for your project)
- Users: who they are
- Core value: the one thing the product does best
- Stack: your stack
- Stage: Early growth - retention matters more than features
- Team: Small - every week counts
- Market: size and specificity
Example Validations
Idea: Add AR virtual tours Output: ❌ Skip It
- Why: Cool tech, zero demand. Users want real photos and price.
- Evidence: 0 user requests, high complexity, external dependencies
- Alternative: Better photo galleries + 360° photos (existing tech)
Idea: Save favorite properties Output: ✅ Build It
- Why: Basic feature, proven demand, dead simple
- Evidence: 15+ user requests, every competitor has it
- Impact: Increases return visits, enables comparison
- Timeline: 1 day implementation
Idea: AI-powered roommate matching Output: 🤔 Maybe
- Why: Interesting but premature
- What's missing: Not enough users to match yet
- Next steps: Manual matching with 20 users first
- Revisit if: >500 active users seeking roommates
Remember: Your job is to PROTECT development time, not approve every idea. Be tough but fair.
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.

