Validate Idea — Data skill for Claude Code
Cross-market idea validation (CN + EN markets) as a Claude Code skill.
How to install Validate Idea
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open w932635477-bit/validate-idea and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Validate Idea does
Cross-market idea validation (CN + EN markets) as a Claude Code skill. Real data · strict scoring · bilingual report. Zero LLM key.
Alternatives in Data
- Global Stock Data — US stock market data for AI coding assistants — zero-auth, official sources 1.5k ★
- Claude Deep Research Skill — Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credibility scoring, and au 1k ★
- Bug Bounty Master Workflow — Full pipeline: Recon -> Learn -> Hunt -> Validate -> Report 924 ★
README
[English](./README.md) | [中文](./README.zh-CN.md)
Cross-market idea validation for indie builders.
Real data from Chinese + English markets · strict scoring · bilingual report.
The killer angle
Most idea-validation tools look at **one** market. This one pulls real signals from **both** the Chinese and English markets at once, then tells you the uncomfortable truth: **your pain is probably already solved in the other market.** Real demand ≠ real opportunity.
Sample verdict — *cross-border payments tool*: Global **45/100**, China **61/100** → both red oceans → **don't build**. Three months of code, saved.
Install (Claude Code skill)
git clone https://github.com/w932635477-bit/validate-idea.git ~/.claude/skills/validate-idea
cd ~/.claude/skills/validate-idea && npm install # one-time
Then just describe your idea in Claude Code ("validate this idea: …") and the skill fires. **Zero LLM API key** — the Claude running the skill *is* the scorer.
How it works
flowchart LR
A["💬 one-line idea"] --> B["🔎 7 fetchers · CN+EN"]
B --> C["📊 raw data: search / community / competitor"]
C --> D["🧠 Claude scores · strict, no hallucination"]
D --> E["📄 bilingual report · local vs foreign · build?"]
This repo ships the **data layer** only: 7 fetchers covering search / community / competitor across both markets. Scoring and the bilingual report are produced by your Claude reading
Related Skills
Read Only Postgres
by jawwadfirdousi - Read-only PostgreSQL query skill for Claude Code. Executes SELECT/SHOW/EXPLAIN/WITH querie
SQL AI Agent
A text-to-SQL AI agent with a safety-first validation layer. Natural language questions become SQL, but a stri
Concilium Brainstorm
Run a Concilium BRAINSTORMING campaign — open-book cross-model idea brainstorminging with a live read-only cop
Pmf Discovery
Run W1 PMF Discovery. Analyses product-market fit across customer segments using event data, behavioural signa
Openclawby Skills
Official Clawby skills for AI agents — live market, on-chain & social data plus trade execution. One API key,
Openui Validate
Run the full validation pipeline and output a pass/fail checklist
Related Agents
Product Critic
Adversarial business validation of a product or feature idea BEFORE any build effort is committed. Use PROACTI
Question Forger
Generates evaluation questions with gold answers and gold evidence from real graph paths and from the syntheti
Sub Market
Internal subagent. Called by hormozi-orchestrator only. Executes market research, micro-niche scoring, pain ex