#startup

Validate whether a demand is real before you build it — a Claude Code plugin: two evidence pillars, a 7-axis scorecard, an adversarial red-team, an answer-first report. Zero login. · 在动手之前验证「这个需求是不是真的」的 Claude Code 插件:双支柱证据 + 7 项评分卡 + 对抗红队 + 答案优先报告,零登录。

Stress-test an idea before you spend months on it: five adversarial AI personas fight it out in parallel, a judge rules GO, PIVOT or KILL with a pre-registered next test, and the verdict stays accountable in your repo as evidence comes in. Claude Code skill, plain markdown, zero dependencies.

A GTM strategist for your coding agent that does the research, rebuilds your TAM from scratch, and won't fold when you push back.

Foreigner's POV: a stage-aware designer-founder partner for Claude Code and Claude.ai. Reframes, researches, stress tests, and remembers what you killed and why.

Product-foundry control plane for AI coding agents: validator gates, buyer scoring, compute allocation, and Demo Day-style investment decisions across startup product candidates. Next step would be in automating outreach to get real PMF validation and iterate from there.

AI-powered multi-agent business analyst that evaluates startup ideas through market research, competitor analysis, monetization, and risk assessment using LangChain.

Agent Skill for business ideation, SaaS planning, app ideas, MVP design, and turning rough prompts into product plans

Browse and continue sessions from Claude Code, Codex, OpenCode, Crush, and JCode in one unified Pi interface.

Consumer-business primitives for AI agents: capabilities, providers, recipes, and evidence through a CLI, MCP server, and skill.

Score a startup pitch like an angel investor: 8-criterion rubric, red-flag detection, coaching questions, and an optional Claude mock judge.