Skip to content
Agent use cases

7-step AI startup agent skill collection for solo founders

A packaged collection of 7 agent skills covering idea validation, business plan writing, policy checking, pitching, customer acquisition, pricing, and registration, complete with a master entry point. It automatically evaluates your current startup progress and invokes the corresponding sub-skill, enabling solo founders to connect every output step without guesswork.

GitHubhuaxialucaicaizi616GitHub stars
CodexClaude CodeCursor

Added 2026-10-31 · originally published 2026-10-31


Steps

  1. 1Clone the repository locally and copy the sub-skills and master entry point from skills/ to your corresponding user skills directory based on the tool you use (such as ~/.agents/skills for Codex or ~/.claude/skills for Claude Code).
  2. 2Send a prompt to the AI explaining what product you are building and your current progress, allowing the master entry point skill to help determine your startup stage.
  3. 3Based on the AI's assessment, follow the default sequence for new founders (Validation → Business Plan → Policy/Registration → Pitching → Customer Acquisition → Pricing) or directly specify a sub-skill to execute.
  4. 4Once the previous step is complete, pass the resulting output to the next step, and proceed using the official reference links and rules provided by the sub-skill.

Ideas for Chinese platforms

The opc-growth-playbook can be directly applied to cold-start customer acquisition on Xiaohongshu, Douyin, and Video Channels, helping solo founders plan operations and growth strategies for Chinese platforms.

Copy-ready prompt
Use ai-startup-skills to help me figure out what startup stage I am in and what I should do next: [Enter your product details and current progress here]
#AI Startup#Agent Skill#Solo Founder#Product Validation
RoadmapAI: Automatically turning user feedback into product roadmaps

Deploy RoadmapAI agents on Discord, Slack, and GitHub to automatically convert every user feature request and bug report into a prioritized product roadmap, integrating with development tools via MCP.

Run multiple AI agents in parallel using the open-source tool T3 Code

Using T3 Code, an open-source tool by Theo, you can run multiple agents like Claude Code, Codex, and Cursor simultaneously within a single interface, using your existing accounts without new subscriptions. It supports multi-machine sync, project organization, visual diffs, and parallel sessions.

Reuse 10 GitHub repositories to quickly set up a Claude Code workflow

Curated 10 GitHub repositories covering best practices, skill libraries, toolkits, and rules to help users skip the zero-to-one setup phase and directly copy guides, agents, hooks, and rules for immediate use.

Found this useful? Get daily updates on Telegram or X.

Summarized by AI from the original source - refer to the original post for details. Copyright belongs to the original author.

nebu.lifeNebula AI Playbook · Daily AI use cases, prompts and prices

Content is collected daily from public sources and summarized with AI. Every entry links to the original, and copyright stays with the original authors. Spotted an error or a rights issue? Let us know via the contact page.

Last updated 2026-11-02 12:11 (Beijing time)