using-startup-superpowers

Establishes shared file conventions and ground rules for startup validation workflows.

3.4k|487|Updated Jul 25, 2025
One-click install
npx skills add https://github.com/davepoon/buildwithclaude --skill using-startup-superpowers
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-startup-superpowers
Source: https://github.com/davepoon/buildwithclaude/tree/main/plugins/startup-superpowers/skills/using-startup-superpowers
Command: npx skills add https://github.com/davepoon/buildwithclaude --skill using-startup-superpowers

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Founders working on startup ideas across multiple conversations lose consistency in how project definitions, hypotheses, competitors, and research are stored and updated. This Skill provides the always-on context that keeps every startup-superpowers workflow operating against the same file conventions and safety rules.

Core Features & Use Cases

  • Shared File Conventions: Defines the structure of startup/core.md, startup/plan.md, hypothesis files, and competitor files so all related skills read and write consistently.
  • Voice Input Handling: Instructs the assistant to clarify garbled proper nouns from voice transcription rather than guessing competitor or product names.
  • Subagent Dispatch Rules: Specifies when to invoke the web-researcher subagent and how research summaries are saved to startup/research/.
  • Use Case: A founder starts a conversation about validating their startup idea. This Skill loads first, ensuring the assistant reads startup/core.md, proposes changes before writing, and routes research tasks to the correct subagent.

Quick Start

Load the startup-superpowers ground rules before we discuss my startup idea or run any validation workflow.

Frequently Asked Questions about using-startup-superpowers

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I keep startup idea notes consistent across AI conversations?

Use a shared conventions skill that defines a single source of truth like startup/core.md with YAML frontmatter and structured key-value fields. Every conversation reads that file first and proposes changes before writing, keeping the project definition consistent.

How should an AI assistant handle voice input with garbled names?

Voice transcription often mangles proper nouns like competitor names, URLs, and technical terms. The correct behavior is to ask the founder to clarify or spell the term rather than guessing and writing incorrect data into project files.

What file structure works for tracking startup hypotheses?

Store each hypothesis as a separate markdown file with YAML frontmatter containing a status field (untested, confirmed, invalidated), an H1 title stating the testable assumption, a type tag, and an optional notes section.

When should a startup assistant dispatch a research subagent?

Dispatch a research subagent when the task goes beyond a quick search, such as competitive landscape discovery, problem space validation, or market signals. Save the research output as dated markdown files so expensive research is preserved for future reference.

Does this skill send my startup data anywhere automatically?

No. The skill states there is no telemetry and nothing is sent automatically. The only external link is an optional, anonymous feedback form offered at specific milestones, and founders can opt out permanently.