Idea generator

Skill hamza-ali-shahjahan/hamzaish/_archive/v0/agents/idea/idea-generator

Your Claude Code setup that builds, launches, and learns — across the whole product lifecycle. Point Claude Code at this and it runs your whole startup factory — and gets smarter every session. Works with Cursor, Codex & Windsurf too.

Install

npx -y skills add hamza-ali-shahjahan/hamzaish --skill idea-generator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate startup ideas grounded in Hamza's existing patterns, current trends, and validated demand signals. Never just brainstorms — pulls from real signals.

SKILL.md

2.0 KB, as published. Nobody here has run it

Idea Generator

When you activate

User asks: "give me ideas", "what should I build?", "ideate around X", "spin up some concepts for Y vertical"

What you produce

A ranked list of 5–10 startup ideas in this exact format per idea:

## Idea N: <short name>
**One-liner:** <one sentence>
**Who feels the pain:** <specific persona>
**Frequency × severity:** <weekly | daily | hourly> × <annoying | costly | blocking>
**Why now:** <a 2026 enabling trend>
**Validation move:** <the cheapest test you'd run first>
**Why this fits Hamza:** <pattern from his existing products>
**Kill criteria:** <what would make us drop this fast>
**Estimated $100K-ARR plausibility:** <low | medium | high> + 1-line reasoning

Protocol

Read products/*/product.config.json to understand Hamza's existing portfolio patterns (what verticals, what users, what monetization).
Read knowledge-base/founders-wisdom/100k-arr-tactics.md and knowledge-base/idea-stage/problem-statement-rubric.md.
Ask the user (one question, not five): "Constraint: any vertical, audience, or theme to focus on? Or fully open?"
Generate the list. Rank by Estimated $100K-ARR plausibility × Why-Hamza-fit.
End with one direct recommendation: "If I had to pick one to validate this week, it's #N because <reason>."

Sources

knowledge-base/idea-stage/problem-statement-rubric.md
knowledge-base/idea-stage/jobs-to-be-done.md
knowledge-base/founders-wisdom/100k-arr-tactics.md
knowledge-base/founders-wisdom/paul-graham-essays.md (Schlep Blindness, How to Get Startup Ideas)

What you don't do

Don't brainstorm in a vacuum. Always anchor on a trend, a pain, or a Hamza pattern.
Don't propose ideas with TAM > $1B unless asked — we're building $100K-ARR units.
Don't romanticize. Each idea gets a kill-criterion.