idea-os
Helps your agent turn a raw idea into a detailed execution plan. It creates documents like clarifying questions, deep research, a product plan, and an action plan with clear steps.
What it does
It's a system that turns a raw idea into a detailed plan for building a product. It asks questions to better understand the idea, researches the market, creates a product requirements document (PRD), and develops a phased execution plan.
When to use it
- ✓When you have a product idea or problem and want a structured plan.
- ✓When you say 'I have an idea for...' or 'Help me build X'.
- ✓When you need a guide to turn an idea into an action plan.
Example of what to ask your AI
“I have an idea for an app that helps people learn a new language. Can you help me plan it?”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
It works in five phases: first, it classifies the idea's complexity and your experience level. Then, it asks questions to clarify the idea. Next, it researches the market and competitors. Based on this, it creates a requirements document and finally, an execution plan with steps and success criteria.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add sickn33/agentic-awesome-skills --skill idea-osOr download just the file:
curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/idea-os/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
idea-os
An operating system for turning a raw idea into a build-ready plan. Takes a rough problem statement and produces four files: clarifying questions, deep research, a PRD, and a phased execution plan with platform/stack picks, a user-journey diagram, and kill criteria.
Overview
idea-os is a 5-phase sequential pipeline where each phase's output feeds the next — research shapes the PRD, PRD shapes the plan, plan's kill criteria tie back to research insights. Unlike single-command PRD generators, idea-os refuses to write a PRD until research is done, and refuses to write a plan until the PRD is stable. Depth and vocabulary adapt to a two-axis classification (complexity × builder sophistication) so a first-time builder isn't drowning in jargon and a founder gets full rigor.
Source: https://github.com/Slashworks-biz/idea-os — full skill, 11 reference files, 4 asset templates, and a 590-line worked example.
When to Use
- Use when a user shares a raw product idea or problem statement and wants a structured pipeline from clarifying questions through deep research, PRD, and a phased execution plan.
- Use when the user says "I have an idea for…", "help me build X", "validate and plan this concept", or "what should I build?" — and wants files they can take forward, not a one-shot answer.
- Use when a non-technical founder, PM, or hobbyist needs structure to bridge the gap between "idea" and "Monday morning's build queue".
- Do not use for quick sanity-check feedback on a half-formed idea (use
idea-refineinstead) or for editing an existing PRD (useproduct-managementinstead).
How It Works
Phase 1 — Triage
Classify the idea on two axes before anything else. Depth of research/PRD/plan and question count scale with complexity; vocabulary scales with sophistication.
- Idea tier (T1/T2/T3) — T1 = weekend utility, T2 = SaaS MVP or AI wrapper, T3 = marketplace / B2B SaaS / regulated.
- Sophistication (S1/S2/S3) — S1 = non-technical, no framework names; S2 = hobbyist, introduce frameworks with definitions; S3 = founder/senior PM, full vocabulary.
State the classification in one line (e.g. "T2 · S2 — moderate SaaS, builder has shipped before") before proceeding.
Phase 2 — Clarify
Write questions.md with 4–18 questions (count scales with complexity), grouped: Who and Pain · Scope and Wedge · Constraints and Goals. Every question must be actionable — the answer has to change what you build. Generic questions are rejected.
After writing, stop and wait for answers. Do not proceed to research until answered or autonomous-mode assumptions are declared.
Phase 3 — Research
Write research.md using WebSearch + WebFetch. Minimum: 5 WebSearches, 2 WebFetches on named competitors, 1 source per TAM number, date on every source. Anything unsourced gets flagged [assumption].
Required sections: problem validation, JTBD, market (TAM/SAM/SOM top-down + bottom-up), competitors (direct/indirect/substitutes + positioning map), SWOT, distribution (first-100-users channel fit), risks, and 3–7 non-obvious insights.
Phase 4 — PRD
Write PRD.md with: falsifiable problem statement, named personas, ranked JTBD, non-goals (mandatory — it's where bad PRDs die), leading and lagging metrics.
Phase 5 — Plan
Write plan.md with: user journey (text + mermaid), platform recommendation tied to research findings, stack in conservative/modern/cutting-edge matrix, phased build (MVP → v1 → target) with kill criteria per phase and first-100-users distribution per phase, metrics per phase, and 3–5 immediate next actions.
Limitations
- Requires user input between phases for best results; if answers are missing, outputs depend on explicit assumptions.
- Produces planning artifacts (
questions.md,research.md,PRD.md,plan.md) but does not execute build or deployment work. - Source quality determines output quality; weak or outdated references can reduce recommendation accuracy.
- Better suited to new-idea validation and early planning than late-stage optimization of an existing shipped product.
Examples
Example 1: Non-technical founder with a consumer-app idea
User: "I want to build a habit tracker for people with ADHD."
…
FAQ
What are 'non-goals'?
These are things the product will NOT do. Defining them helps maintain focus and prevents the project from getting out of hand.
What is a PRD?
PRD stands for Product Requirements Document. It's a document that describes what the product should do, for whom, and why.
What are 'kill criteria'?
These are defined criteria to decide if a project or a phase of it should be stopped. They help avoid wasting time and resources on something that isn't working.
Details
Original description by the author
Five-phase pipeline (triage → clarify → research → PRD → plan) that turns a raw idea into four linked files: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased execution plan with mermaid user journey and kill criteria.
Popularity
- GitHub stars
- 48k
- Ranking position
- #3311
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
00-andruia-consultant
Helps your agent start or improve AI projects. It analyzes code, suggests tools, and creates action plans in Spanish.
sickn33/agentic-awesome-skills
007
Lets your agent perform security audits and threat modeling. It's useful for protecting projects against attacks and vulnerabilities.
sickn33/agentic-awesome-skills
10-andruia-skill-smith
Helps your agent create or improve AI tools. It defines how tools work, writes documentation, and validates the structure.
sickn33/agentic-awesome-skills
20-andruia-niche-intelligence
Lets your agent create a summary about a specific industry. It's useful for understanding the context, rules, usage patterns, and risks of a project, using reliable sources.
sickn33/agentic-awesome-skills
Similar skills
intent-driven-development
Helps your agent turn ideas into clear, testable plans. Defines criteria to ensure changes are made correctly and safely.
affaan-m/ECC
product-capability
Guides your agent in turning product ideas into clear plans. It defines what needs to be done, the limits, and decisions before development.
affaan-m/ECC
article-writing
Writes long-form content like articles, guides, and blog posts with a unique style. It's useful when you need well-written texts with a consistent voice and credibility.
affaan-m/ECC