ideate
A structured idea validation engine that uses adversarial gating and 8-dimension scoring to scope your next MVP.
Free
Works with the AI Agents you already use
ideate
Example session with this skill installed
/ideate I want to build a CLI tool that automatically generates READMEs for Python projects using AST analysis. Is this a good idea? My goal is OSS and I'm solo.
- Read your context and instructions
- Compiled the ideate
I have initialized the validation sequence for the project slug python-ast-readme-gen. Based on your OSS goal and solo constraints, I have analyzed the market landscape and technical feasibility.
Validation Verdict: NARROW
| Dimension | Score | Notes |
|---|---|---|
| Market Demand | 7/10 | High interest in automated documentation for active repos. |
| Technical Risk | 4/10 | AST parsing is stable; logic is well-defined. |
| Time to Value | 8/10 | Can ship a core parser in <2 weeks. |
| Competitive Gap | 5/10 | Several incumbents exist; differentiation needed on AST accuracy. |
| Solo-ability | 9/10 | Perfect scope for a single developer. |
Adversarial Gate: Why this might fail
- Maintenance Overhead: High churn in Python syntax versions (e.g., new 3.12+ features) may break the AST logic.
Generic Competition: LLM-based chat agents already generate READMEs, reducing the need for specialized CLI tools.
3. Edge Case Fragility: Complex metaprogramming or dynamic imports might result in incomplete documentation.
Summary
The idea is strong for an OSS project due to high solo-ability and clear utility. However, to succeed, you must focus on the "AST-native" accuracy that generic LLMs lack. The adversarial gate suggests focusing on a specific niche, such as Type-Hint enforcement in documentation, to widen the competitive gap.
Next steps
- Review the full report in
ideate/python-ast-readme-gen/validation.md. - Run
/ideate competeto analyze how this compares topydocandsphinx. - Proceed to
/ideate scopeonce the competitive gaps are addressed.
Connects securely to your tools. The creator never sees your data.
About this skill
Building products based on a hunch often leads to wasted engineering hours. This skill provides a structured engine to move from a blank page to an evidence-backed verdict and a scoped MVP.
What it does
- Idea validation runs specific concepts against 8-dimension scoring anchors to determine viability.
- Competitive landscape identifies direct competitors and finds market gaps for differentiation.
- Comparison engine evaluates multiple ideas side-by-side using weighted goal variants.
- MVP scoping generates a lean build plan but only after the idea passes an adversarial gate.
- Multi-session discovery tracks progress in local directories to resume validation stages later.
How it works
- Intake uses specific widgets to capture your goal type, constraints, and target users without unnecessary chatter.
- Capability detection checks for search tools to toggle between online evidence gathering and offline logic.
- Scoring applies dimension weights based on your profile (Commercial, OSS, Research, or Learning).
- Adversarial gating forces a mandatory analysis of the top-3 failure reasons before any positive verdict.
Frameworks & tools
This skill is designed for agents with file system access and web search capabilities. It uses a modular load order for specific logic files and outputs structured Markdown documentation to an ideate/ directory.
Why this beats prompting it yourself
Generic prompts often suffer from confirmation bias and lack rigorous scoring criteria. This skill enforces an adversarial gate that blocks positive verdicts until the case against the idea is thoroughly debunked.
Use cases
- Validate a new SaaS concept before writing a single line of code.
- Compare three different side project ideas to see which fits a 2-week "Lean" constraint.
- Map out the competitive landscape for a niche internal tool.
- Generate a scoped MVP plan for a validated startup idea.
Known limitations
Verification is subject to the availability of search tools for real-world evidence. Scoping is gated behind a positive validation verdict in the local directory.
Online mode requires active search/fetch tools. MVP scoping is blocked until an idea passes the adversarial gate. Slugs are limited to 40 characters.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 13 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts
File Scopes