IdeaForge

Intent

Run raw ideas through a structured R&D pipeline that clarifies the concept, expands it, scores it, and produces an MVP direction.

Workflow

1. Identify the exact task and available source material.
2. Apply the domain rules and output format in this skill.
3. State assumptions, uncertainty, and missing inputs clearly.
4. Return the requested artifact, recommendation, or review in a practical format.
5. Check the result against the validation checklist before finishing.

Constraints

• Do not fabricate missing facts, measurements, dates, sources, or user context.
• Keep output aligned with Mick's direct, practical communication style unless the skill says otherwise.
• Preserve safety, legal, medical, financial, and operational boundaries stated in this file.
• Prefer concise, usable output over broad explanation.

Validation Checklist

• The output matches the skill's intended task and platform.
• Required inputs, assumptions, and uncertainty are explicit.
• Safety, scope, and source limits are respected.
• The response follows the requested format or the skill's default output format.
• The result is practical enough to use without another cleanup pass.

Runs raw ideas through a five-stage R&D pipeline — capture, interpret, expand, score, output. Turns a rough thought into a structured invention plan with scoring, architecture suggestions, monetization paths, and a working MVP roadmap.

Trigger

Start any message with idea to activate immediately.

idea [raw idea, rough concept, or messy note]

Other triggers: ideaforge, analyze this idea, expand this concept, assess this invention, explore this thought, develop this further, evaluate feasibility

Delivery target modifiers:

• save to apple notes
• send to apple notes
• save this analysis to apple notes folder [folder name]
• save to obsidian
• send to obsidian
• save this analysis to obsidian ideas folder

Do Not Use When

• The user wants to capture a note without analysis — use a notes tool instead.
• The user wants a resume, blog post, or content piece — use the appropriate skill.
• The user is asking a general knowledge question — answer directly without running the pipeline.

If the user explicitly asks for the final analysis to be saved after the pipeline runs, keep using IdeaForge and treat persistence as a delivery step after Stage 5.

Modes

Default is Full Pipeline. Detect intent and run the smallest mode that fits.

Delivery targets:

• Default: return the analysis in chat only
• Apple Notes on macOS: after Stage 5, save the final analysis into the requested Apple Notes folder by running scripts/save_to_apple_notes.py when the runtime can access the local Notes app
• Apple Notes on iOS: prepare the final analysis for Apple Notes, then hand it off through an iOS Shortcut or share action because the skill runtime does not get direct Notes app write access on iOS
• Obsidian Ideas folder: after Stage 5, save the final analysis as a Markdown note in the Ideas folder of the user's Obsidian vault by running scripts/save_to_obsidian.py when the runtime can access the vault path or an Obsidian URL handoff

Stage 1 — Capture and Classify

Accept any input format: typed sentence, pasted notes, bullet list, voice note transcript, rough sketch in words.

Extract:

• Core problem — what problem is this solving, even if the user did not state it explicitly
• Proposed mechanism — what the idea does or how it works at a high level
• Idea type — classify using the type table below
• Domain — one or more industries or technology areas this touches

Idea type classification:

If the type is unclear, choose the closest fit and state the assumption in one line.

Stage 2 — Interpret

Assess the idea against these dimensions. Each feeds the scoring model in Stage 4.

Existence check Does this already exist in a recognizable form? If yes, name the closest known product or project. If a version exists but the idea adds meaningful differentiation, note the gap.

Technical feasibility Is this buildable with current technology? What are the hardest technical problems? What dependencies does it require (APIs, hardware, compute, data)?

Commercial viability Is there a realistic customer or buyer? What is the likely size of the market? Is this a painkiller (solves a real problem) or a vitamin (nice to have)?

Patent potential Does this involve a novel mechanism, process, or composition? Is the core concept likely already claimed? What is the strongest angle for IP protection if any exists?

Competition saturation How crowded is this space? Name direct competitors if known. A saturated space is not automatically a reason to abandon — execution and positioning matter.

Automation potential How much of this could be automated, scheduled, or made self-running? Higher automation potential means lower ongoing operational cost.

Privacy and security surface Does this touch personal data, credentials, financial data, health data, or live system access? Flag any significant risk area.

Stage 3 — Expand

Generate extensions, implications, and possibilities the user may not have considered. Cover all that apply:

Features and capabilities

• What is missing from the core idea that would make it meaningfully more useful?
• What edge cases does the current framing not handle?

Integration opportunities

• What existing systems, APIs, or platforms could this connect to?
• What would an n8n workflow look like that incorporates this?
• What Home Assistant, Proxmox, or other homelab integrations apply?

Business models

• SaaS subscription
• One-time purchase or license
• Usage-based pricing
• Open source with paid support or hosted version
• White-label licensing
• API access tier model
• Marketplace listing

AI opportunities

• Where could a Claude, OpenAI, or local LLM model make this smarter?
• Where could embeddings or semantic search add value?
• What prompt or agent architecture fits?

Automation paths

• What parts of this could run unattended on a schedule?
• What triggers (webhook, cron, sensor event) would power the automation?

Local-first alternative

• Can this run fully local without cloud dependencies? What would that require?

Monetization angles

• What is the fastest path to revenue?
• What would the first paying customer look like?
• What is the minimum viable commercial version?

Licensing and IP

• Could this be patented? What is the specific novel claim?
• Could this be licensed to a larger platform?
• Does this have open source potential that builds adoption before monetization?

Stage 4 — Score

Use scoring-model.md as the authoritative source for weights, scales, and formulas.

Score each metric from 0 to 10. Calculate the