idea-generation

Holo00's avatarfrom Holo00

Work with IdeaForge's AI idea generation system. Triggers: generation flow, AI prompts, scoring system, duplicate detection, real-time logs, generation debugging. Pipeline: API → PromptBuilder → AI → Parse → Dedupe → Save.

⭐0stars🔀0forks📁View on GitHub🕐Updated Nov 28, 2025
[Market Research]

When & Why to Use This Skill

The IdeaForge skill is a comprehensive AI-driven idea generation system designed to streamline the creative process from initial prompt to validated concept. By leveraging advanced LLMs like Claude and Gemini, it automates the discovery of business opportunities through structured frameworks, semantic duplicate detection, and a weighted scoring mechanism, ensuring high-quality and unique outputs for product teams and entrepreneurs.

Use Cases

  • Product Innovation: Automatically generate and score new product ideas within specific domains like Healthcare or Fintech using the 'pain-point' framework to identify market gaps.
  • Strategic Brainstorming: Utilize the PromptBuilder and AI pipeline to create detailed elevator pitches and solution descriptions for internal innovation labs and R&D departments.
  • Market Validation: Evaluate the severity of problems and the effectiveness of solutions using the built-in weighted scoring system and semantic similarity checks to avoid redundant concepts.
  • Workflow Automation: Integrate the SSE-enabled logging and API-driven pipeline into existing developer tools for real-time monitoring and debugging of AI-generated insights.
nameidea-generation
descriptionWork with IdeaForge's AI idea generation system. Triggers: generation flow, AI prompts, scoring system, duplicate detection, real-time logs, generation debugging. Pipeline: API → PromptBuilder → AI → Parse → Dedupe → Save.

Idea Generation

Pipeline

POST /api/generation/generate
  → IdeaGenerationService
    → PromptBuilder (YAML configs)
    → callAI() (Claude/Gemini)
    → parseAIResponse()
    → EmbeddingService (duplicate check)
    → IdeaRepository (save)
    → GenerationLogger (SSE logs)

API

POST /api/generation/generate
{
  "framework": "pain-point",  // optional, random if not specified
  "domain": "Healthcare",      // optional
  "sessionId": "uuid"          // for log tracking
}

AI Response Shape

{
  "name": "Idea Name (max 60 chars)",
  "domain": "Domain → Subdomain",
  "problem": "...",
  "solution": "...",
  "quickSummary": "Elevator pitch",
  "concreteExample": {
    "currentState": "How users handle this today",
    "yourSolution": "How they'd use your product",
    "keyImprovement": "Quantifiable improvement"
  },
  "evaluation": {
    "problemSeverity": { "score": 8, "reasoning": "..." }
  },
  "tags": ["tag1", "tag2"]
}

Scoring

  • Per-criterion: 1-10 scale
  • Weighted total: 0-100 scale
  • Config: evaluation-criteria.yaml

Duplicate Detection

  1. Exact: Same domain + problem + solution
  2. Semantic: Embedding similarity > 85%

SSE Logs

Stages: INIT → CONFIG_LOAD → PROMPT_BUILD → API_CALL → RESPONSE_PARSE → DUPLICATE_CHECK → DB_SAVE → COMPLETE

Endpoint: GET /api/logs/stream/{sessionId}

Key Files

File Purpose
services/ideaGenerationService.ts Orchestration
services/promptBuilder.ts AI prompts
services/configService.ts YAML configs
lib/aiProvider.ts Claude/Gemini