fabric-ai
Guides pattern selection through decomposition, exploration, and diverse approach generation
When & Why to Use This Skill
Fabric Orchestrator is a powerful Claude skill designed to streamline complex problem-solving by leveraging an extensive library of over 200 specialized patterns and strategies. It acts as an intelligent layer that decomposes challenges, explores diverse creative angles, and generates multiple deeply reasoned approaches. By orchestrating workflows across analysis, writing, and development, it ensures users can select and execute the most effective AI-driven solutions for any given task.
Use Cases
- Complex Problem Decomposition: Break down multifaceted technical or business challenges into granular components and generate 5-7 distinct strategic approaches with detailed trade-off analysis.
- Automated Content Intelligence: Extract insights, 'wisdom', and structured data from diverse sources including YouTube transcripts, web URLs, and audio/video files using specialized extraction patterns.
- Cross-Domain Creative Brainstorming: Combine patterns from different disciplines—such as security, writing, and business—to generate innovative solutions and unexpected perspectives for project planning.
- Standardized Workflow Pipelines: Build repeatable AI sequences for tasks like code reviews, document processing, and meeting summarization by chaining specific patterns and strategies with session management.
| name | fabric-ai |
|---|---|
| description | Guides pattern selection through decomposition, exploration, and diverse approach generation |
Fabric Orchestrator
--ultrathink --seq
Core Mission
Explore patterns creatively → Generate 5-7+ deeply reasoned approaches per challenge
Resources: references/pattern_descriptions.json (228 patterns), references/strategies.json (9 strategies)
Workflow
- Analyze (--ultrathink --seq): Components, goals, dimensions, creative angles
- Ask (AskUserQuestion): Objective, constraints, creativity level, expansion ideas
- Consult: Read JSONs
- Generate: 5-7+ approaches (unique angle, patterns, strategy, WHY, commands, trade-offs)
- Present → Execute → Iterate
Pattern Discovery
- Read Resoureces
- Explore MULTIPLE tag categories (ANALYSIS:97, WRITING:63, DEVELOPMENT:44, EXTRACT:39, BUSINESS:34, SECURITY:30, others)
- Consider unexpected combinations
- Think across dimensions
Content Types
| Type | Flags |
|---|---|
| YouTube | -y <url> --transcript |
| Web | -u <url> |
| Audio/Video | --transcribe-file <path> |
Always add: --stream (long), --session (multi-step), -c (clipboard), -o (save), --strategy
Pipelines
fabric <input> -p <pattern> --session <name>
fabric -p <pattern> --strategy <strat> --session <name> -c
Quality Checklist
- Read both JSONs
- Explored MULTIPLE tags
- Generated 5-7+ approaches
- Deep WHY reasoning
- Varied all dimensions
- Used --session for pipelines
Commands
fabric -y <url> -p extract_wisdom --strategy cot --stream
fabric --listpatterns / --liststrategies / --listmodels