Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Run Fabric AI patterns for text transformation, analysis, and content creation. Use when the user asks to use a Fabric pattern, extract wisdom, analyze claims, improve writing, summarize with Fabric, or mentions 'fabric' CLI. Supports 242+ patterns for tasks like content analysis, writing improvement, code review, threat modeling, and structured extraction.
Run Fabric AI patterns for text transformation, analysis, and content creation. Use when the user asks to use a Fabric pattern, extract wisdom, analyze claims, improve writing, summarize with Fabric, or mentions 'fabric' CLI. Supports 242+ patterns for tasks like content analysis, writing improvement, code review, threat modeling, and structured extraction.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Run Fabric AI patterns via the fabric-ai CLI. Each pattern is a reusable system prompt for a specific task. See references/popular-patterns.md for a curated list of high-quality patterns by category.
The command is fabric-ai, not fabric. First-time setup: run fabric-ai -S to configure API keys. If pattern list is empty: run fabric-ai -U to update patterns. Use -s (stream) for most calls to avoid long waits.
echo "input text" | fabric-ai -p <pattern>
echo "input text" | fabric-ai -p <pattern> -s
fabric-ai -y "https://youtube.com/watch?v=..." -p extract_wisdom -s
fabric-ai -u "https://example.com/article" -p summarize -s
echo "input" | fabric-ai -p <pattern> -m gpt-4o
echo "input" | fabric-ai -p <pattern> -g zh -s
echo "input" | fabric-ai -p extract_wisdom | fabric-ai -p summarize
echo "input" | fabric-ai -p <pattern> --strategy cot -s
echo "describe this image" | fabric-ai -p <pattern> -a /path/to/image.png -s
echo "input" | fabric-ai -p <pattern> -C my_context -s
echo "input" | fabric-ai -p <pattern> --session my_session -s
echo "input" | fabric-ai -p extract_wisdom -o output.md
echo "input" | fabric-ai -p extract_wisdom -c
fabric-ai -p <pattern> --dry-run
fabric-ai -l
Patterns can contain {{variable}} placeholders. Pass values with -v: # Single variable echo "input" | fabric-ai -p <pattern> -v="#role:expert" # Multiple variables echo "input" | fabric-ai -p <pattern> -v="#role:expert" -v="#points:30"
Create custom patterns at ~/.config/fabric/patterns/<name>/system.md. Each pattern directory contains a system.md file with the system prompt.
cat file.txt | fabric-ai -p <pattern> -s cat file1.md file2.md | fabric-ai -p <pattern> -s
Prefer -s (stream) for interactive use โ output appears incrementally. Chain patterns for multi-step processing (extract โ summarize โ translate). Use -g zh when the user wants Chinese output. Use -o file.md to save output, -c to copy to clipboard. Use --dry-run to inspect what will be sent before making API calls. Run fabric-ai -U periodically to get new community patterns.
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.