What does the Fabric AI skill do?

Intelligent pattern selection for Fabric CLI. Automatically selects the right pattern from 242+ specialized prompts based on your intent - threat modeling, analysis, summarization, content creation, extraction, and more. USE WHEN processing content, analyzing data, creating summaries, threat modeling, or transforming text.

Why use Fabric on TypingMind?

Because you install it once and use it with any model. Fabric is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Fabric in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ynulihao/AgentSkillOS/tree/main/data/skill_seeds/fabric. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Fabric?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Fabric?

As many as you like. As long as a model supports skills, you can use Fabric with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Fabric AI skill free?

It is published on GitHub by ynulihao. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Fabric by ynulihao — AI Skill for Any LLM

Fabric Skill

Setup Check - Fabric Repository

IMPORTANT: Before using this skill, verify the Fabric repository is available:

bash
# Check if Fabric repo exists
if [ ! -d "$HOME/.claude/skills/fabric/fabric-repo" ]; then
  echo "Fabric repository not found. Cloning..."
  cd "$HOME/.claude/skills/fabric"
  git clone https://github.com/danielmiessler/fabric.git fabric-repo
  echo "Fabric repository cloned successfully."
else
  echo "Fabric repository found at $HOME/.claude/skills/fabric/fabric-repo"
fi

If the repo doesn't exist, clone it immediately before proceeding with any pattern selection.

When to Activate This Skill

Primary Use Cases:

"Create a threat model for..."
"Summarize this article/video/paper..."
"Extract wisdom/insights from..."
"Analyze this [code/malware/claims/debate]..."
"Improve my writing/code/prompt..."
"Create a [visualization/summary/report]..."
"Rate/review/judge this content..."

The Goal: Select the RIGHT pattern from 242+ available patterns based on what you're trying to accomplish.

🎯 Pattern Selection Strategy

When a user requests Fabric processing, follow this decision tree:

1. Identify Intent Category

Threat Modeling & Security:

Threat model → create_threat_model or create_stride_threat_model
Threat scenarios → create_threat_scenarios
Security update → create_security_update
Security rules → create_sigma_rules, write_nuclei_template_rule, write_semgrep_rule
Threat analysis → analyze_threat_report, analyze_threat_report_trends

Summarization:

General summary → summarize
5-sentence summary → create_5_sentence_summary
Micro summary → create_micro_summary or summarize_micro
Meeting → summarize_meeting
Paper/research → summarize_paper
Video/YouTube → youtube_summary
Newsletter → summarize_newsletter
Code changes → summarize_git_changes or summarize_git_diff

Wisdom Extraction:

General wisdom → extract_wisdom
Article wisdom → extract_article_wisdom
Book ideas → extract_book_ideas
Insights → extract_insights or extract_insights_dm
Main idea → extract_main_idea
Recommendations → extract_recommendations
Controversial ideas → extract_controversial_ideas

Analysis:

Malware → analyze_malware
Code → analyze_code or review_code
Claims → analyze_claims
Debate → analyze_debate
Logs → analyze_logs
Paper → analyze_paper
Threat report → analyze_threat_report
Product feedback → analyze_product_feedback
Sales call → analyze_sales_call

Content Creation:

PRD → create_prd
Design document → create_design_document
User story → create_user_story
Visualization → create_visualization, create_mermaid_visualization, create_markmap_visualization
Essay → write_essay
Report finding → create_report_finding
Newsletter entry → create_newsletter_entry

Improvement:

Writing → improve_writing
Academic writing → improve_academic_writing
Prompt → improve_prompt
Report finding → improve_report_finding
Code → review_code

Rating/Evaluation:

AI response → rate_ai_response
Content quality → rate_content
Value assessment → rate_value
General judgment → judge_output

2. Execute Pattern

bash
# Basic format
fabric [input] -p [selected_pattern]

# From URL
fabric -u "URL" -p [pattern]

# From YouTube
fabric -y "YOUTUBE_URL" -p [pattern]

# From file
cat file.txt | fabric -p [pattern]

# Direct text
fabric "your text here" -p [pattern]

📚 Pattern Categories (242 Total)

Threat Modeling & Security (15 patterns)

create_threat_model - General threat modeling
create_stride_threat_model - STRIDE methodology
create_threat_scenarios - Threat scenario generation
create_security_update - Security update documentation
create_sigma_rules - SIGMA detection rules
write_nuclei_template_rule - Nuclei scanner templates
write_semgrep_rule - Semgrep static analysis rules
analyze_threat_report - Threat report analysis
analyze_threat_report_cmds - Extract commands from threat reports
analyze_threat_report_trends - Identify threat trends
t_threat_model_plans - Threat model for plans
ask_secure_by_design_questions - Secure by design questions
create_network_threat_landscape - Network threat landscape
analyze_incident - Incident analysis
analyze_risk - Risk analysis

Summarization (20 patterns)

summarize - General summarization
create_5_sentence_summary - Ultra-concise 5-line summary
create_micro_summary - Micro summary
create_summary - Detailed summary
summarize_micro - Micro summarization
summarize_meeting - Meeting notes summary
summarize_paper - Academic paper summary
summarize_lecture - Lecture summary
summarize_newsletter - Newsletter summary
summarize_debate - Debate summary
summarize_legislation - Legislation summary
summarize_rpg_session - RPG session summary
summarize_board_meeting - Board meeting summary
summarize_git_changes - Git changes summary
summarize_git_diff - Git diff summary
summarize_pull-requests - PR summary
summarize_prompt - Prompt summary
youtube_summary - YouTube video summary
create_ul_summary - Unsupervised Learning summary
create_cyber_summary - Cybersecurity summary

Extraction (30+ patterns)

extract_wisdom - General wisdom extraction
extract_article_wisdom - Article-specific wisdom
extract_book_ideas - Book ideas
extract_insights - General insights
extract_insights_dm - Daniel Miessler style insights
extract_main_idea - Core message
extract_recommendations - Recommendations
extract_ideas - Ideas from content
extract_questions - Questions raised
extract_predictions - Predictions made
extract_controversial_ideas - Controversial points
extract_business_ideas - Business opportunities
extract_skills - Skills mentioned
extract_patterns - Patterns identified
extract_sponsors - Sponsor mentions
extract_references - References cited
extract_instructions - Instructions from content
extract_jokes - Humor extraction
extract_primary_problem - Main problem
extract_primary_solution - Main solution
extract_product_features - Product features
extract_core_message - Core message
extract_algorithm_update_recommendations - Algorithm recommendations
extract_extraordinary_claims - Extraordinary claims
extract_most_redeeming_thing - Most valuable aspect

Analysis (35+ patterns)

analyze_claims - Claim analysis
analyze_malware - Malware analysis
analyze_code - Code analysis
analyze_paper - Paper analysis
analyze_logs - Log analysis
analyze_debate - Debate analysis
analyze_incident - Incident analysis
analyze_comments - Comment analysis
analyze_answers - Answer analysis
analyze_email_headers - Email header analysis
analyze_military_strategy - Military strategy
analyze_mistakes - Mistake analysis
analyze_personality - Personality analysis
analyze_presentation - Presentation analysis
analyze_product_feedback - Product feedback
analyze_proposition - Proposition analysis
analyze_prose - Prose analysis
analyze_risk - Risk analysis
analyze_sales_call - Sales call analysis
analyze_spiritual_text - Spiritual text analysis
analyze_tech_impact - Tech impact analysis
analyze_threat_report - Threat report analysis
analyze_bill - Legislation analysis
analyze_candidates - Candidate analysis
analyze_cfp_submission - CFP submission analysis
analyze_terraform_plan - Terraform plan analysis
analyze_interviewer_techniques - Interviewer technique analysis

Creation (50+ patterns)

create_prd - Product Requirements Document
create_design_document - Design documentation
create_user_story - User stories
create_coding_project - Coding project
create_coding_feature - Code features
create_mermaid_visualization - Mermaid diagrams
create_markmap_visualization - Markmap mindmaps
create_visualization - General visualizations
create_threat_model - Threat models
create_stride_threat_model - STRIDE threat models
create_threat_scenarios - Threat scenarios
create_report_finding - Report findings
create_newsletter_entry - Newsletter content
create_keynote - Keynote presentations
create_academic_paper - Academic papers
create_flash_cards - Study flashcards
create_quiz - Quizzes
create_graph_from_input - Graphs
create_tags - Content tags
create_art_prompt - Art generation prompts
create_command - CLI commands
create_pattern - Fabric patterns
create_logo - Logo designs
create_podcast_image - Podcast imagery
create_sigma_rules - SIGMA rules
create_video_chapters - Video chapters
create_upgrade_pack - Upgrade documentation

Improvement (10 patterns)

improve_writing - General writing improvement
improve_academic_writing - Academic writing
improve_prompt - Prompt engineering
improve_report_finding - Report findings
review_code - Code review
review_design - Design review
refine_design_document - Design refinement
humanize - Humanize AI text
enrich_blog_post - Blog enhancement
clean_text - Text cleanup

Rating/Judgment (8 patterns)

rate_ai_response - Rate AI outputs
rate_ai_result - Rate AI results
rate_content - Rate content quality
rate_value - Rate value proposition
judge_output - General judgment
label_and_rate - Label and rate
check_agreement - Agreement checking
arbiter-evaluate-quality - Quality evaluation

🔄 Updating Patterns

The Fabric repository is included in this skill at ${PAI_DIR}/skills/fabric/fabric-repo/.

To update patterns:

bash
cd ${PAI_DIR}/skills/fabric/fabric-repo
git pull origin main

To see all available patterns:

bash
ls ${PAI_DIR}/skills/fabric/fabric-repo/data/patterns/
# OR from your local Fabric install:
ls ~/.config/fabric/patterns/

💡 Usage Examples

Threat Modeling:

bash
# User: "Create a threat model for our new API"
fabric "API that handles user authentication and payment processing" -p create_threat_model

Summarization:

bash
# User: "Summarize this blog post"
fabric -u "https://example.com/blog-post" -p summarize

# User: "Give me a 5-sentence summary"
fabric -u "https://example.com/article" -p create_5_sentence_summary

Wisdom Extraction:

bash
# User: "Extract wisdom from this video"
fabric -y "https://youtube.com/watch?v=..." -p extract_wisdom

# User: "What are the main ideas?"
fabric -u "URL" -p extract_main_idea

Analysis:

bash
# User: "Analyze this code for issues"
fabric "$(cat code.py)" -p analyze_code

# User: "Analyze these security claims"
fabric "security claims text" -p analyze_claims

🎯 Pattern Selection Decision Matrix

User Request Contains	Likely Intent	Recommended Patterns
"threat model"	Security modeling	`create_threat_model`, `create_stride_threat_model`
"summarize", "summary"	Summarization	`summarize`, `create_5_sentence_summary`
"extract wisdom", "insights"	Wisdom extraction	`extract_wisdom`, `extract_insights`
"analyze [X]"	Analysis	`analyze_[X]` (match X to pattern)
"improve", "enhance"	Improvement	`improve_writing`, `improve_prompt`
"create [visualization]"	Visualization	`create_mermaid_visualization`, `create_markmap_visualization`
"rate", "judge", "evaluate"	Rating	`rate_content`, `judge_output`
"main idea", "core message"	Core extraction	`extract_main_idea`, `extract_core_message`

🚀 Advanced Usage

Pipe content through Fabric:

bash
cat article.txt | fabric -p extract_wisdom
pbpaste | fabric -p summarize
curl -s "https://..." | fabric -p analyze_claims

Process YouTube videos:

bash
# Fabric handles download + transcription + processing
fabric -y "https://youtube.com/watch?v=..." -p youtube_summary

Chain patterns (manual):

bash
# Extract then summarize
fabric -u "URL" -p extract_wisdom > wisdom.txt
cat wisdom.txt | fabric -p create_5_sentence_summary

📖 Supplementary Resources

Full Pattern List: ls ${PAI_DIR}/skills/fabric/fabric-repo/data/patterns/ Fabric Repo: ${PAI_DIR}/skills/fabric/fabric-repo/ Fabric Documentation: https://github.com/danielmiessler/fabric Pattern Templates: See ${PAI_DIR}/skills/fabric/fabric-repo/data/patterns/official_pattern_template/

🔑 Key Insight

The skill's value is in selecting the RIGHT pattern for the task.

When user says "Create a threat model using Fabric", your job is to:

Recognize "threat model" intent
Know available options: create_threat_model, create_stride_threat_model, create_threat_scenarios
Select the best match (usually create_threat_model unless STRIDE specified)
Execute: fabric "[content]" -p create_threat_model

Not: "Here are the patterns, pick one" Instead: "I'll use create_threat_model for this" → execute immediately

Publisher	ynulihao
Repository	`AgentSkillOS`
Skill name	`fabric`
Stars	612
Forks	76
Bundled files	Instructions only
Links	Skill source Repository

Fabric

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Fabric Skill

Setup Check - Fabric Repository

When to Activate This Skill

🎯 Pattern Selection Strategy

1. Identify Intent Category

2. Execute Pattern

📚 Pattern Categories (242 Total)

Threat Modeling & Security (15 patterns)

Summarization (20 patterns)

Extraction (30+ patterns)

Analysis (35+ patterns)

Creation (50+ patterns)

Improvement (10 patterns)

Rating/Judgment (8 patterns)

🔄 Updating Patterns

💡 Usage Examples

🎯 Pattern Selection Decision Matrix

🚀 Advanced Usage

📖 Supplementary Resources

🔑 Key Insight

Frequently asked questions

Set up your own AI workspace now

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Fabric Skill

Setup Check - Fabric Repository

When to Activate This Skill

🎯 Pattern Selection Strategy

1. Identify Intent Category

2. Execute Pattern

📚 Pattern Categories (242 Total)

Threat Modeling & Security (15 patterns)

Summarization (20 patterns)

Extraction (30+ patterns)

Analysis (35+ patterns)

Creation (50+ patterns)

Improvement (10 patterns)

Rating/Judgment (8 patterns)

🔄 Updating Patterns

💡 Usage Examples

🎯 Pattern Selection Decision Matrix

🚀 Advanced Usage

📖 Supplementary Resources

🔑 Key Insight

Frequently asked questions

Related AI Skills

Set up your own AI workspace now