菜单
USE WHEN user says 'use fabric', 'fabric pattern', 'run fabric', 'update fabric', 'update patterns', 'sync fabric', 'extract wisdom', 'summarize with fabric', 'create threat model', 'analyze with fabric', OR any request to apply Fabric patterns to content.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
USE WHEN PAI system, PAI algorithm, how PAI works, system overview, core configuration, PAI infrastructure.
USE WHEN upgrade, improve system, system upgrade, analyze for improvements, check Anthropic, Anthropic changes, new Claude features, check YouTube, new videos, sync PAI, sync upstream, pull PAI updates. SkillSearch('upgrade') for docs.
USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.
USE WHEN user wants to create visual content, illustrations, diagrams, OR mentions art, header images, visualizations, mermaid, flowchart, technical diagram, infographic, PAI icon, pack icon, or PAI pack icon.
USE WHEN TELOS, life goals, projects, dependencies, books, movies. SkillSearch('telos') for docs.
USE WHEN annual reports, security reports, threat reports, industry reports, update reports, analyze reports, vendor reports, threat landscape.
| name | Fabric |
| description | USE WHEN user says 'use fabric', 'fabric pattern', 'run fabric', 'update fabric', 'update patterns', 'sync fabric', 'extract wisdom', 'summarize with fabric', 'create threat model', 'analyze with fabric', OR any request to apply Fabric patterns to content. |
Before executing, check for user customizations at:
~/.claude/skills/PAI/USER/SKILLCUSTOMIZATIONS/Fabric/
If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.
When executing a workflow, do BOTH:
Send voice notification:
curl -s -X POST http://localhost:8888/notify \
-H "Content-Type: application/json" \
-d '{"message": "Running the WORKFLOWNAME workflow in the Fabric skill to ACTION"}' \
> /dev/null 2>&1 &
Output text notification:
Running the **WorkflowName** workflow in the **Fabric** skill to ACTION...
Full documentation: ~/.claude/skills/PAI/SYSTEM/THENOTIFICATIONSYSTEM.md
Intelligent prompt pattern system providing 240+ specialized patterns for content analysis, extraction, summarization, threat modeling, and transformation.
Patterns Location: ~/.claude/skills/Fabric/Patterns/
| Workflow | Trigger | File |
|---|---|---|
| ExecutePattern | "use fabric", "run pattern", "apply pattern", "extract wisdom", "summarize", "analyze with fabric" | Workflows/ExecutePattern.md |
| UpdatePatterns | "update fabric", "update patterns", "sync fabric", "pull patterns" | Workflows/UpdatePatterns.md |
Example 1: Extract wisdom from content
User: "Use fabric to extract wisdom from this article"
-> Invokes ExecutePattern workflow
-> Selects extract_wisdom pattern
-> Reads Patterns/extract_wisdom/system.md
-> Applies pattern to content
-> Returns structured IDEAS, INSIGHTS, QUOTES, etc.
Example 2: Update patterns
User: "Update fabric patterns"
-> Invokes UpdatePatterns workflow
-> Runs git pull from upstream fabric repository
-> Syncs patterns to local Patterns/ directory
-> Reports pattern count
Example 3: Create threat model
User: "Use fabric to create a threat model for this API"
-> Invokes ExecutePattern workflow
-> Selects create_threat_model pattern
-> Applies STRIDE methodology
-> Returns structured threat analysis
Instead of calling fabric -p pattern_name, PAI executes patterns natively:
Patterns/{pattern_name}/system.mdOnly use fabric command for:
-y URL - YouTube transcript extraction-u URL - URL content fetching (when native fetch fails)| Intent | Pattern | Description |
|---|---|---|
| Extract insights | extract_wisdom | IDEAS, INSIGHTS, QUOTES, HABITS |
| Summarize | summarize | General summary |
| 5-sentence summary | create_5_sentence_summary | Ultra-concise |
| Threat model | create_threat_model | Security threat analysis |
| Analyze claims | analyze_claims | Fact-check claims |
| Improve writing | improve_writing | Writing enhancement |
| Code review | review_code | Code analysis |
| Main idea | extract_main_idea | Core message extraction |
See PatternCatalog.md for complete list of 240+ patterns organized by category.
How it works:
User Request → Pattern Selection → Read system.md → Apply → Return Results
Pattern Structure:
Patterns/
├── extract_wisdom/
│ └── system.md # The prompt instructions
├── summarize/
│ └── system.md
├── create_threat_model/
│ └── system.md
└── ...240+ patterns
Each pattern's system.md contains the full prompt that defines:
| Category | Count | Examples |
|---|---|---|
| Extraction | 30+ | extract_wisdom, extract_insights, extract_main_idea |
| Summarization | 20+ | summarize, create_5_sentence_summary, youtube_summary |
| Analysis | 35+ | analyze_claims, analyze_code, analyze_threat_report |
| Creation | 50+ | create_threat_model, create_prd, create_mermaid_visualization |
| Improvement | 10+ | improve_writing, improve_prompt, review_code |
| Security | 15 | create_stride_threat_model, create_sigma_rules, analyze_malware |
| Rating | 8 | rate_content, judge_output, rate_ai_response |
-y) and URL fetching (-u)| Path | Purpose |
|---|---|
~/.claude/skills/Fabric/Patterns/ | Local pattern storage (240+) |
~/.claude/skills/Fabric/PatternCatalog.md | Full pattern documentation |
~/.claude/skills/Fabric/Workflows/ | Execution workflows |
~/.claude/skills/Fabric/Tools/ | CLI utilities |