agentleFS
CarbeneAICarbeneAI/Forge/.claude/skills/Fabric/SKILL.md

fabric

Skill9 starsChanged 6 months agoMITView on GitHub

Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).

  • Installs packages

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Fabric patterns are just markdown prompts: Instead of spawning fabric -p pattern_name for every task, Claude Code reads and applies …

    line 10
  2. Distinctive:

    Same 248 patterns: - All the patterns you know, just applied natively

    line 15
  3. Very specific:

    Only use the fabric command for operations that require external services:

    line 44
  4. Distinctive:

    Run the update script to sync latest patterns from upstream:

    line 101
  5. Very specific:

    Run fabric -U to fetch upstream updates

    line 108

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Fabric Skill - Native Pattern Execution

The Key Insight

Fabric patterns are just markdown prompts. Instead of spawning fabric -p pattern_name for every task, Claude Code reads and applies patterns directly from tools/patterns/. This gives you:

  • Your Claude subscription's full power - Opus/Sonnet intelligence, not Fabric's default model
  • Full conversation context - Patterns work with your entire session
  • No CLI overhead - Faster execution, no process spawning
  • Same 248 patterns - All the patterns you know, just applied natively

When to Use Native Patterns (Default)

For any pattern-based processing:

  1. Read tools/patterns/{pattern_name}/system.md
  2. Apply the pattern instructions directly to the content
  3. Return results without external CLI calls

Examples:

User: "Extract wisdom from this transcript"
→ Read tools/patterns/extract_wisdom/system.md
→ Apply pattern to content
→ Return structured output (IDEAS, INSIGHTS, QUOTES, etc.)

User: "Create a threat model for this API"
→ Read tools/patterns/create_threat_model/system.md
→ Apply pattern to the API description
→ Return threat model

User: "Summarize this article"
→ Read tools/patterns/summarize/system.md
→ Apply pattern to article
→ Return summary

When to Still Use Fabric CLI

Only use the fabric command for operations that require external services:

OperationCommandWhy CLI Needed
YouTube transcriptsfabric -y "URL"Downloads video, extracts transcript
Update patternsfabric -UPulls from GitHub
List patternsfabric -lQuick reference

For everything else, use native patterns.

Pattern Categories (248 Total)

Threat Modeling & Security

  • create_threat_model - General threat modeling
  • create_stride_threat_model - STRIDE methodology
  • create_threat_scenarios - Threat scenario generation
  • analyze_threat_report - Threat report analysis
  • create_sigma_rules - SIGMA detection rules
  • write_nuclei_template_rule - Nuclei scanner templates
  • write_semgrep_rule - Semgrep static analysis rules

Summarization

  • summarize - General summarization
  • create_5_sentence_summary - Ultra-concise summary
  • summarize_paper - Academic paper summary
  • summarize_meeting - Meeting notes
  • youtube_summary - Video summary

Wisdom Extraction

  • extract_wisdom - General wisdom extraction
  • extract_insights - Key insights
  • extract_main_idea - Core message
  • extract_recommendations - Actionable recommendations
  • extract_alpha - High-value insights

Analysis

  • analyze_claims - Claim verification
  • analyze_code - Code analysis
  • analyze_malware - Malware analysis
  • analyze_paper - Academic paper analysis
  • analyze_debate - Debate analysis

Content Creation

  • create_prd - Product Requirements Document
  • create_design_document - Design documentation
  • create_mermaid_visualization - Mermaid diagrams
  • write_essay - Essay writing
  • create_report_finding - Security findings

Improvement

  • improve_writing - Writing enhancement
  • improve_prompt - Prompt engineering
  • review_code - Code review
  • humanize - Humanize AI text

Updating Patterns

Run the update script to sync latest patterns from upstream:

./tools/update-patterns.sh

This will:

  1. Run fabric -U to fetch upstream updates
  2. Sync patterns to tools/patterns/

Requirements: fabric CLI must be installed (go install github.com/danielmiessler/fabric@latest)

Pattern Structure

Each pattern directory contains:

  • system.md - The main prompt/instructions (this is what gets applied)
  • README.md - Documentation (optional)
  • user.md - Example user input (optional)

Why Native > CLI

AspectNative Patternsfabric CLI
ModelYour subscription (Opus/Sonnet)Fabric's configured model
ContextFull conversation historyJust the input
SpeedInstant (no process spawn)~1-2s CLI overhead
IntegrationSeamless with Claude CodeExternal tool call

The patterns are identical. The difference is execution context and model power.

Full Pattern List

See all available patterns:

ls tools/patterns/

Or browse: tools/patterns/{pattern_name}/system.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.