Skip to content
Get packs

Fabric Prompt Patterns

Runs 240+ specialized Fabric prompt patterns for summaries, analysis, security reports and diagrams

Source Download skill
Repository
danielmiessler/LifeOS
Stars
19,682
Licence
MIT
Files
15 files

What it does

This skill gives an AI agent a library of about 240 ready-made prompt recipes from the Fabric project, covering summarizing, extracting insights, analyzing logs or claims, writing security findings, and making diagrams. When you ask for one by name or by what you want done, the agent reads the matching recipe and applies it directly, without calling an outside program. It also includes its own refined versions of the most popular recipes, which it uses instead of the originals.

Great for

  • People who want structured summaries or analyses of articles, meetings or documents using proven prompt formats
  • Security engineers who want help drafting threat models, pentest findings or incident write-ups
  • Developers who want commit messages, pull request descriptions or code explanations in a consistent format

Skip it if

  • Sensitive material you would not want sent to an AI service, since the text is processed by the model and summaries on URLs or long text also trigger a separate harvest skill that writes notes (review that behaviour first)
  • Multi-agent investigations or deep research, which the skill explicitly excludes in favour of other skills
  • Anyone expecting guaranteed factual accuracy: the output is only as good as the model reading the source text

Try asking

  • “ws 3 — turn this article into a three-level word summary”
  • “Analyze these logs and tell me why the deploy failed”
  • “Write a pentest finding from this scan output using the Fabric report pattern”
  • “Extract the claims from this paper and check them for logical fallacies”
Step-by-step guide: how to use Fabric Prompt PatternsInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    Fabric.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip Fabric.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip Fabric.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the pattern directly (for example extract_wisdom or analyze_claims) to get the most reliable routing.
  • For YouTube videos, make sure the Fabric CLI is installed so transcripts can be fetched.
  • Review the harvest note-writing behaviour on URLs and long text if you care where notes are stored.

What's inside

  • Evals/HeldOut/AnalyzeBill.json
  • Evals/HeldOut/AnalyzeClaims.json
  • Evals/HeldOut/AnalyzeComments.json
  • Evals/HeldOut/AnalyzeIncident.json
  • Evals/HeldOut/AnalyzeLogs.json
  • Evals/HeldOut/AnalyzeMalware.json
  • Evals/HeldOut/AnalyzePaper.json
  • Evals/HeldOut/AnalyzeProse.json
  • Evals/HeldOut/AnalyzeRisk.json
  • Evals/HeldOut/AnalyzeThreatReport.json
  • Evals/HeldOut/AuditConsent.json
  • Evals/HeldOut/AuditTransparency.json
  • Evals/HeldOut/BusinessIdeas.json
  • Evals/HeldOut/CheckAgreement.json
  • SKILL.md

Redistributed unmodified from danielmiessler/LifeOS under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.