fpf

Frame non-trivial problems using an Abduction–Deduction–Induction cycle.

Updated May 21, 2026
One-click install
npx skills add https://github.com/random1st/groundwork --skill fpf-random1st
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fpf
Source: https://github.com/random1st/groundwork/tree/main/plugins/fpf
Command: npx skills add https://github.com/random1st/groundwork --skill fpf-random1st

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, curl, and includes scripts (resource) components.

What problem does it solve?

FPF provides a disciplined framing approach to complex problems to improve reasoning quality and auditability.

Core Features & Use Cases

  • Abduction–Deduction–Induction (ADI) cycle to structure reasoning and ensure traceability.
  • I/D/S discipline to separate observed, described, and specified aspects.
  • Calibration tags and a modular corpus to guide decision-making and evidence gathering.
  • A built-in builder that pulls upstream FPF specs to customize your local corpus.

Quick Start

Apply the FPF workflow to frame a non-trivial problem and drive the ADI cycle before solving.

Frequently Asked Questions about fpf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I structure reasoning for root-cause investigations across complex systems?

Use the Abduction–Deduction–Induction cycle to structure reasoning for root-cause investigations across complex systems. This method separates observed, described, and specified aspects to ensure traceability and improve auditability.

What is the best way to frame complex engineering problems for design reviews?

Frame complex engineering problems for design reviews by applying a disciplined lifecycle framing approach. Separating observed, described, and specified aspects guides evidence gathering and enables repeatable decision-making.

Do I need python3 and curl installed to run the FPF workflow?

Yes, you need python3 and curl installed to run the FPF workflow. The built-in builder uses these dependencies to pull upstream specs and customize your local corpus for problem framing.

How does evidence tagging work during engineering audits?

Evidence tagging works during engineering audits by applying calibration tags within a modular corpus. This separates observed data from described aspects and specified requirements to ensure explicit traceability.

Can I use this approach to audit complex systems without losing decision context?

Yes, you can use this approach to audit complex systems without losing decision context. The modular corpus and calibration tags maintain explicit lifecycle framing to capture and preserve reasoning throughout the analysis.

Why does problem framing fail without separating observed, described, and specified data?

Problem framing fails without separating observed, described, and specified data because reasoning becomes entangled. The I/D/S discipline enforces clear boundaries to prevent assumptions from corrupting the evidence gathering process.