quint-fpf
CommunityTurn design claims into auditable decisions
System Documentation
What problem does it solve?
Quint FPF provides a disciplined, auditable process to turn vague architectural or product claims into traceable decisions by guiding teams through six formal phases: Initialize, Abduct, Deduce, Induce, Audit, and Decide. It eliminates informal reasoning and undocumented assertions that lead to hidden technical risk by enforcing tool-backed state transitions and evidence tracking.
Core Features & Use Cases
- Structured reasoning workflow: Enforces phase-by-phase progression (L0→L1→L2) with exact verdicts and mandatory tool calls in tooled mode.
- Audit and trust calculus: Computes effective reliability (R_eff) via WLNK, visualizes dependency trees, and surfaces weakest links and epistemic debt.
- Dual execution modes: Integrates with a quint MCP server for persistent holons and slash commands, or produces conversational markdown artifacts in docs/fpf when MCP is absent.
- Use cases: Validating PRDs and ADRs, stress-testing architectural claims before implementation, generating Design Rationale Records for compliance and review.
Quick Start
Run a full FPF cycle against a PRD by invoking the skill with the PRD path and mode set to auto to produce an audit-ready decision artifact.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: quint-fpf Download link: https://github.com/russosalv/NONoise/archive/main.zip#quint-fpf Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.