fpf:query

Search and aggregate FPF knowledge base hypotheses with assurance scores.

Updated Apr 6, 2026
One-click install
npx skills add https://github.com/luicabref97/sushi-jungle-web --skill fpf-query
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fpf:query
Source: https://github.com/luicabref97/sushi-jungle-web/tree/main/.agents/skills/fpf-query
Command: npx skills add https://github.com/luicabref97/sushi-jungle-web --skill fpf-query

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly locate and interpret hypotheses, decisions, and evidence within the FPF knowledge base without manually opening numerous files, saving time and reducing missed context when assessing design rationale and assurance.

Core Features & Use Cases

  • Search across .fpf/knowledge (L0-L2), .fpf/decisions, and .fpf/evidence for matching hypotheses, decisions, or keywords.
  • Display hypothesis details including title, layer, kind, scope, R_eff breakdown from audit sections, dependency trees, and evidence summaries in a tabular, human-readable format.
  • Use Case: An engineer validating caching strategies can query "caching" to see candidate hypotheses, their R_eff scores, weakest links, dependencies, and associated evidence to decide between Redis and CDN approaches.

Quick Start

Ask the skill to search for "caching" to list matching hypotheses, their layers, R_eff values, dependencies, and evidence summaries.

Frequently Asked Questions about fpf:query

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

FAQPage Schema
How do I search for design rationale and evidence in the FPF knowledge base?

To search the FPF knowledge base, query across .fpf/knowledge, .fpf/decisions, and .fpf/evidence directories. The skill aggregates matching hypotheses, displays their layers, R_eff scores, dependency trees, and evidence summaries in a readable tabular format.

What is R_eff and how does it relate to hypothesis assurance scores?

R_eff is an assurance score computed from audit sections within FPF knowledge files. It quantifies the reliability of a hypothesis, allowing engineers to evaluate design rationale and identify weakest links in dependency trees during analysis.

How do I query decisions and hypotheses across L0 to L2 knowledge layers?

You query L0 to L2 knowledge layers by searching keywords like "caching" across the .fpf/knowledge directory. The skill parses these files, computes R_eff values, renders dependency trees, and presents matching hypotheses with their evidence summaries.

Can I use this to evaluate dependencies and evidence for architectural decisions?

Yes, you can evaluate architectural decisions by searching the FPF knowledge base. The skill renders dependency trees and displays evidence summaries alongside R_eff breakdowns, helping you assess assurance and validate approaches like Redis versus CDN.

Does the FPF knowledge search tool require any external dependencies?

No, the FPF knowledge search tool has zero external dependencies. It directly parses files located in the .fpf/knowledge, .fpf/decisions, and .fpf/evidence directories to compute R_eff and render dependency trees without requiring additional packages.

What is the best way to locate a specific evidence summary in FPF decision records?

The best way to locate a specific evidence summary is to search the .fpf/decisions and .fpf/evidence directories by keyword. The tool aggregates matching records, computes R_eff from audit sections, and displays results in a tabular format.