skills.rest
ajrmooreuk
ajrmooreukCOMMUNITY
Explore all skills by this author →
GitHub

pfc-reason

Validate SKILL.md presence and frontmatter, then apply REASON-ONT workflow to produce structured outputs.

Updated Feb 17, 2026
Search Tags:#reasoning#hypothesis-testing#analysis-framework#mece#logic-tree#rsn-ont
One-click install
npx skills add https://github.com/ajrmooreuk/pfi-w4m-dev --skill pfc-reason
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pfc-reason
Source: https://github.com/ajrmooreuk/pfi-w4m-dev/tree/main/pfc-core/skills/pfc-reason
Command: npx skills add https://github.com/ajrmooreuk/pfi-w4m-dev --skill pfc-reason

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

MECE decomposition, logic-tree analysis, hypothesis testing, and synthesis are essential for rigorous, structured reasoning in analytical workflows. This skill provides a reusable substrate that orchestrates these methods and is invoked by orchestrators (pfc-delta-pipeline, pfc-ve-pipeline) or phase skills (pfc-delta-evaluate, pfc-delta-leverage) to apply REASON-ONT v1.0.0.

Core Features & Use Cases

  • MECE decomposition with branch validation to ensure full coverage and non-overlap.
  • Hypothesis formation with testable assumptions and explicit evidence chains.
  • Logic-tree analysis with quantitative drivers and sensitivity ranking to identify top levers.
  • Synthesis of mixed analyses into convergent/divergent findings and actionable recommendations for VSOM.

Quick Start

Submit a strategic question to trigger the REASON-ONT workflow and return MECE, hypothesis, logic tree, and synthesis outputs.

Frequently Asked Questions about pfc-reason

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

FAQPage Schema
How do I use MECE decomposition and logic-tree analysis for structured reasoning?▼

MECE decomposition and logic-tree analysis are applied by validating branch coverage and non-overlap, forming testable hypotheses with evidence chains, and synthesizing findings into actionable recommendations.

What is the best way to structure complex hypothesis testing with quantitative drivers?▼

Hypothesis testing with quantitative drivers is structured by forming testable assumptions, ranking sensitivity to identify top levers, and synthesizing mixed analyses into convergent or divergent findings.

Can I generate JSON-LD compatible outputs from a MECE logic tree workflow?▼

JSON-LD compatible outputs are generated by applying the REASON-ONT workflow to produce structured outputs that reference original questions and handle evidence chains for rsn ontologies.

How do I synthesize mixed analyses into actionable recommendations?▼

Mixed analyses are synthesized into actionable recommendations by converging logic-tree findings and hypothesis results, ensuring outputs reference original strategic questions and quantitative drivers.

Do I need a specific framework to validate MECE branch coverage for complex analysis?▼

MECE branch validation requires applying the REASON-ONT workflow, which ensures full coverage and non-overlap during decomposition to produce rigorous structured reasoning outputs.

Why does my structured analysis lack actionable recommendations from logic-tree outputs?▼

Structured analysis lacks actionable recommendations when logic-tree outputs are not synthesized with hypothesis evidence chains, preventing the identification of top levers and convergent findings.

Related Skills

Explore More Data & Analytics Skills→
haabehaabe
42

bad_skill

Detects missing 'name' field in 'SKILL.md' frontmatter using string parsing.

Community
Basic
ajrmooreukajrmooreuk

pfc-vsom

Generate VSOM and Balanced Scorecard JSON-LD artifacts from organizational context and SA analyses.

Community
Advanced
SensLiaoSensLiao

gsd-secure-phase

Verify security mitigations for completed GSD-namespace workflow phases.

Community
Advanced
AllanYiinAllanYiin
2

problem-decomposer

Decompose ambiguous problems into work plans with acceptance criteria.

Community
Advanced