# Proof Trees Reasoning

> Declare reasoning DAG before prose: premises, claims, dependencies. Flag downstream if upstream fails. Use for multi-step arguments and agent plans. Scope boundary: dual-axis → `score-study-dual-axis`.

- Skill: `catcorner22/proof-trees-reasoning` (Agent Skill)
- Install (CLI): `npx skillmds@latest add catcorner22/proof-trees-reasoning`
- Raw SKILL.md: https://api.skillmd.com/api/skills/catcorner22/proof-trees-reasoning/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: CatCorner22 (https://skillmd.com/u/catcorner22)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/catcorner22/proof-trees-reasoning

---

# Proof trees (reasoning DAG)

**#12** · **Domain:** Mathematics · **Category:** architecture · **Difficulty:** 🔴 High

## Core principle

Explicit dependencies — if a premise fails, downstream collapses visibly.

## AI problem addressed

Prose hides dependencies; step 3 error poisons 4–9 invisibly.

## Implementation

Declare: Premise P1, P2 → Claim A(P1,P2) → Claim B(A,P3) → Conclusion C(B)
Generate prose following DAG only.
Self-check: weakest premise? Downstream auto-flag if premise fails.

## Boundaries

- Prototype as prompt scaffold (🟢) before full pipeline middleware (🟡/🔴)
- Category router: **`ai-transfer-architecture`**
- Catalog: **`ai-transfer-ecosystem-primer`**
- Runtime plugin id: `proof_trees`
- Also implements: `scientific_method`
- Merge notes: Scientific-method plugin is this DAG, not a separate skill.