---
name: Memorix Reasoning
slug: memorix-reasoning
category: AI Engineering
description: Memorix Reasoning stores why a technical decision was made and retrieves prior rationale later. Use it for trade-offs, rejected alternatives, architecture choices, and design risks.
github: "https://github.com/AVIDS2/memorix/tree/main/plugins/claude/memorix/skills/memorix-reasoning"
language: TypeScript
stars: 681
forks: 53
install: "npx degit https://github.com/AVIDS2/memorix/tree/main/plugins/claude/memorix/skills/memorix-reasoning ~/.claude/skills/memorix-reasoning"
installs_to: ~/.claude/skills/memorix-reasoning
source_path: plugins/claude/memorix/skills/memorix-reasoning/SKILL.md
collection_size: 10
category_size: 2451
collection_url: "https://dirskills.com/collections/AVIDS2/memorix"
added: 2026-08-24T05:16:07.628Z
last_synced: 2026-08-24T05:16:07.628Z
canonical_url: "https://dirskills.com/skills/memorix-reasoning"
---

# Memorix Reasoning

Memorix Reasoning stores why a technical decision was made and retrieves prior rationale later. Use it for trade-offs, rejected alternatives, architecture choices, and design risks.

**Install:**

```bash
npx degit https://github.com/AVIDS2/memorix/tree/main/plugins/claude/memorix/skills/memorix-reasoning ~/.claude/skills/memorix-reasoning
```

## README

# Memorix Reasoning

Use reasoning memory for why a decision was made. Use ordinary memory for what happened.

## Tool Router

| Situation | Prefer | CLI fallback |
|---|---|---|
| Store why a decision was made | `memorix_store_reasoning` | `memorix reasoning store --entity <name> --decision "<decision>" --rationale "<why>"` |
| Find earlier rationale | `memorix_search_reasoning` | `memorix reasoning search --query "<topic>"` |
| Need a stable evolving topic key | `memorix_suggest_topic_key` | `memorix memory suggest-topic-key --type decision --title "<title>"` |
| Link rationale to commit evidence | `relatedCommits` on reasoning store | `memorix reasoning store ... --relatedCommits <sha>` |

## Use Reasoning When

- The answer depends on alternatives considered, constraints, expected outcomes, or accepted risks.
- A future agent may otherwise reopen the same debate.
- The user chose a direction and the reason matters more than the implementation details.
- A Git Memory entry says what changed, but not why it changed.

## Do Not Use Reasoning For

- Simple progress notes.
- Mechanical refactors with no decision.
- Facts that belong in `memorix_store` as `how-it-works`, `what-changed`, or `problem-solution`.