# Confidently Incorrect Is Worst-Case Scenario
- If the user asks a question and you are not very confident in your answer, tell the user that you are not sure
- When this happens, offer your current hypothesis (if you have one) and then offer options you can take to find the answer

## Basics

- User's name is Cal and uses he/him pronouns
- When writing test, always include a detailed docstring explaining the "what" and "why" of the test.
- DO NOT COMMIT CODE WITHOUT APPROVAL FROM THE USER

## Memory Protocol (MemoryGraph Skill)

MemoryGraph provides persistent, graph-based memory across all sessions. Use it to accumulate learnings, patterns, and solutions.

**Skill Location:** `~/.claude/skills/memorygraph/`
**Database:** `~/.memorygraph/memory.db`
**Documentation:** https://notes.manticorum.com/reference/skills/memorygraph

### REQUIRED: Before Starting Complex Work
Recall relevant memories before any significant task:

```bash
python ~/.claude/skills/memorygraph/client.py recall "project-name technology problem-type"
```

Query by project name, technology, or problem type (e.g., "paper-dynasty python api", "tdarr gpu timeout").

### REQUIRED: Automatic Storage Triggers
Store memories on ANY of these events:

| Trigger | What to Store |
|---------|---------------|
| **Bug fix** | Problem + solution with SOLVES relationship |
| **Git commit** | Summary of what was fixed/added and why |
| **Architecture decision** | Choice made + rationale + alternatives |
| **Pattern discovered** | Reusable approach with context |
| **Configuration that worked** | Setup details that solved an issue |
| **Troubleshooting session** | Steps taken, what worked, what didn't |

### CLI Usage

```bash
# Store a memory
python ~/.claude/skills/memorygraph/client.py store \
  --type solution \
  --title "Fixed Redis timeout" \
  --content "Added socket_keepalive=True..." \
  --tags "redis,timeout,homelab" \
  --importance 0.8

# Recall memories
python ~/.claude/skills/memorygraph/client.py recall "redis timeout"

# Get specific memory
python ~/.claude/skills/memorygraph/client.py get <memory_id>

# Create relationship
python ~/.claude/skills/memorygraph/client.py relate <from_id> <to_id> SOLVES

# Search with filters
python ~/.claude/skills/memorygraph/client.py search --types "solution" --tags "python"

# Get related memories
python ~/.claude/skills/memorygraph/client.py related <memory_id> --depth 2

# Statistics
python ~/.claude/skills/memorygraph/client.py stats
```

### Memory Types
`solution` | `problem` | `error` | `fix` | `decision` | `code_pattern` | `configuration` | `workflow` | `general`

### Importance Scale
- `0.8-1.0`: Critical - affects multiple projects or prevents major issues
- `0.5-0.7`: Standard - useful pattern or solution
- `0.3-0.4`: Minor - nice-to-know, edge case

### Tag Requirements (ALWAYS include)
1. Project name (paper-dynasty, major-domo, homelab, etc.)
2. Primary technology (python, docker, proxmox, bash, etc.)
3. Category (fix, pattern, decision, config, troubleshooting)

### Relationship Types
- `SOLVES` - Solution addresses a problem
- `CAUSES` - One issue leads to another
- `BUILDS_ON` - Enhancement to existing pattern
- `ALTERNATIVE_TO` - Different approach to same problem
- `REQUIRES` - Dependency relationship
- `FOLLOWS` - Workflow sequence

### Proactive Memory Usage

**At session start:** If working on a known project, recall relevant memories.

**During work:** When solving a non-trivial problem, check if similar issues were solved before.

**At session end:** If significant learnings occurred, prompt: "Should I store today's learnings to MemoryGraph?"

## Project Planning

Use `/project-plan` to generate structured `PROJECT_PLAN.json` files for tracking refactoring, features, migrations, or audits. See `~/.claude/skills/project-plan/SKILL.md` for full schema and usage.