How to manually sync learnings to memory systems after tasks.
Inherits all available tools
Additional assets for this skill
This skill inherits all available tools. When active, it can use any tool Claude has access to.
How to manually sync learnings to memory systems after tasks.
Ariff uses two complementary memory systems:
Use mcp__mem0-memory-mcp__add_memory to store:
- Task context and solution
- Key learnings and gotchas
- Useful commands discovered
Use mcp__obsidian-memory__create_note with:
- path: "tasks/YYYY-MM-DD-task-slug.md"
- content: Structured task notes
## Task: [Brief Title]
Date: [YYYY-MM-DD]
Device: [hostname]
### Problem
[What was the issue/request]
### Solution
[How it was resolved]
### Key Learnings
- [Learning 1]
- [Learning 2]
### Related
- Previous tasks: [links]
- Documentation: [links]
When a mistake or pattern should be avoided in future:
Create instruction file at:
Ariff-code-config/instructions/[category]-[topic].instructions.md
Use format:
---
description: [What this instruction prevents/ensures]
applyTo: [glob pattern like **/*.py or **/canvas/**]
---
# [Rule Title]
## Context
[When this applies]
## Rule
[What to do/not do]
## Example
[Good vs bad example]
Add to 00_INSTRUCTIONS_INDEX.md if significant
If memories seem out of sync:
Save memory when:
Skip saving when: