Megg learn
Multi-agent team for Claude Code: 7 AI specialists (strategy, dev, security, sales, design, data, research) that collaborate and challenge you. Dev-cycle workflow with machine-verifiable completion.
npx -y skills add ToruAI/toru-claude-agents --skill megg-learnAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 15 stars15 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Save a project fact, decision or gotcha so your next session already knows it.
SKILL.md
1.1 KB, as published. Nobody here has run it
Capture Learning
User wants to save something to megg knowledge.
Process
- If argument provided, use it as the learning content
- If no argument, ask: "What should we capture?"
- Determine the appropriate entry type:
- decision: Architectural or design choice made
- pattern: How we do things here (reusable approach)
- gotcha: Trap to avoid, something that caught us
- context: Background info, not actionable
- Extract or ask for relevant topics (tags for categorization)
- Use the
mcp__megg__learntool to save
Example
User: /megg-learn always use absolute paths in hooks
→ Capture as pattern with topics like hooks, paths
Important
- Keep entries concise and actionable
- Topics should be 1-3 words each
- Title should be short (5-10 words max)
- Content can include examples or context