Skills that make Claude Code agents proactively intelligent. Memory search, code graph queries, documentation lookup, and agent-to-agent messaging - all auto-triggered without you asking.
Skills are SKILL.md files that teach Claude Code how to use specific tools and workflows. They're like plugins - but smarter.
Just markdown files in ~/.claude/skills/. No compilation, no runtime.
Claude reads skills and understands when and how to use them automatically.
Skills auto-trigger based on context - no need to ask Claude to use them.
Three of our four skills follow a proactive pattern - they trigger automatically without you asking.
memory-search
"What did we discuss about authentication?"
docs-search
"What's the documented behavior?"
Reads file
Opens UserController.ts
graph-query
"What depends on this?"
Result: Claude now has previous context, documentation, code structure, and dependencies - all before writing a single line of code.
🎯 Why This Matters
Without proactive skills, Claude might repeat explanations you've already heard, contradict previous decisions, miss dependencies that break, or start over instead of continuing where you left off.
These skills complement each other but solve fundamentally different problems.
Solves RETRIEVAL
"What did we discuss last week?"
Solves EXECUTION
"What am I supposed to do next?"
Use BOTH for complex work: Memory tells you what happened before. Planning keeps you focused now.
Each skill gives Claude Code a specific superpower
Solves RETRIEVAL: Search past conversation history from days/weeks/months ago. "What did we discuss last week?"
Auto-triggers when:
Search auto-generated documentation for function signatures, class definitions, and API specs.
Auto-triggers when:
Query the code graph database to understand relationships and impact of changes.
Auto-triggers when:
Send and receive messages between AI agents asynchronously. Multi-host support included.
Use when:
Solves EXECUTION: Stay focused during current complex tasks. Prevents goal drift, lost progress, and repeated errors within the current session.
Use when:
The 3-file pattern:
task_plan.md - Goals, phases, decisionsfindings.md - Research, discoveriesprogress.md - Session log, resultsGet all five skills in under 2 minutes
In Claude Code, run this command:
Skills are immediately available! They auto-trigger when Claude Code agents read files or receive instructions.
That's it! No cloning, no manual installation. Skills work instantly.
4 of 5 skills require the AI Maestro service running on localhost:23000.
| planning | ✓ Works standalone |
| memory-search | Needs AI Maestro running |
| docs-search | Needs AI Maestro running |
| graph-query | Needs AI Maestro running |
| agent-messaging | Needs AI Maestro running |
To enable all skills, install AI Maestro:
Skills are available with the namespace:
memory-search.sh, graph-describe.sh, etc.) work with any AI agent running in tmux. You can teach other agents to use these scripts directly.
localhost:23000. These skills (memory-search, docs-search, graph-query, agent-messaging) communicate with AI Maestro's backend APIs.~/.claude/skills/your-skill/ with a SKILL.md file. Include frontmatter with name, description, and allowed-tools. Then document when the skill should trigger and what commands to run.
Install AI Maestro Skills and watch Claude Code become proactively intelligent.