system-overview
Show users how Maestro works - the opinionated setup with hooks, memory, and coordination
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Show users how Maestro works - the opinionated setup with hooks, memory, and coordination
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Maestro spec-driven development for Claude Code. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.
Maestro spec-driven development for Gemini CLI. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.
Maestro spec-driven development for Amp CLI. Load this skill when invoking Maestro commands so workflows stay aligned with LeIndex and the Rust TUI.
Full 5-layer analysis of a specific function for debugging or deep understanding
Get a token-efficient overview of any project using the TLDR stack
Maps questions to the optimal LeIndex command
| name | system_overview |
| description | Show users how Maestro works - the opinionated setup with hooks, memory, and coordination |
| user-invocable | true |
Show users how Maestro works - the opinionated setup with hooks, memory, and coordination.
/maestro:system_overviewCONTINUOUS CLAUDE SYSTEM OVERVIEW
=================================
MEMORY LAYER (PostgreSQL + pgvector)
------------------------------------
- 78,000+ temporal facts from past sessions
- Learnings extracted automatically at session end
- Semantic search with embeddings
RECALL: uv run python opc/scripts/recall_temporal_facts.py --query "your topic"
HOOKS (9 event types registered)
--------------------------------
SessionStart → Load continuity ledger, rebuild symbol index
UserPromptSubmit → Skill activation check, context injection
PreToolUse → Smart search routing (Grep → TLDR for code)
PostToolUse → File claims, compiler feedback
PreCompact → Save state before context compaction
Stop → Extract learnings, create handoffs
SubagentStart → Register spawned agents
SubagentStop → Coordination, handoff creation
SessionEnd → Cleanup
CONTINUITY SYSTEM
-----------------
Ledger: thoughts/ledgers/CONTINUITY_CLAUDE-{session}.md
Handoffs: thoughts/shared/handoffs/{session}/*.yaml
Commands:
/resume_handoff <path> - Continue from handoff
/create_handoff - Create snapshot for transfer
TLDR CODE INTELLIGENCE
----------------------
5-layer analysis: AST → Call Graph → CFG → DFG → PDG
95% token savings vs reading raw files
Auto-intercepts Grep for .py/.ts/.go/.rs files
Pre-built index: /tmp/claude-symbol-index/symbols.json
SETUP
-----
Run: uv run python opc/scripts/setup/wizard.py
Options:
[1] SQLite only (simple, offline)
[2] PostgreSQL + pgvector (semantic search)
| Component | Location |
|---|---|
| Hook registration | .maestro/settings.json |
| Hook implementations | .maestro/hooks/src/*.ts |
| Rules (auto-injected) | .maestro/rules/*.md |
| Skills | .maestro/skills/*/SKILL.md |
| Setup wizard | opc/scripts/setup/wizard.py |
| Recall script | opc/scripts/recall_temporal_facts.py |
| Store learning | opc/scripts/store_learning.py |
| Symbol index builder | opc/scripts/build_symbol_index.py |
| Variable | Purpose |
|---|---|
CONTINUOUS_CLAUDE_DB_URL | PostgreSQL connection |
VOYAGE_API_KEY | Embeddings (optional) |
BRAINTRUST_API_KEY | Tracing (optional) |
CLAUDE_PROJECT_DIR | Auto-set by Maestro |