recall
Semantic memory retrieval that queries stored learnings from past sessions
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Semantic memory retrieval that queries stored learnings from past sessions
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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.
Show users how Maestro works - the opinionated setup with hooks, memory, and coordination
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
| name | recall |
| description | Semantic memory retrieval that queries stored learnings from past sessions |
| user-invocable | true |
Query the memory system for relevant learnings from past sessions.
/recall <query>
/recall hook development patterns
/recall wizard installation
/recall TypeScript errors
When this skill is invoked:
Determine the memory stack root:
MEMORY_DIR="${MAESTRO_MEMORY_DIR:-$CLAUDE_PROJECT_DIR/opc}"
Check that the recall script exists before running:
if [ ! -f "$MEMORY_DIR/scripts/recall_learnings.py" ]; then
echo "⚠️ Recall unavailable: memory stack not found at $MEMORY_DIR"
echo " Set MAESTRO_MEMORY_DIR to your OPC installation path."
exit 0
fi
cd "$MEMORY_DIR" && PYTHONPATH=. uv run python scripts/recall_learnings.py --query "<ARGS>" --k 5
Where <ARGS> is the query provided by the user.
Present results as:
## Memory Recall: "<query>"
### 1. [TYPE] (confidence: high, id: abc123)
<full content>
### 2. [TYPE] (confidence: medium, id: def456)
<full content>
The user can specify options after the query:
--k N - Return N results (default: 5)--vector-only - Use pure vector search (higher precision)--text-only - Use text search only (faster)Example: /maestro:recall hook patterns --k 10 --vector-only