aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Create and manage memory palaces, the unified storage for knowledge captured from research sessions.
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/palaceContext preview
What this command does when you run it.
Create and manage memory palaces, the unified storage for knowledge captured from research sessions.
name: palace description: Create and manage memory palaces, the unified storage for knowledge captured from research sessions.
Create and manage memory palaces for spatial knowledge organization. Palaces are the unified storage for all captured knowledge from research sessions.
/palace list
Shows all existing memory palaces with entry counts and last-modified dates.
/palace view <palace-id>
Displays the structure, districts, and entries of a specific palace.
/palace diagram <palace-id> [--type map|ascii|entity|heatmap]
Renders the palace as a diagram by invoking `Skill(memory-palace:palace-diagram)`. Types:
Mermaid output renders via the Mermaid Chart MCP; ASCII prints inline.
/palace create <name> <domain> [--metaphor <type>]
Creates a new memory palace with the specified name and domain.
/palace sync [--dry-run] [--auto-create]
Process the intake queue (`data/intake_queue.jsonl`) into palaces:
/palace prune [--stale-days 90]
Check palaces for entries needing cleanup. Also available via the consolidated garden command:
memory_palace_cli.py garden tend --palaces [--stale-days 90]
Identifies:
Shows recommendations and **prompts for user approval** before any changes.
/palace prune --apply
Apply cleanup after reviewing recommendations. **Only run after reviewing the prune check output.**
/palace status
Shows:
/palace delete <palace-id>
Removes a palace (creates backup first).
1. **Unified Knowledge Storage**: Palaces are the single source of truth for captured knowledge 2. **Queue Processing**: Syncs research from intake queue into palace entries 3. **Domain Organization**: Groups knowledge by domain in districts within palaces 4. **Lifecycle Management**: Tracks creation, updates, quality scores 5. **Integration**: Works with `/update-plugins` for automated maintenance
Choose a metaphor that fits your knowledge domain:
| Metaphor | Best For | |----------|----------| | `building` | General organization (default) | | `fortress` | Security, defense, production-grade systems | | `library` | Research, documentation | | `workshop` | Practical skills, tools | | `garden` | Evolving knowledge | | `observatory` | Exploration, patterns |
# List all palaces with entry counts /palace list # Check queue size and palace health /palace status # Sync queued research into palaces (dry run first) /palace sync --dry-run /palace sync # Create a new palace for a domain /palace create "K8s Concepts" "kubernetes" --metaphor workshop # View specific palace structure /palace view abc123
WebSearch/Research → data/intake_queue.jsonl
↓
/palace sync
↓
data/palaces/*.jsonResearch captured during sessions is automatically queued. Run `/palace sync` (or `/update-plugins` which includes it) to process queued items into palaces.
Uses `memory_palace_cli.py` from the plugin's scripts directory:
# Run from repository root with absolute paths plugins/memory-palace/.venv/bin/python \ plugins/memory-palace/scripts/memory_palace_cli.py <command> [args] # Available commands: enable, disable, status, skills, install, # garden, export, import, create, list, sync, prune, search, manager
**Requirements**:
**First-Time Setup**:
# 1. Enable the plugin (creates config) plugins/memory-palace/.venv/bin/python \ plugins/memory-palace/scripts/memory_palace_cli.py enable # 2. Now you can list/create palaces plugins/memory-palace/.venv/bin/python \ plugins/memory-palace/scripts/memory_palace_cli.py list
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.