agentsclimarketplace

Palace diagram

Skill athola/claude-night-market/plugins/memory-palace/skills/palace-diagram

23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.

Install
npx -y skills add athola/claude-night-market --skill palace-diagram

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Generates Mermaid and ASCII diagrams of palace structure, knowledge topology, and synapse connectivity. Use when inspecting or presenting a palace visually.

SKILL.md

3.7 KB, as published. Nobody here has run it

Palace Diagram

Generate Mermaid and ASCII diagrams from the knowledge graph, showing palace structure, entity relationships, synapse connectivity, and tier assignments.

Status: wired. Invoke via /palace diagram <palace-id> [--type map|ascii|entity|heatmap], which calls Skill(memory-palace:palace-diagram). The renderer lives in memory_palace.palace_renderer.PalaceRenderer; see the Usage section below for direct programmatic access.

When To Use

  • Inspecting palace structure after creation or migration
  • Understanding knowledge topology and connections
  • Identifying strong and weak synapses (heatmap)
  • Reviewing entity relationships and triples
  • Getting an ASCII overview for inline display

When NOT To Use

  • Creating palaces: use memory-palace-architect
  • Searching knowledge: use knowledge-locator
  • Code architecture diagrams: use cartograph

Diagram Types

TypeFormatDescription
Palace mapMermaid flowchartRooms as subgraphs, entities as nodes, synapses as edges
Entity graphMermaid flowchartSingle entity's connections and triples
Synapse heatmapMermaid flowchartEdge styling by strength (thick=strong, dotted=weak)
ASCII overviewTextBox-drawing palace layout with entity counts

Workflow

  1. Identify palace by ID or name
  2. Choose diagram type based on what you want to see
  3. Generate diagram using PalaceRenderer
  4. Render via Mermaid Chart MCP (for Mermaid) or display inline (for ASCII)

Usage

Palace Map

from memory_palace.knowledge_graph import KnowledgeGraph
from memory_palace.palace_renderer import PalaceRenderer

graph = KnowledgeGraph("path/to/knowledge_graph.db")
renderer = PalaceRenderer(graph)
mermaid = renderer.palace_map("palace_id")

Then call mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram with the generated Mermaid string.

ASCII Overview

ascii_art = renderer.ascii_overview("palace_id")
print(ascii_art)

Entity Graph

mermaid = renderer.entity_graph("entity_id")

Synapse Heatmap

mermaid = renderer.synapse_heatmap("palace_id")

Edge Styling

StrengthStyleMeaning
>= 0.7==> (thick)Strong connection
>= 0.4--> (normal)Medium connection
< 0.4-.-> (dotted)Weak connection

Integration

Works with:

  • memory-palace-architect: visualize after palace creation
  • knowledge-locator: display search results as graph
  • graph-analyzer: tier-informed node sizing

Exit Criteria

  • At least one of the four diagram types (palace map, entity graph, synapse heatmap, ASCII overview) is generated without a Python exception from PalaceRenderer
  • Mermaid diagrams are passed to mcp__claude_ai_Mermaid_Chart__validate_and_render_mermaid_diagram and render successfully
  • ASCII overview displays rooms with box-drawing characters and entity counts per room
  • Synapse edge styling matches strength thresholds: ==> for strength ≥ 0.7, --> for ≥ 0.4, -.-> for < 0.4
  • If the requested palace ID does not exist in the knowledge graph, an error is reported with the palace ID that was searched

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.