mcpbeat Sign in

Session Palace Builder Skill for Claude

Builds session-scoped temporary memory palaces for extended conversations. Use when tracking state across interruptions in a multi-step project.

2k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
324
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/athola/claude-night-market --skill session-palace-builder

The instruction itself

20 sections, as written by the author

Table of Contents

  • What It Is
  • Quick Start
  • Mental Model
  • When to Use
  • Session Palace Templates
  • Information Categories
  • Core Workflow
  • Session Lifecycle
  • Clarity Checkpoints
  • Detailed Resources
  • Integration
  • Exit Criteria

Session Palace Builder

Construct temporary, session-specific memory palaces for extended conversations and complex projects. Preserves context across interruptions and enables structured information accumulation.

What It Is

Session palaces are lightweight, temporary memory structures that:

  • Preserve context for extended conversations
  • Track decisions and their rationale
  • Organize project artifacts spatially
  • Enable context recovery after interruptions
  • Support collaborative information gathering

Quick Start

Build Commands

\\\`bash

Run build

make build

Clean and rebuild

make clean && make build

\\\`

Testing

\\\`bash

Run tests

make test

Run with verbose output

make test VERBOSE=1

\\\`

Verification: Run make build && make test to confirm build works.

When To Use

  • Extended conversations requiring context preservation
  • Complex, multi-step projects with interrelated components
  • Workflows requiring state management across interactions
  • Collaborative sessions accumulating information over time
  • Code review or debugging sessions with many findings

When NOT To Use

  • Permanent knowledge structures

needed - use memory-palace-architect

  • Searching existing knowledge
  • use knowledge-locator
  • Permanent knowledge structures

needed - use memory-palace-architect

  • Searching existing knowledge
  • use knowledge-locator

Session Palace Templates

| Template | Purpose | Key Areas |

|----------|---------|-----------|

| Workshop | Active development | Workbench, tools, materials |

| Library | Research and analysis | Stacks, reading room, archives |

| Council Chamber | Decision-making | Round table, evidence wall, vote board |

| Observatory | Exploration and discovery | Telescope, star charts, log book |

| Forge | Implementation tasks | Anvil, cooling rack, finished goods |

Information Categories

Organize session content into these standard areas:

  • Conversations - Dialogue threads and key exchanges
  • Decisions - Choices made with rationale
  • Code - Snippets and technical artifacts
  • Research - Findings and references
  • Requirements - Specifications and constraints
  • Progress - Completed milestones
  • Issues - Blockers and challenges
  • Next Steps - Pending action items

Core Workflow

  • Analyze Context - Assess session scope and complexity
  • Design Palace - Select template and layout
  • Structure State - Organize information spatially
  • Build Navigation - Create access shortcuts
  • Test Integration - Verify context preservation

Session Lifecycle

Create → Populate → Navigate → Export/Archive
   ↑         ↓          ↓
   └─── Checkpoint ←────┘

Verification: Run the command with --help flag to verify availability.

Clarity Checkpoints

A session palace decays silently: each Populate step can add

ambiguity that only surfaces at Export, when it is too late to

recover the lost state. MMPO (arXiv:2605.30159, Section 3) frames

this as a case for sub-trajectory dense rewards: check intermediate

quality at each transition, not just the final outcome.

At every Checkpoint arrow in the lifecycle above (and before any

Export/Archive), run the dual-probe gate against the current

palace state:

Skill(memory-palace:memory-clarity-probe)

The probe returns a Clarity Assessment with progress/gap verdicts

and a Recommendation:

| Recommendation | Action at the checkpoint |

|----------------|--------------------------|

| Proceed | Palace state is clear; continue the session |

| Expand memory | Add the gap probe's open items to the palace before continuing |

| Regenerate | Flag the session as ambiguous: the progress probe hedges, so reconstruct the current-state room before more work lands on it |

Flagging at the checkpoint, not at export, is the point: an

ambiguous palace caught early costs one room rebuild; caught at

export it costs the session.

When memory-clarity-probe is not installed, ask the two anchor

questions inline (progress: what is done and what state is the task

in; gap: what concrete items remain) and apply the same table.

Detailed Resources

  • Template Details: See modules/templates.md
  • State Management: See modules/templates.md
  • Export Patterns: See modules/templates.md

Integration

  • memory-palace-architect - Export important concepts to permanent palaces
  • knowledge-locator - Search session content
  • digital-garden-cultivator - Seed garden with session insights
  • memory-clarity-probe - Dual-probe clarity gate at session checkpoints

Exit Criteria

  • [ ] A session palace is created with a template and spatial layout

before any state is populated

  • [ ] The dual-probe clarity gate runs at each Checkpoint transition

and before Export/Archive, not only at the end

  • [ ] A checkpoint returning Expand memory or Regenerate is acted

on (gap items added or current-state room rebuilt) before more work

lands, and the ambiguous session is flagged

  • [ ] Exported concepts round-trip into a permanent palace via

memory-palace-architect

Other skills for the same job

different authors, same section of the catalogue
Skill Creator
by anthropics
vendor ×10

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

56k tokens scripts
Skill Creator
by vercel-labs
vendor ×10

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

12k tokens scripts
Skill Creator
by JayZeeDesign
×9

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

10k tokens scripts
Template Skill
by JayZeeDesign
×7

Replace with description of the skill and when Claude should use it.

35 tokens
Dispatching Parallel Agents
by ZhanlinCui
×5

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

2k tokens
Skill Development
by anthropics
vendor ×4

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

9k tokens
Find Skills
by sanity-io
vendor ×4

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

1k tokens
Writing Skills
by ZhanlinCui
×4

Use when creating new skills, editing existing skills, or verifying skills work before deployment

26k tokens scripts

How to use it

Copy the folder

Take athola/session-palace-builder from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.