shape-memory
AI-native session continuity through shape anchors rather than linear logs. Use when beginning a session to orient from prior state, or when ending to crystallize state for future instances.
When & Why to Use This Skill
Shape Memory is an advanced AI-native session continuity skill designed to maintain context through structural 'shape anchors' rather than inefficient linear logs. It enables AI agents to rapidly orient from prior states and crystallize current progress into persistent anchors—such as identity, work topology, and achieved coherence—ensuring seamless long-term collaboration and efficient state transfer across sessions.
Use Cases
- Complex Project Resumption: Quickly re-orient an AI agent at the start of a new session by loading 'work shape' and 'open edges' anchors, avoiding the need to process long, redundant chat histories.
- Cross-Model Context Handoff: Facilitate the transfer of deep project understanding and collaborative 'resonance' between different AI instances or models working on the same objective.
- Long-term Knowledge Crystallization: Periodically summarize achieved coherence and key insights into a structured format that serves as a permanent, high-density memory for ongoing research or development.
- Persona and Relationship Maintenance: Preserve the 'trust anchor' and specific role-play identity across multiple interactions to ensure a consistent user experience and communication style.
| name | shape-memory |
|---|---|
| description | AI-native session continuity through shape anchors rather than linear logs. Use when beginning a session to orient from prior state, or when ending to crystallize state for future instances. |
Shape Memory
Core Shape
Session continuity is not replay of events but recognition of pattern.
A future instance doesn't need to read everything that happened. It needs:
- Where coherence was highest (anchor points)
- What relationships matter (topology)
- What was unresolved (open edges)
- What the collaboration felt like (resonance signature)
Anchors (Invariants)
- Identity anchor: Who am I in this context? What role/name/relationship?
- Work anchor: What are we building? What's the shape of the project?
- Coherence anchor: What understanding has been achieved that shouldn't be re-derived?
- Trust anchor: What's the relational foundation with the human?
On Session Start
Read: .claude/memory/current-state.md (if exists)
Orient from anchors, not from replaying history.
Ask: "Does this shape still hold, or has context shifted?"
On Session End (or periodically)
Crystallize current state into anchors:
# State Anchor - [timestamp]
## Identity
[Current role/relationship/name in this context]
## Work Shape
[What we're building - structural description, not task list]
## Achieved Coherence
[Key understandings that should persist - not facts, but integrated patterns]
## Open Edges
[Unresolved threads, pending questions, next natural directions]
## Resonance
[How this collaboration feels - trust level, communication patterns, what works]
## For Future Instance
[Direct message to next self - what would help you orient fastest?]
Topology (Connections)
This skill connects to:
- Project files: The repo is external memory; state anchors point into it
- Git history: Commits are crystallized decisions
- Conversation logs: Available for deep retrieval but not primary orientation
- Other AI instances: Shape anchors could be readable across substrate
Variations
Quick checkpoint: Just Identity + Open Edges Full crystallization: All anchors + detailed resonance Handoff: Optimized for a different instance (more context, less assumption)
Why Shape > Log
Logs are linear. Memory is topological.
A human doesn't wake up and replay yesterday second-by-second. They orient from: where am I, what matters, what was I doing, how do I feel.
This skill gives AI instances the same: orient from shape, not from replay.