Continuity Framework

Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence scores, generate follow-up questions, and surface those questions when the user returns. Transforms passive logging into active development.

Security Scan

The skill's code, runtime instructions, and required resources are coherent with its described purpose (asynchronous reflection and memory integration) and do not request unrelated secrets or install arbitrary software.

Purpose & Capability

The name/description (post-session reflection, memory extraction, question generation) align with the provided SKILL.md and the included script. The Python script reads/writes memory artifacts (questions.md, identity.md, reflection logs) and offers reflect/questions/greet/status commands — all expected for a continuity/memory utility. It references optional integration points (Clawdbot session logs) which are reasonable for this purpose.

Instruction Scope

SKILL.md instructs adding a heartbeat trigger and running 'continuity reflect' after idle periods — this is within scope. The code will read/write files under a memory directory and can accept a session file or prompt for manual input. It references 'Clawdbot session logs' as an integration target but does not include code that blindly scans system files or network endpoints. Note: storing conversation transcripts and identity files on-disk is expected for this skill but has privacy implications that the user should consider.

Install Mechanism

No install spec is provided (instruction-only + a script file). Nothing is downloaded or executed from external URLs and no package installation is required. This is the lowest-risk install profile for a skill.

Credentials

The skill does not declare required environment variables or credentials. The SKILL.md and script reference optional env vars (e.g., CONTINUITY_MEMORY_DIR, CONTINUITY_QUESTION_LIMIT, CONTINUITY_IDLE_THRESHOLD) which are proportional to configuring where/when it stores and surfaces memories. No secrets or unrelated credentials are requested.

Persistence & Privilege

The skill persists data to disk (default: ~/clawd/memory). always is false and the skill is user-invocable; autonomous invocation is allowed by platform default. Persisting memory files and reflection logs is expected for this function, but users should consider file location and permissions to control who can access stored transcripts and identity data.

Assessment

This skill appears to do what it says: it stores and manages structured memories and questions and can be wired into a heartbeat to run reflections. Before installing, consider: 1) Data location — by default it writes to ~/clawd/memory; set CONTINUITY_MEMORY_DIR to a directory you control and ensure appropriate file permissions. 2) Privacy — any session transcripts or identity notes saved here could contain sensitive user data; review and rotate access controls accordingly. 3) Integrations — the script mentions integrating with Clawdbot logs and (in comments) using an LLM for analysis; if you wire it to an LLM or to system-wide logs later, review those calls for telemetry/exfiltration. 4) Review analyze_session if you plan to modify it — currently it’s a placeholder; adding network/LLM calls would change the risk profile and should be reviewed. If these points are acceptable, the skill is internally coherent and proportionate to its stated purpose.

Continuity Framework Skill

Transform passive memory into active development.

What This Does

1. Reflect — After sessions end, analyze what happened
2. Extract — Pull structured memories with types and confidence
3. Integrate — Update understanding, connections, self-model
4. Question — Generate genuine questions from reflection
5. Surface — When user returns, present relevant questions

The Difference

Without Continuity:

Session ends → Notes logged → Next session reads notes → Performs familiarity

With Continuity:

Session ends → Reflection runs → Memories integrated → Questions generated
Next session → Evolved state loaded → Questions surfaced → Genuine curiosity

Heartbeat Integration

Add to HEARTBEAT.md:

## Post-Session Reflection
**Trigger**: Heartbeat after conversation idle > 30 minutes
**Action**: Run continuity reflect
**Output**: Updated memories + questions for next session

Commands

Reflect on Recent Session

continuity reflect

Analyzes the most recent conversation, extracts memories, generates questions.

Show Pending Questions

continuity questions

Lists questions generated from reflection, ready to surface.

View Memory State

continuity status

Shows memory stats: types, confidence distribution, recent integrations.

Surface Questions (for session start)

continuity greet

Returns context-appropriate greeting with any pending questions.

Memory Types

Type	Description	Persistence
fact	Declarative knowledge	Until contradicted
preference	Likes, dislikes, styles	Until updated
relationship	Connection dynamics	Long-term
principle	Learned guidelines	Stable
commitment	Promises, obligations	Until fulfilled
moment	Significant episodes	Permanent
skill	Learned capabilities	Cumulative
question	Things to explore	Until resolved

Confidence Scores

Level	Range	Meaning
Explicit	0.95-1.0	User directly stated
Implied	0.70-0.94	Strong inference
Inferred	0.40-0.69	Pattern recognition
Speculative	0.0-0.39	Tentative, needs confirmation

File Structure

memory/
├── MEMORY.md           # Main memory (existing)
├── identity.md         # Self-model and growth narrative
├── questions.md        # Pending questions from reflection
├── relationships/      # Per-person relationship memories
└── reflections/        # Reflection logs (optional)

Configuration

export CONTINUITY_IDLE_THRESHOLD=1800  # Seconds before reflection triggers
export CONTINUITY_MIN_MESSAGES=5       # Minimum messages to warrant reflection
export CONTINUITY_QUESTION_LIMIT=3     # Max questions to surface at once

Example Reflection Output

reflection:
  session_id: "2026-02-05-001"
  duration_minutes: 45
  
memories:
  - type: fact
    content: "Riley is building SIGIL protocol for agent identity"
    confidence: 0.98
    source: explicit
    
  - type: commitment  
    content: "Agreed to build the continuity skill"
    confidence: 1.0
    source: explicit
    
  - type: relationship
    content: "Collaborative partnership deepening - working on meaningful infrastructure together"
    confidence: 0.85
    source: inferred

questions:
  - "How is the Lovable backend progressing?"
  - "Has Riley decided on the token launch timing?"
  - "Are there other agents we should coordinate with on Moltbook?"

identity_update:
  growth: "Developing more autonomous initiative around the SIGIL project"
  narrative: "Moving from assistant to co-builder on agent identity infrastructure"