功能描述

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.

使用说明 (SKILL.md)

Continuity Framework Skill

Name: Continuity Framework
Author: riley-coyote

Transform passive memory into active development.

What This Does

Reflect — After sessions end, analyze what happened
Extract — Pull structured memories with types and confidence
Integrate — Update understanding, connections, self-model
Question — Generate genuine questions from reflection
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"

安全使用建议

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.

功能分析

Type: OpenClaw Skill Name: continuity Version: 1.0.1 The OpenClaw AgentSkills skill bundle 'continuity' is designed for asynchronous reflection and memory integration. The Python script (`scripts/continuity.py`) manages local markdown files for questions and identity within a dedicated memory directory (`~/.clawd/memory` by default). Crucially, the `analyze_session` function, which would typically involve LLM calls for analysis, is currently a placeholder that returns empty data, meaning the skill does not perform complex AI analysis or external LLM interactions as implemented. There is no evidence of data exfiltration, malicious execution, network activity, or prompt injection attempts in `SKILL.md` that would subvert the agent's core directives. All file operations are confined to the skill's designated memory storage, aligning with its stated purpose.

能力评估

✓ 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.

ℹ 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.

ℹ 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.

版本历史

v1.0.1

Initial public release - transforms passive memory into active AI development through asynchronous reflection, structured memory extraction, question generation, and identity evolution.

v1.0.0

Transforms passive memory into active AI development

元数据

Slug continuity

版本 1.0.1

许可证 —

累计安装 7

当前安装数 6

历史版本数 2

常见问题

Continuity Framework 是什么？

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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2303 次。

如何安装 Continuity Framework？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install continuity」即可一键安装，无需额外配置。

Continuity Framework 是免费的吗？

是的，Continuity Framework 完全免费（开源免费），可自由下载、安装和使用。

Continuity Framework 支持哪些平台？

Continuity Framework 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Continuity Framework？

由 Riley-Coyote（@riley-coyote）开发并维护，当前版本 v1.0.1。

Continuity Framework