What makes OpenClaw Continuity notable?

1.2K downloads. Trust evidence available

How should OpenClaw Continuity be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

OpenClaw Continuity

Structured continuity and follow-up skill for OpenClaw agents. Use when an agent needs to decide whether natural user dialogue should stay as casual chat, be... Skill: OpenClaw Continuity Owner: redwakame Summary: Structured continuity and follow-up skill for OpenClaw agents. Use when an agent needs to decide whether natural user dialogue should stay as casual chat, be... Tags: carryover:2.0.21, continuity:2.0.21, follow-up:2.0.21, latest:2.0.21, memory:2.0.21 Version history: v2.0.21 | 2026-04-27T23:58:39.524Z | user OpenClaw Continuity 2.0.21 - Fixed ClawHub registry metad

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

2.0.21

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 2.0.21release · observed Apr 27, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1752d2d37r7kps0axxb1k71gx83k8rj:openclaw-continuity

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-redwakame-openclaw-continuity/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: personal-hooks
description: >-
  Structured continuity and follow-up skill for OpenClaw agents. Use when an
  agent needs to decide whether natural user dialogue should stay as casual
  chat, become staged memory, or become tracked follow-up with carryover,
  closure, cooldown, sleep/rest suppress, routine-aware wording, quiet-hours
  behavior, traceability, and release-grade frontstage safety guards. This
  package is not a generic cron sender. It uses context, causal state, and
  explicit lifecycle rules to decide whether care or follow-up should appear at
  all. It covers parked topics, watchful states, delegated tasks, sensitive
  events, candidate to incident to hook flow, /new carryover, deterministic
  onboarding/guided settings, and time-aware continuity guards. It does not
  include always-on idle/social nudging as a default feature.
version: 2.0.21
homepage: https://github.com/redwakame/openclaw-continuity
os:
  - darwin
  - linux
requires:
  bins:
    - python3
  env:
    - OPENCLAW_STATE_DIR
    - OPENCLAW_CONFIG_PATH
metadata:
  openclaw:
    os:
      - darwin
      - linux
    requires:
      bins:
        - python3
      env:
        - OPENCLAW_STATE_DIR
        - OPENCLAW_CONFIG_PATH
    envVars:
      - name: OPENCLAW_STATE_DIR
        description: "Required path to the dedicated OpenClaw state directory used by this skill for continuity state."
        required: true
      - name: OPENCLAW_CONFIG_PATH
        description: "Required path to the OpenClaw config file used for setup validation."
        required: true
---

# OpenClaw Continuity

Use this skill as a continuity/follow-up layer on top of an existing OpenClaw agent. Keep the agent's soul/persona intact and let this skill own the structured follow-up mechanics.

Public product name: `OpenClaw Continuity`.
Technical package / slug: `personal-hooks`.
Internal diagnostics may still use `staged-followup-memory` as a status label for continuity state surfaces.
Questions, feedback, or implementation discussion: `[email protected]`.
如果你期待這個技能持續優化與維護，請在 GitHub 給星支持：https://github.com/redwakame/openclaw-continuity

## V2 public scope

- Route turns into `casual_chat`, `staged_memory`, or `tracked_followup`.
- Classify tracked content into:
  - `parked_topic`
  - `watchful_state`
  - `delegated_task`
  - `sensitive_event`
- Maintain `event_chain` summaries with:
  - `context_before`
  - `event_core`
  - `immediate_result`
  - `followup_focus`
- Maintain `causal_memory` as structured continuity state with:
  - `facts`
  - `state`
  - `open_loop`
  - `time_anchor`
  - `followup_focus_code`
  - `writeback_policy`
- Promote `candidate -> incident -> hook`.
- Preserve `/new` carryover from the previous 3-5 turns and let the user
  choose which continuity anchor leads a new conversation.
- Preserve voice/image discussion style as a host-neutral preference when the
  OpenClaw host already supports those modalities. This skill records the
  preference only; it does not bund

README.md

# OpenClaw Continuity

Make OpenClaw remember the right thing, reconnect the right topic after `/new`,
and follow up naturally without leaking internal state into chat.

`OpenClaw Continuity` is the public product name for the `personal-hooks` skill
package. It is a **skill-layer continuity engine** for an existing OpenClaw
agent: it does not replace the agent's persona, and it does not bundle a
chat-platform adapter.

![OpenClaw Continuity product story](assets/publish/product-story-bilingual.svg)

## Four Quick Comics

These four panels show the parts that matter most after someone installs the
skill: guided setup, later adjustment, natural-language setting changes, and
precise command changes.

![Install and setup wizard](assets/publish/comic-01-setup-wizard.svg)

![Adjust settings anytime](assets/publish/comic-02-adjust-anytime.svg)

![Natural-language setting changes](assets/publish/comic-03-natural-language-settings.svg)

![Precise command setting changes](assets/publish/comic-04-command-settings.svg)

## For Everyone

Most agents can answer a message. The harder part is remembering what still
matters after an interruption, a delayed reply, or a new conversation.

OpenClaw Continuity helps an agent:

- keep ordinary chat light
- stage "let's talk about this later" without losing it
- track important follow-up without chasing every casual sentence
- reconnect the right topic after `/new`
- understand time with sleep/wake and routine context
- let the user adjust behavior in natural language

中文簡介：

OpenClaw Continuity 是替 OpenClaw 補上「延續感、時間感、關心與追蹤」的技能包。
它不是單純排程發訊息，也不是把所有對話都硬塞進記憶。它會分辨哪些只是一般聊天，
哪些要暫存，哪些真的需要追蹤，並在新開對話時接回使用者選定的承接方式。

## What It Feels Like

Example:

```text
User: I need to pause this repo release check. Let's continue later.
Agent: Got it. I will keep the release check as the thread to continue.

/new

Agent: I still have the release check thread. Do you want to pick it up from
the last user intent, the follow-up focus, or the recent conversation summary?
```

中文例子：

```text
使用者：這個技能上架檢查先放著，晚點再接。
Agent：好，我先把這段接住，不會當成一般閒聊丟掉。

/new

Agent：前面那段技能上架檢查我還接得住。現在要從最後意圖、追蹤焦點，
還是最近 4 輪摘要開始？
```

The exact wording still belongs to the host agent's persona. This skill supplies
the structured continuity state that makes the answer possible.

## Minimal Telegram/TG Showcase

Telegram/TG can be used as a small live showcase **when your OpenClaw host is
already connected to Telegram**. The skill does not bundle a Telegram adapter or
bot setup; it only supplies the continuity behavior that the host sends through
its normal reply pipeline.

Demo flow:

```text
TG user: 這個上架檢查先放著，晚點再接。
Agent: 好，我先幫你接住這條線，不會當成普通閒聊丟掉。

TG user: /new
Agent: 前面那個上架檢查我還接得住。要從最近 4 輪、最後意圖，還是追蹤焦點接？

TG user: 新對話改成看最後使用者意圖。
Agent: 已更新。之後新對話會優先從最後使用者意圖承接。
```

What this demonstrates:

- `/new` carryover
- staged memory instead of forced tracking
- natural-language settings update
- frontstage text stays user-facing, not internal runtime text

## Core Features

- **New convers

_meta.json

{
  "ownerId": "kn77md9ahr1tc0zvhm9pvda7w9822n9k",
  "slug": "openclaw-continuity",
  "version": "2.0.21",
  "publishedAt": 1777334319524
}

references/modules.md

# V2 module map

## Core

- continuity routing
- staged memory promotion
- tracked follow-up
- carryover
- closure consistency
- frontstage safety

## State layer

- `profile.json`
- `user_model.json`
- `emotion_state.json`
- `persona_state.json`
- `memory_rank.json`
- `autonomy_state.json`
- `settings.json`

## Event layer

- `candidate_buffer.json`
- `incidents.json`
- `hooks.json`
- `session_memory_staging.json`

## Trace layer

- `followup_trace.jsonl`
- `candidate_buffer_audit.jsonl`
- `session_memory_staging_audit.jsonl`
- `hook_completion_audit.jsonl`
- `frontstage_guard_log.jsonl`

## Public V2 tracked event types

- `parked_topic`
- `watchful_state`
- `delegated_task`
- `sensitive_event`

## Optional and host-boundary items

- host delivery concerns
- provider/network transport concerns
- optional rhythm or nudge layers

references/templates.md

# Frontstage notes

This file stays intentionally small. V2 does not own persona design; it protects continuity-facing frontstage behavior and keeps internal reasoning out of user-visible text.

## V2 frontstage rules

- keep frontstage text in natural Traditional Chinese
- avoid exposing hook, schedule, checker, runtime, or internal-source language to the user
- avoid unresolved fragments that require the user to guess what `這個` or `that` refers to
- avoid false closure when no concrete continuity anchor exists
- apply sleep/rest suppress only to follow-up behavior, not to ordinary user-facing replies

## V2 follow-up tone boundaries

- `emotional_followup`: accompany first, ask lightly
- `health_followup`: check condition gently, do not sound like generic health advice
- `progress_followup`: continue a parked task or topic without sounding like a manager reminder
- `tomorrow_check`: light next-step reminder with human warmth

## Optional note

Rhythm or nudge variants belong to optional layers. They are not part of the public V2 default unless a host explicitly enables and supports them.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.