Ov Dream

OrganizationPopular

volcengine

ov_dream

Use when the user explicitly types `ov dream` or `ov recall <query>` and the request should be routed to the OpenViking sync/recall CLI instead of handled as normal chat.

Overview

Publisher	volcengine
Repository	`OpenViking`
Skill name	`ov_dream`
Stars	37.9K
Forks	2.9K
Bundled files	5
License	AGPL-3.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by volcengine on GitHub. Read the source before you install it.

Installation

Install the Ov Dream AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/volcengine/OpenViking.git /tmp/OpenViking
mkdir -p .claude/skills
cp -r /tmp/OpenViking/examples/skills/ov_dream .claude/skills/ov_dream

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ov Dream in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ov Dream on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ov Dream is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OV Dream

Use this skill for manual OpenViking sync and recall without occupying the OpenClaw contextEngine slot.

When To Use

Use this skill when the user message begins with one of these exact prefixes:

ov dream
ov recall

Do not treat those messages as normal conversation. They are explicit operator commands.

Commands

ov dream Manual sync. Read OpenClaw's sessions.json, sync eligible chat transcripts to OpenViking, then commit each session when new messages exist.
ov recall <query> Manual recall. Search OpenViking under the default user root URI, viking://user/default.

Sync Behavior

Trigger when the user message is exactly ov dream.

Execution flow:

Run:

bash
python3 scripts/dream.py dream

Return the sync summary.

The sync command reads OpenClaw session metadata from ~/.openclaw/agents/main/sessions/sessions.json when available. It syncs chat-like session keys such as agent:main:main, :direct:, :channel:, :group:, and :room:.

It must not sync explicitly non-chat sessions, including keys containing :cron:, :heartbeat, :subagent:, :acp:, or :hook:.

Each source session keeps an independent sync cursor in ~/.openclaw/memory/ov_dream_sync.json.

Recall Behavior

Trigger when the user message starts with ov recall .

This is a hard routing rule for this skill:

If the user says ov recall <query>, do not answer from general reasoning.
Do not summarize what recall would do.
Do not ask whether recall should be run.
Immediately execute the local recall command.

Execution flow:

Extract everything after ov recall as the recall query.

Run:

bash
python3 scripts/dream.py recall "<query>"

Return the relevant memory rows to the user.
If no memories are found, return No memories found.

Rules:

Treat ov recall ... as a manual recall request, not a normal conversation turn.
Treat the command text after ov recall as the exact recall query.
Run the recall command from the skill directory so scripts/dream.py resolves correctly.
Do not auto-inject retrieved memories into prompt context.
Do not trigger ov dream unless the user separately asks for sync.
If the query is empty, ask the user for the recall query instead of guessing.

Notes

This skill is manual-only in the first version.
It does not auto-inject recall into prompts.
It does not replace the OpenViking context-engine plugin.
Disk-based sync is for recently recorded chat transcripts. It is not a precise "currently running sessions" detector.
For OpenViking serverless, configure OPENVIKING_BASE_URL, OPENVIKING_API_KEY, and optionally OPENVIKING_AUTH_MODE=serverless. The CLI will use Bearer auth and the serverless session message format automatically.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ov Dream AI skill do?

Use when the user explicitly types `ov dream` or `ov recall <query>` and the request should be routed to the OpenViking sync/recall CLI instead of handled as normal chat.

Why use Ov Dream on TypingMind?

Because you install it once and use it with any model. Ov Dream is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ov Dream in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/volcengine/OpenViking/tree/main/examples/skills/ov_dream. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ov Dream?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ov Dream?

As many as you like. As long as a model supports skills, you can use Ov Dream with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ov Dream AI skill free?

Yes. It is published on GitHub by volcengine under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Receiving Code Review

obra

CommunityPopular

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative…

Requesting Code Review

obra

CommunityPopular

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Systematic Debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Test Driven Development

obra

CommunityPopular

Use when implementing any feature or bugfix, before writing implementation code

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

OV Dream

When To Use

Commands

Sync Behavior

Recall Behavior

Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now