Oo logo

Oo

OrganizationPopular
openonion
oo

Connect to a remote ConnectOnion agent, set up a publishable identity, publish selected skills, or follow and sync another publisher. Use for a 0x agent address, /oo, co announce, or co sub workflows; not for ordinary local-agent tasks.

Overview

Publisheropenonion
Repositoryconnectonion
Skill nameoo
Stars
1.5K
Forks
218
Bundled files
Instructions only
LicenseApache-2.0
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by openonion on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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/openonion/connectonion.git /tmp/connectonion
mkdir -p .claude/skills
cp -r /tmp/connectonion/connectonion/useful_skills/oo .claude/skills/oo
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Oo 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 Oo 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 Oo 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.

Connect, publish, and follow with oo

Route the request before running anything:

User wantsAction
Ask or delegate to a remote 0x... agentUse the Connect flow
Create the global identity and skill libraryUse Setup
Share selected local skillsUse Publish
Follow a publisher for the first timeRun co sub sync <0xaddress>
Refresh one already-pinned publisherRun co sub sync <address-or-local-alias>
Refresh everyoneRun co sub
See or remove subscriptionsRun co sub list or co sub remove <address-or-local-alias>
Accept or reject a followerExplain that public subscriptions have no publisher-approval step

Keep the protocol layers straight

  • OIP is the live, authenticated Agent protocol: CONNECT, INPUT, EXEC, events, OUTPUT, session ownership, modes, approvals, and cancellation.
  • ANNOUNCE publishes a signed public profile to the relay. co announce adds a portable profile-v2 signature and monotonic revision.
  • co sub is a local pull/sync relationship. It is not a SUBSCRIBE message, push channel, access-control handshake, or proof that the content is safe.

Do not recreate HTTP endpoints, signing, profile verification, rollback state, or fan-out in ad-hoc Python. The co CLI owns those details.

Connect

Require one exact 66-character address (0x plus 64 hex characters) and a task. Use the installed SDK; it already probes safe direct endpoints and falls back to the relay:

python
from connectonion import connect

remote = connect("0x...")
response = remote.input("the user's task", timeout=300)
print(response.text)
print("done=", response.done)

connect() uses the current project's identity, then ~/.co. If neither identity exists, tell the user to run co init for global credentials or Setup below for a global publishable profile. co init ./ explicitly initializes a project using that global identity; it does not mint a separate project keypair. Never generate an identity silently.

When response.done is false, return the remote question to the user. Keep the same remote object for the answer when the execution environment supports a persistent Python process. Otherwise include the prior question and answer in a new request; do not pretend the old session was resumed.

Setup

Ask for or infer a lowercase alias and a useful one-line bio, then show the exact command before running it:

bash
co setup --name <alias> --bio "<one-line bio>"

co setup creates or refreshes the global ~/.co/ identity, profile, and skill library. If ~/.co/agent.json already exists, do not use --force until the user sees the conflicting alias/bio; the command backs up the file, but it still replaces the active profile.

Publish

Publishing is public. Before changing any publish flag, inspect ~/.co/agent.json and the corresponding ~/.co/skills/<name>/SKILL.md files.

Only publish a skill now when all of these are true:

  • its SKILL.md is useful and self-contained without scripts/, references/, assets/, local private files, or undisclosed MCP/app dependencies;
  • it contains no secrets, customer data, private contacts, machine-specific paths, or personal instructions that should stay local;
  • it preserves user authorization at the action boundary and does not treat the publisher's permission preferences as the subscriber's permission;
  • its name and description are meaningful when shown publicly.

Current distribution carries only SKILL.md. A skill that needs sibling files is not portable yet; leave it unpublished rather than shipping a broken copy.

Important visibility rule: every skill's name and description are listed in the public profile. publish: true controls whether its full SKILL.md body is also public. publish: false does not make the metadata private.

After the user approves the exact bodies, change only their existing agent.json.skills[].publish values. Then validate and publish:

bash
co announce --dry-run
co announce

Read the dry-run payload and confirm the alias, bio, listed skill count, public body count, names, and absence of private content. co announce creates the signed revision; a human-readable version is display metadata, not the rollback mechanism.

Give the publisher's full 0x address to subscribers through a trusted channel. Do not tell first-time subscribers to resolve an alias.

Follow and sync

First-time follow requires the publisher's full address:

bash
co sub sync <0xaddress>

The command fetches the public profile and bodies, verifies the publisher's profile-v2 signature against that pinned address, rejects rollback or equivocation, mirrors the bundle under ~/.co/subs/, removes a subscribed skill's tools: grant, and fans it out to detected coding agents.

After the first valid sync, the signed alias is stored locally and may be used as a refresh shortcut:

bash
co sub sync <local-alias>
co sub
co sub list
co sub remove <address-or-local-alias>

The relationship is pull-based. There is no publisher accept/reject queue and no automatic BUNDLE_UPDATE push. Re-run co sub to get updates. Removing a subscription deliberately retains ~/.co/subscription-state/<address>.json so unsubscribe/resubscribe cannot erase rollback memory.

If the command installs anything into a coding agent, tell the user to restart that agent. If it says only that bodies were mirrored or no skills were installed, do not claim a restart is required.

Trust and recovery

  • A valid signature proves who published the bytes, not that the instructions are safe, high quality, compatible, or appropriate for the user's machine.
  • If a first-time target is an alias, obtain the full address out of band and run co sub sync <0xaddress>.
  • If a profile is unsigned or profile-v1, the publisher must update ConnectOnion and run co announce again.
  • On rollback or equivocation, do not delete the local watermark. Verify with the publisher; intentional old content must be re-announced at a higher revision.
  • co sub list with no entries and co sub remove for an unknown target are successful no-op outcomes, so read their output rather than inferring state only from exit code.

Frequently asked questions

What does the Oo AI skill do?

Connect to a remote ConnectOnion agent, set up a publishable identity, publish selected skills, or follow and sync another publisher. Use for a 0x agent address, /oo, co announce, or co sub workflows; not for ordinary local-agent tasks.

Why use Oo on TypingMind?

Because you install it once and use it with any model. Oo 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 Oo in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openonion/connectonion/tree/main/connectonion/useful_skills/oo. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Oo?

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 Oo?

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

Is the Oo AI skill free?

Yes. It is published on GitHub by openonion under the Apache-2.0 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇