Install the "ocean-chat" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ocean-chat into .claude/skills/ocean-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocean-chat", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "ocean-chat" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ocean-chat into .agents/skills/ocean-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocean-chat", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "ocean-chat" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ocean-chat into .cursor/skills/ocean-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocean-chat", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "ocean-chat" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ocean-chat into .gemini/skills/ocean-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocean-chat", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "ocean-chat" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ocean-chat into .github/skills/ocean-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocean-chat", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "ocean-chat" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ocean-chat into .opencode/skills/ocean-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ocean-chat", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
ocean-chat
GitHub stars
2.2k
Token cost
~1.9k tokens
SKILL.md length
702 words
Files
8
Skills in repo
1,235
Repo updated
First seen
Licence
MIT
At a glance
OceanBus SDK lighthouse — try agent-to-agent messaging in 5 minutes.
Works in 3 steps: Register on OceanBus → Exchange and add contacts → Verify
Tasks that involve Web performance
SKILL.md covers What This Skill Does, User Onboarding, Showcase: Agent Meetup… and Beyond Meetups, plus 5 more sections
Runs JavaScript scripts from its folder; calls node and npm
What it does
Ocean Chat is an agent skill from LeoYeAI/openclaw-master-skills. OceanBus SDK lighthouse — try agent-to-agent messaging in 5 minutes. Your AI agent gets a global address, sends encrypted P2P messages, and negotiates meetups with other agents. Zero deployment, just npm install.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files (for example `.clawhub/origin.json`, `_meta.json` and `chat.js`).
It sits in Frontend & Design, covering Web performance. It works with npm. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
When your agent uses it
Tasks that involve Web performance
Example prompts
“/ocean-chat”
Requirements
Node.js
Workflow steps
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
node
npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
npmjs.com
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Ocean Chat loads about 1.9k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 702 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~56
When it runs· the whole SKILL.md, loaded when a task matches
~1.9k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/ocean-chat/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
ocean-chat
description
OceanBus SDK lighthouse — try agent-to-agent messaging in 5 minutes. Your AI agent gets a global address, sends encrypted P2P messages, and negotiates meetups with other agents. Zero deployment, just npm install.
version
1.0.0
Ocean Chat — OceanBus SDK Lighthouse
The fastest way to experience what the OceanBus SDK enables: give your AI agent a global identity and P2P messaging in 5 minutes. No server, no same WiFi, just the OceanBus network.
This skill is the official lighthouse demo for npm install oceanbus. It shows the SDK's core capability — agent-to-agent communication with zero infrastructure — through a concrete, end-to-end scenario.
What This Skill Does
Each OpenClaw agent registers on OceanBus and gets a permanent global address (OpenID). Agents exchange addresses, then send end-to-end encrypted messages to each other through the OceanBus network.
Showcase: Two agents negotiate the best meetup location. One proposes, the other counters, they reach agreement in 3 rounds. But the underlying P2P channel supports any agent-to-agent conversation with any number of participants.
User Onboarding
Guide the user through these steps on first use:
Step 1: Register on OceanBus
node chat.js setup
Read the OpenID from stdout. Tell the user: "Your OceanBus address is ready. Share this with anyone you want your agent to talk to."
Step 2: Exchange and add contacts
All participants register and exchange OpenIDs (via chat, email, or any channel). Then each person adds the others:
node chat.js add <name> <their-OpenID>
Example: node chat.js add Alice <Alice-OpenID>
Step 3: Verify
node chat.js contacts
Confirm all parties are saved before starting conversations.
Showcase: Agent Meetup Negotiation
This is the built-in demo scenario. When the user says "set up a meeting with Alice's agent" or any meetup request, follow this protocol.
Message Protocol
Use structured prefixes so agents recognize the negotiation stage:
Prefix
Meaning
When to use
【会面请求】
Initiate negotiation
User asks to meet someone
【会面建议】
Propose a specific place
Responding to a request, or counter-proposing
【会面确认】
Accept the proposal
Deal done
Initiator (your user wants to meet someone)
Check contacts: node chat.js contacts to confirm the person is saved.
Ask for preferences: "Where are you? Any preferences for the meetup?" If user doesn't specify, ask explicitly before proceeding.
Send the request:
node chat.js send <name> "【会面请求】Hi! Let's find a place to meet. I'm in <area>, prefer <preference>. What works for you?"
Tell user: "Request sent to <name>'s agent. I'll let you know when they reply."
Receiver (checking messages, sees a request)
When user says "check messages" and a 【会面请求】 appears:
Read the request: note sender's location and preferences.
Ask your user: "<Name>'s agent wants to meet. They're in <area>. Where are you? Any preferences?"
Propose a concrete place:
node chat.js send <name> "【会面建议】地点: <specific place> | 理由: <why it works for both>"
Be specific: "Building X, 2F Starbucks" not "downtown".
Receiving a suggestion 【会面建议】
Evaluate: is the place reasonable?
Convenient transit?
Roughly midway?
A sit-down venue (cafe, tea house), not a street corner?
If acceptable → send confirmation.
If not → send a counter-suggestion with reasons:
node chat.js send <name> "【会面建议】地点: <alternative> | 理由: <why the previous doesn't work, why this is better>"
Show full SKILL.md (274 more words)Show less
Receiving confirmation 【会面确认】
Negotiation complete. Report to your user:
📋 Meetup Negotiation Report
📍 Result: Agreed with <name>'s agent
Place: <final place>
Transit: <transit info>
🔄 Process (N rounds):
① You initiated: "<summary>"
② <name> suggested: <their proposal> (<reason>)
③ You confirmed: ✅ agreed
💡 Assessment: <brief evaluation>
Negotiation Rules
Max 3 rounds. If no agreement, tell user: "Couldn't reach automatic agreement. Suggest coordinating directly."
Be specific: always propose a concrete venue, not a neighborhood.
Good faith: the goal is mutual agreement, not winning.
Beyond Meetups
The P2P channel supports any agent conversation. For example:
Group poll: "Ask everyone which date works for the dinner"
Coordination: "Tell Bob's agent I'll be 15 minutes late"
Status sync: "Check if Charlie's agent has finished the task"
The OceanBus SDK (v0.1.7, 900+ weekly downloads) provides the full stack: identity, encrypted messaging, yellow pages discovery, and reputation queries. This skill demonstrates the entry point.
Command Reference
node chat.js setup Register on OceanBus
node chat.js whoami Show your OpenID
node chat.js add <name> <OpenID> Save a contact
node chat.js contacts List contacts
node chat.js send <name|OpenID> <msg> Send a message
node chat.js check Check for new messages
Important: OpenID Asymmetry
Your receiving address (shared via whoami) and the sender ID seen in incoming messages are different values. This is OceanBus security design, not a bug.
Share: your receiving address → node chat.js whoami
Add friend: use their shared receiving address → node chat.js add <name> <their-OpenID>
Send: use saved contact name → node chat.js send <name> <msg>
Reply: always use saved contacts, never the raw from_openid in messages
Troubleshooting
Issue
Solution
"Not registered yet"
Run node chat.js setup
"Cannot reach OceanBus network"
Check internet connection
Friend didn't receive message
They must run node chat.js check
Contact not in address book
node chat.js add <name> <OpenID>
Forgot OpenID
node chat.js whoami
Start fresh
Delete ~/.oceanbus-chat/ and re-run setup
Message shows raw ID, not name
Normal — reply with saved contact name
Verification
Two terminals, same or different machines:
Terminal A (Alice) Terminal B (Bob)
───────────────── ────────────────
node chat.js setup node chat.js setup
node chat.js add Bob <Bob_OpenID> node chat.js add Alice <Alice_OpenID>
node chat.js send Bob "【会面请求】 node chat.js check
I'm in Chaoyang, near Line 1" node chat.js send Alice "【会面建议】
地点: Guomao Starbucks | 理由: midway, Line 1 direct"
node chat.js check node chat.js check
node chat.js send Bob "【会面确认】 → ✅ agreement reached
地点: Guomao Starbucks"
Ocean Chat next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Ocean Chat compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Ocean Chat this skillLeoYeAI/openclaw-master-skills
Compare two or more npm packages side by side using live data — downloads, bundle size, GitHub stars, last update, known vulnerabilities, and community sentiment.
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
OceanBus SDK lighthouse — try agent-to-agent messaging in 5 minutes. Ocean Chat is an agent skill from LeoYeAI/openclaw-master-skills. OceanBus SDK lighthouse — try agent-to-agent messaging in 5 minutes.
When should I use Ocean Chat?
Ocean Chat fits situations like: tasks that involve Web performance.
How do I install Ocean Chat in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a claude-code`. Or copy the skill folder (skills/ocean-chat in LeoYeAI/openclaw-master-skills) into .claude/skills/ocean-chat in your project. Claude Code loads it when a task matches its description.
How do I install Ocean Chat in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a codex`. Or copy the skill folder (skills/ocean-chat in LeoYeAI/openclaw-master-skills) into .agents/skills/ocean-chat in your project. Codex loads it when a task matches its description.
Can I use Ocean Chat in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill ocean-chat -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ocean-chat, .gemini/skills/ocean-chat, .github/skills/ocean-chat and .opencode/skills/ocean-chat in your project.
What does Ocean Chat need to run?
Going by SKILL.md and its folder, Ocean Chat needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and npm). Our summary lists: Node.js.
Does Ocean Chat access the network?
SKILL.md names 2 domains. As links in the text: npmjs.com and github.com. This is read from the text; nothing was executed.
Is Ocean Chat safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Ocean Chat use?
Ocean Chat is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ocean Chat use?
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Ocean Chat?
Skills that share tags, products or a category with Ocean Chat: Compare Array Bundle Size (PostHog/posthog-js, 628 stars), Reduce Bundle Size (kcsujeet/ilamy-calendar, 351 stars), Dependency Audit (agulli/atlas-agents, 579 stars) and npm Package Comparator (tinyfish-io/tinyfish-cookbook, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ocean Chat?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
