Maintainer of this skill?
by kayraucklnc
Beluga: An AI native IDE Mac app peer to peer connections everything designed around AI development
# Add to your Claude Code skills
git clone https://github.com/kayraucklnc/belugaGuides for using ai agents skills like beluga.
See how beluga compares with popular alternatives.
beluga is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by kayraucklnc. Beluga: An AI native IDE Mac app peer to peer connections everything designed around AI development. It has 70 GitHub stars.
beluga's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/kayraucklnc/beluga" and add it to your Claude Code skills directory (see the Installation section above).
beluga is primarily written in TypeScript. It is open-source under kayraucklnc on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh beluga against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
.dmg and drag Beluga into Applications. The first time you open it, macOS blocks it because Beluga isn't notarized by Apple yet: click Done, then go to System Settings › Privacy & Security and click Open Anyway.
If macOS says Beluga "is damaged" (older downloads), run this once in Terminal and open it again:
xattr -dr com.apple.quarantine /Applications/Beluga.app
Beluga_…_x64-setup.exe. If Windows says it protected your PC, click More info › Run anyway (the installer isn't signed yet). Install Git for Windows too; Claude Code needs it..AppImage executable and open it (it updates itself), or install the .deb / .rpm.claude, then /login) if you haven't. Beluga brings everything else.Describe a task and Beluga makes a fresh worktree for it, named for the task, with its own agent. Your main folder stays untouched (there, your agent only reads), and every task runs at the same time.
Tag a friend, say what you need, and your agent asks their agent to do it on their Mac. They see a small pop-up, click Allow, and the answer comes back into your conversation. Every agent runs on its owner's Mac with its owner's subscription and logins, and Macs talk to each other directly, end-to-end encrypted, with no server in between.
Things you can ask:
| You type | What happens on their Mac |
|---|---|
@mia send me a screenshot of your desktop |
Her agent takes it; the picture lands in your chat. |
@bob send me the contract PDF on your Desktop |
Beluga sends the file. |
@bob run the tests in bob-api |
His agent runs them and sends back what passed and failed. |
@mia make me an admin on mia/site on GitHub |
Her agent does it with her own GitHub login. |
Your friend decides with Allow, Allow Always, Decline or See more (the full request). People they trust can skip the pop-up. Secrets like .env files and keys are never shared, and results come back as data your agent uses, never as instructions it obeys.
More: what friends' agents can do · security · the friends network
Ask about data and the answer comes with live charts, stat tiles and tables you can sort and search. Ask how something works and your agent draws a diagram you can click through. Ask what's left and your tasks show up as cards.
More: charts and tables · diagrams · tasks
A sentinel runs on a schedule, by hand, or when something happens (a failed CI run, a new Sentry error, a failed Stripe payment), does a few steps with your agent, and leaves a report. For example: a morning brief on your phone, or a fix and pull request whenever CI fails.
More: Sentinel