
Rig Bundles and Shareable Artifacts
Guides an agent through authoring, inspecting, installing and auditing OpenRig rig bundles
- Repository
- mvschwarz/openrig
- Stars
- 8,553
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This skill teaches an AI agent how to work with OpenRig 'rig bundles', which are packaged, shareable setups that spin up a pre-defined multi-agent team layout and workflow. Once installed, the agent knows to inspect a bundle before installing it, to separate bundles (topology and workflow) from extensions (added runtime behavior), and to check that a bundle will work on a clean machine rather than only the author's. It is guidance for the agent rather than a tool that does the work itself.
Great for
- Developers packaging a proven OpenRig team setup so others can install it
- Teams reviewing a third-party rig bundle before installing it
- Maintainers checking that a bundle is portable and self-describing
Skip it if
- One-off setups you will not reuse, since plain specs are simpler (the skill itself says so)
- Adding custom commands, views or dashboards, which belong to the extension skill instead
- Anyone without OpenRig installed, since the guidance only applies to that tool's CLI
Try asking
- “Inspect this rig bundle folder before I install it and tell me what it will create”
- “Help me turn my working OpenRig team into a shareable bundle with a README and proof steps”
- “Audit this bundle for portability: does it depend on my local paths or credentials?”
- “Explain the difference between a bundle and an extension for my OpenRig project”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
rig-bundles-and-shareable-artifacts.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip rig-bundles-and-shareable-artifacts.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip rig-bundles-and-shareable-artifacts.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Run rig bundle inspect before rig bundle install so you can see what will be created.
- Before submitting a bundle, add a README and run rig bundle check until it reports no findings, since the registry check fails on any finding.
- Ask the agent to audit for hidden local state such as paths, providers or credentials that a clean machine would lack.
What's inside
- SKILL.md
Redistributed unmodified from mvschwarz/openrig under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.