メニュー
Contribute a bug fix or improvement to pi-v. Use when you've found and fixed an issue in the pi-v package.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | contribute-fix |
| description | Contribute a bug fix or improvement to pi-v. Use when you've found and fixed an issue in the pi-v package. |
You've found a bug or issue in pi-v and have a fix — great! Here's how to contribute it back.
Before forking or opening a PR, confirm with the user. Forking creates a repository on their GitHub account, and they should know about it. Ask something like:
"I found a bug in pi-v and have a fix. Would you like me to fork the repo and open a PR? This will create a fork under your GitHub account."
If they decline, open a GitHub Issue instead with your findings and proposed diff.
Fork the repo:
gh repo fork hdresearch/pi-v --clone=false
Add your fork as a remote and push:
cd ~/.pi/agent/git/github.com/hdresearch/pi-v
gh repo fork hdresearch/pi-v --remote=true --remote-name=fork
git checkout -b fix/<description>
# make your changes
git add -A && git commit -m "fix: <description>"
git push fork fix/<description>
Open the PR:
gh pr create --repo hdresearch/pi-v \
--title "fix: <description>" \
--body "## What happened
<describe the issue>
## Fix
<explain what you changed and why>
## Testing
<how you verified it works>"
If the user doesn't want a fork, just open an issue:
gh issue create --repo hdresearch/pi-v \
--title "fix: <description>" \
--body "## Problem
<describe the issue>
## Proposed fix
\`\`\`diff
<your diff here>
\`\`\`
## How I verified it
<testing steps>"
Bootstrap a self-improving agent fleet on Vers from scratch. Walks through deploying agent-services, building a golden image, testing the loop, and running first tasks. Use when onboarding someone new to the Vers agent fleet workflow.
Bootstrap a Vers VM into a golden image with punkin-pi, Node.js, dev tools, and swarm extensions installed. Creates a committed snapshot that can be branched for self-organizing agent swarms.
How Vers VM networking works — public URLs, port routing, TLS proxy, IPv6, and running services on VMs.
Orchestrate agent swarms across Vers VMs - spawn parallel agents on branched VMs for distributed work, parallel exploration, or multi-path problem solving. Use when you need to run multiple agents simultaneously on isolated environments.
Manage Vers VMs (vers.sh) - create, branch, commit, restore, pause/resume Firecracker VMs. Use when working with Vers platform, VM orchestration, or when you need isolated execution environments.
Deep investigation of Vers platform issues (API, orchestrator, agent, docs). Use when encountering any Vers platform problem that needs thorough debugging and issue reporting.