team-skills

Start the development server in background mode

Start dev server and interact with the platform via agent-browser. Use when user asks to browse, test, or demo the platform UI, connect services, or perform any browser-based interaction with the local dev environment.

Reset turbo environment (clean node_modules, reinstall, sync DB)

Check if a PR, commit, or tag has been deployed to production

Query, investigate, and manage Sentry issues for debugging and incident response

Create or update a PR and hand it off to a coding agent worker via load balancing. Removes pending label if present, then assigns a worker.

Query logs from Axiom for debugging (read-only, no ingestion allowed)

Implement issue, review PR, and verify CI — runs issue-implement, pr-review-loop, and pr-check-loop sequentially

Deep brainstorming and solution exploration based on research findings

Create concrete implementation plan based on research and innovation findings

Deep research and information gathering before any implementation discussion

Continue working on GitHub issue — implement code and create PR

Start working on GitHub issue with deep-dive workflow (research, innovate, plan phases)

Review a pull request and post findings as a PR comment

Start an adaptive coding loop that dynamically adjusts interval based on activity — short intervals when busy, longer when idle.

Generate UI design variants for a GitHub issue. Snapshots baseline pages, creates 3 solution variants, publishes to GitHub Pages, and comments on the issue.

Authenticate with local development server and get CLI token

View development server logs with optional filtering

Full dev setup with tunnel (automatic) and CLI authentication

Deploy runner to metal host for local development. Use when user needs to run agents (CLI, frontend sessions, scheduled jobs) with local dev server.

Analyze conversation history for dev server errors and create a structured GitHub bug report

Monitor PR CI pipeline, auto-fix issues, and loop until all checks pass

Monitor merge queue until PR is successfully merged into main, auto-recovering from conflicts and queue ejections

Iteratively review PR, post comment, fix issues, and re-review until LGTM

Review PR, fix CI issues, and merge to main — runs pr-review-loop, pr-check-loop, and pr-merge-loop sequentially

Consolidate GitHub issue discussion into clean body for handoff

Implement changes to team-skills repo based on deep-dive research, innovation, and plan findings

Clone team-skills repo and deep-research its skills, plugins, and architecture

Test runner profiles and VM sandbox on metal hosts using dev-runner.sh (deploy-local, submit, exec)

Local testing setup - start dev server with mock Claude and run tests (unit tests, CLI E2E)

Switch to main branch and pull latest changes

List open issues created by or assigned to the current user, deduplicated and prioritized.

Rebase current branch onto origin/main and resolve conflicts

Create GitHub issues from conversation context (general, bug reports, or feature requests)

Check PR CI pipeline status and auto-fix lint/format issues (single pass, no loop)

PR lifecycle management - create PRs with proper commits, merge with validation, and manage PR comments

Create a new skill in an existing or new plugin in the team-skills marketplace repo.

Fix bugs in the forked release-please ecosystem (vm0-ai/release-please + vm0-ai/release-please-action)

Create command aliases for skills with arguments

Migrate skills (and their script dependencies) from the current project into a plugin in the team-skills marketplace repo.