인프라·DevOps 스킬

Check a gbrain installation after a restart or when services seem broken. It tests key components, repairs some local problems, checks OpenClaw when installed, and records results, with support for custom test scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check services after a machine or container restart
• Investigate problems with a gbrain installation
• Check OpenClaw services when installed

Check whether gbrain uses PGLite or Postgres, set up a Postgres-backed installation, or migrate existing PGLite data with its history. The workflow presents a migration plan for approval, verifies transferred tables, and supports interrupted migration recovery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking which database engine gbrain uses
• Setting up Postgres for a new gbrain installation
• Moving PGLite data and history to Postgres

Make your local gbrain accessible to other devices and cloud agents through MCP, a connection interface for AI tools. Set up Tailscale access, assign limited permissions to each client, configure authentication, and verify connections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Accessing gbrain from another laptop or phone
• Connecting cloud agents to your local gbrain
• Giving each client limited access permissions

Check a gbrain installation and its migration status, including pending or incomplete updates. Return a concise health summary, proposed repairs, and a machine-readable JSON report for scheduled briefings, troubleshooting, or CI checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check gbrain health on demand
• Include problems in a scheduled morning briefing
• Investigate stalled jobs or knowledge updates

Manage recurring jobs with staggered schedules, collision checks, and quiet hours that hold notifications until morning contact. The workflow checks for duplicate side effects on reruns and saves dated reports of job results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Scheduling recurring tasks at staggered times
• Holding nighttime notifications until morning
• Preventing duplicate output when jobs rerun

Check your gbrain setup and receive prioritized suggestions for overdue updates, pending migrations, stalled jobs, and other maintenance issues. Findings include repair commands, while any fixes require your approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing your gbrain setup
• Getting a weekly maintenance check
• Prioritizing updates and stalled jobs

Manage GBrain client registrations, permissions, and OAuth connections, a method for authorizing access. The skill separates server owner administration from ordinary client access and guides token invalidation, revocation, and connection verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Open the GBrain owner dashboard
• Register an MCP client and configure its connection
• Review and change client permissions

Manage shell commands and AI agent tasks through a shared gbrain job queue. Track progress, steer agents, pause or resume work, and coordinate parallel tasks, with guidance for long operations, completion reporting, and reusable stage checkpoints.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run scripts as monitored background jobs
• Coordinate parallel research by AI agents
• Redirect, pause, or resume an agent task

Diagnose and repair GBrain’s Postgres access with a fixed recovery command. Apply routine fixes, request approval for configuration rewrites, and verify connectivity afterward. Credential problems and other manual cases are returned with instructions for the operator.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnose GBrain database connection failures
• Apply routine fixes such as reconnecting or pending migrations
• Review and approve connection configuration rewrites

Keep gbrain current by checking available updates, summarizing release changes, and applying or deferring upgrades according to configured preferences. Migration instructions take priority when a release requires an operator to supervise the update.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether gbrain has an available update
• Review release changes before upgrading
• Defer update reminders during ongoing work

Investigate slow jobs, stale data, and timeout alerts by timing the specific operation and comparing monitoring thresholds. Produce an evidence-based verdict that distinguishes insufficient time, stalled work, and false alerts before proposing changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate repeated timeout alerts
• Check whether stale-data warnings reflect actual lag
• Compare monitor thresholds with gbrain doctor

Create or update step-by-step instructions for recurring operational tasks. Document exact commands, expected results, failure responses, verification checks, rollback steps, and escalation contacts so operations teams have a concrete procedure to follow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting recurring operational tasks
• Turning experienced staff knowledge into written procedures
• Adding troubleshooting and rollback steps to existing instructions

Prepare a deployment checklist covering tests, approvals, database changes, release steps, and monitoring. Tailor it to the release and document rollback triggers, the conditions for reverting a change, before production deployment begins.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare checks for an upcoming production release
• Review a release with database migrations
• Verify feature flags and CI status before deployment

Manage service incidents from initial assessment through recovery review. The skill organizes severity, impact, roles, status updates, and timelines, then drafts a blameless postmortem with root cause analysis and action items assigned to owners.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess the severity and impact of a new incident
• Draft internal and customer status updates
• Record mitigation steps and an incident timeline

Deploy web applications to Vercel for production or preview, then check build results, deployment status, and the live URL. The skill also covers linking projects, managing domains, and adding or downloading environment variables through the command line.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publish an existing web app to production
• Create a preview deployment for review
• Check deployment status and live URL responses

Update a customized NanoClaw installation with official changes. The skill stages and tests updates in a separate workspace, manages required migrations, restarts the detected service, and restores saved local state if the build or health checks fail.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Apply routine official updates to a customized installation
• Review and resolve conflicts before changing the live installation
• Apply selected upstream commits

Refresh installed NanoClaw channel and agent provider code from its registry branches. Update all integrations or a selected subset, check a structured result report, and validate the updated installation with builds and tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refreshing integrations after a NanoClaw update
• Updating selected channels or agent providers
• Updating from a fork with an upstream remote

Enable NanoClaw agents to deploy web applications to Vercel. The skill installs the Vercel CLI, a command-line tool, and configures automatic credential injection through OneCLI, supporting production deployment and deployment status checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enabling Vercel deployment for NanoClaw agents
• Configuring Vercel credentials through OneCLI
• Adding deployment tools to existing agent groups

Install rtk in NanoClaw agent containers to compress development command output and reduce token use. A Claude Code hook automatically routes Bash calls through rtk, with runtime checks to verify installation and a command to inspect savings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reduce token use from development command output
• Automatically route Bash calls through rtk
• Configure rtk for multiple agent groups

Manage which host folders NanoClaw agent containers may access. View the current permissions, add or remove allowed directories, choose read-only or read-write access, and reset the list, with guidance on applying changes to running groups.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking which host folders agents may access
• Sharing a folder with read-only or read-write access
• Removing a folder from the allowed list

Switch a NanoClaw agent group to a local Ollama model by configuring environment variables and model settings. The skill covers setup checks, optional blocking of Anthropic API access, verification, troubleshooting, and switching back to Claude.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running a NanoClaw agent with a local model
• Reducing use of the Anthropic API
• Trying open-weight models through Ollama

Install a local NanoClaw dashboard to inspect agents, sessions, channels, messages, and users. It displays token usage, context usage, activity, and live logs using periodic data snapshots and a log forwarding module.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking agent and session status in one place
• Reviewing token and context usage
• Following live logs with level filters

Add a read-only web dashboard for browsing NanoClaw agents, sessions, and other resources. It builds tables from command-line JSON output and includes message activity charts, recent logs, and a viewer for skills, profiles, and CLAUDE.md files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check agent and session status in a browser
• Review message counts and daily activity
• Read recent host logs

Add a NanoClaw status icon to the macOS menu bar. Check whether the service is running through a green or red dot, then start, stop, restart, or open its logs from the menu.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking NanoClaw's running status
• Starting or stopping the service from the menu bar
• Restarting after code changes