인프라·DevOps 스킬

Build a single-page operations guide for engineers on call, the people assigned to respond to service issues. Organize service dependencies, alert thresholds, dashboard links, copyable commands, duty rotations, and an incident response checklist.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Bring service operations information onto one page
• Document alert severity, thresholds, and procedure links
• Prepare commands and checklists for incident response

Audit database migration changes before a Bifrost release for lock contention, deadlocks, and delayed application startup. Receive pass, warning, or failure results, a release recommendation, and concrete remediation steps without modifying files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review migration safety before a release
• Check index creation risks on large log tables
• Find migration work that delays application startup

Update Bifrost Helm charts, the packages used to configure deployments, while keeping settings, schemas, templates, and documentation aligned. Check the published release and group changes into the next unreleased version.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add Bifrost settings to the Helm chart
• Check configuration fields missing from the chart
• Combine changes into one unreleased version

Helps investigate and modify Apache Beam's automated build and test workflows in GitHub Actions. Explains workflow types, failure logs, targeted reruns, local reproduction, and the cloud credentials needed for workflows that access GCP.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failed checks on a pull request
• Rerunning a specific test workflow
• Reproducing CI test commands locally

Collect operation events across an AI agent workflow and link them into traceable execution records. Search by tracking ID, time range, or responsible agent, with semantic indexing and local event storage to support audits and investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing handoffs and processing steps across multiple agents
• Tracing related operations with a tracking ID
• Finding past events by time range or responsible agent

Record operations across multiple AI agents and connect events into a traceable history. Search records by tracking ID, time window, or responsible component to support audits and investigations, with local storage available when the vector database fails.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trace task dispatch and execution across agents
• Search audit records by time or responsible component
• Keep recording events during vector database failures

Start and manage long-running background services such as development servers. Check their status and output logs, verify listening ports, retrieve local URLs, and restart services while keeping the same service ID.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a development server in the background
• Checking service status and output logs
• Restarting a service while keeping its ID

Find user-configured API keys and tokens by listing their names and descriptions, then retrieve a chosen value for scripts. Helps use credentials in API calls or authentication without embedding them directly in code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check which credentials are configured for the current assistant
• Retrieve a configured API key for a script
• Get a token for git authentication

Find workspaces on remote nodes, inspect their details, browse folders, and read or write files. Supports text files and binary content, such as images, through base64 encoding, a text representation of binary data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find workspaces on a specific remote node
• Browse folders and read project files
• Save output files to a remote workspace

Check the health of the HashiCorp Vault instance in an OpenRig environment and manage stored secrets. Use its API to write, read, list, or delete entries and explain how secret paths are organized.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether the local Vault instance is healthy
• Storing or retrieving secret values
• Listing secret paths and explaining their contents

Opens groups of OpenRig agent terminals as live herdr tiles for interaction or observation. Explains view selection, read-only access, saved groups, and how to interpret agents that are offline or cannot be displayed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Opening all live agents in a rig as terminal tiles
• Watching mission or slice agents in read-only views
• Reopening a custom group from a saved view

Guide OpenRig CLI and background service upgrades while protecting active sessions and local file changes. The skill provides staged checks, verified database backups, selective plugin refreshes, and migration helpers, with evidence checked after each change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Upgrading OpenRig while preserving active sessions
• Backing up and checking the database before an upgrade
• Refreshing managed plugins while preserving local edits

Coordinate with OpenRig agents on registered remote machines using SSH or HTTP connections. Select the intended host, inspect agent state, send messages, and interpret failures while checking whether remote actions actually took effect.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking agents on a registered remote host
• Sending messages to agents on another machine
• Diagnosing connection and authentication failures

Configure a new OpenRig agent seat, a managed place for an agent to run, using a prior Claude or Codex conversation. Covers fork settings, new session identities, and checks that distinguish forking from restoring.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a new agent seat from an earlier conversation
• Add conversation source settings to a rig expand payload
• Distinguish conversation forks from seat restoration

Monitor other agent teams for abandoned work, process drift, off-task activity, and excessive token use. It guides evidence checks after alerts and chooses a proportionate response, from notifying the team’s coordinator to escalating to a human.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether unfinished work was abandoned
• Detect process drift or off-task activity
• Investigate excessive token use

Configure selected OpenRig command permissions in Claude Code or Codex at the agreed project or user scope. Preserve existing restrictions, verify that settings load and behave as intended, and record additions so they can be removed later.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configuring command permissions before launching an agent team
• Reducing repeated approvals for selected rig commands
• Adding permission rules within a chosen project scope

Package an OpenRig agent arrangement and workflow for reuse by others. Guides bundle creation, inspection before installation, and checks in a clean environment to identify hidden dependencies on local paths, providers, or credentials.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Package a proven agent setup for reuse
• Inspect bundle contents before installation
• Check whether a bundle works in a clean environment

Change a running OpenRig setup by adding or removing agent seats, connecting existing sessions, or attaching terminals. Guides checks for roles, startup context, permissions, and session identity so the setup reflects each change correctly.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add agent seats to a running rig
• Remove seats and clean up remaining references
• Connect an existing session to an OpenRig node

Plan and verify OpenRig startup, shutdown, and recovery. Compare reported status with actual running sessions, distinguish recovery outcomes, and define reboot tests that expose partial failures instead of hiding them behind a fresh launch.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking rig status after a host reboot
• Designing recovery tests across runtimes
• Investigating partially restored agent sessions

Analyze agent runs that fail before any work begins. Check iteration counts, tool use, logs, and outputs to identify startup failures, then direct investigation toward environment setup, input formatting, permissions, or resource limits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failed runs with zero iterations
• Checking startup errors across multiple agents
• Recording failures that require system review

Diagnose failed connections to government websites and corporate portals by checking network access, SSL certificates, and proxy settings. If access remains unavailable, the workflow helps identify alternative data sources and document attempts and next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating SSL certificate errors
• Checking connections through a corporate proxy
• Finding alternative sources for inaccessible data

Diagnose connection problems with government websites by checking SSL certificates, which verify website identity, and proxy settings. Follow structured troubleshooting steps, record failed attempts, and explore alternative APIs or data sources when access remains blocked.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnosing certificate errors on government websites
• Checking whether proxy settings block data access
• Finding alternative sources for inaccessible public data

Troubleshoot access to government and institutional websites by checking connectivity, SSL certificates, and proxy settings. Follow a structured process to test request options, configure retries, and identify alternative data sources when access fails.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating SSL certificate errors
• Comparing browser and script connectivity
• Checking proxy authentication failures

Identify agent failures that happen before any work starts by checking iteration counts, tool use, artifacts, and logs. Classify these incidents as pre-execution failures and guide investigation toward environment setup, initialization, and resource limits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating agent sessions with zero completed iterations
• Classifying failures before the first tool call
• Routing incidents to infrastructure or platform teams