스킬 찾기

Assess Verdaccio issues against the code, affected release lines, and related reports. Distinguish bugs from configuration problems or duplicates, then propose existing labels, next steps, and a reply draft backed by evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classifying a newly reported issue
• Checking which release lines a bug affects
• Finding duplicates and related fixes

Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test CUDA code without a local GPU
• Run model training or LoRA fine-tuning on cloud GPUs
• Deploy a model inference API or vLLM service

Launch machine learning experiments on local GPUs, remote servers, Vast.ai, or Modal. It checks the configured environment, deploys code, saves logs, and verifies startup, with optional W&B metric logging and automatic Vast.ai result collection and instance cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run training jobs on a local GPU
• Deploy experiments to an SSH server
• Run experiments on Vast.ai and collect results

Rent and manage vast.ai GPUs based on the training task rather than a chosen hardware model. The skill estimates requirements, compares offers by total expected cost, prepares the selected instance, and retrieves results before destroying it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a cloud GPU for a training task
• Comparing rental offers by estimated total cost
• Preparing a rented GPU environment for experiments

Set up KubeSphere’s WizTelemetry Data Pipeline to collect, transform, and route logs, audit data, events, and notifications. Configure delivery to OpenSearch, deploy agents across selected clusters, and check their operating status.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a shared collection pipeline for observability data
• Configuring delivery to OpenSearch
• Deploying agents across multiple clusters

Configure and troubleshoot Jenkins in KubeSphere DevOps, including login integration and build agents, the environments that run pipeline tasks. Get guidance for starting builds through the API, checking logs and status, and downloading build artifacts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect Jenkins login to LDAP or OIDC
• Customize build agent images and resources
• Start builds and download artifacts through the API

Install and configure WizTelemetry Logging in KubeSphere to collect container output and file logs. Use its API to filter logs by workload, time, or keywords, retrieve statistics, and export results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploy log collection to selected clusters
• Enable collection of log files inside containers
• Search logs by keyword, workload, and time

Automate Docker Hub administration through Composio: create organizations and repositories, list teams, invite members, and configure webhooks that notify other services when container images are pushed to a repository.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a Docker Hub organization or repository
• Review repositories with filters and sorting
• List teams and invite organization members

Automate Docker Hub repository, image, and tag management through Rube MCP. Discover available operations and their required inputs, then carry out individual tasks, connected workflows, or bulk operations using Composio’s toolkit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Manage Docker Hub repositories, images, and tags
• Check available Docker Hub operations
• Connect multiple registry management steps

Turn plain-language requirements and optional API documentation into OpenShell sandbox network policies in YAML. Define allowed destinations, programs, and API operations, with optional middleware settings for inspecting or transforming traffic and controlling what happens when processing fails.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Restrict API access to reading operations
• Allow only specific API methods and paths
• Limit internal service access by program and IP range

Set up and manage a local Kubernetes development environment for OpenShell using k3d, Skaffold, and Helm. Build and deploy changes, inspect traces, configure optional authentication components, and test behavior across multiple gateway replicas.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create or stop a local OpenShell development cluster
• Rebuild and deploy changes during development
• Inspect local execution traces

Maintain and validate OpenShell builds for Windows on x64 and ARM64 using MSVC, Microsoft's C++ toolchain. Check compilation, build executables, run tests on native hosts, and report artifacts and unsupported driver behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating Windows compilation failures
• Building x64 and ARM64 release executables
• Checking errors for unsupported drivers

Manage isolated working environments in OpenShell using its command-line tool. Register gateways, create and connect to sandboxes, configure credential providers, and reuse workload templates with shared images, environment settings, and computing resources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create and connect to a sandbox
• Configure and refresh provider credentials
• Inspect and import provider profiles

Launch and supervise gator agents for specific GitHub issues or pull requests in OpenShell. Check isolated execution environments, inspect logs, restart stalled agents, and test model or image overrides without changing default settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch gator to review and monitor a specific pull request
• Inspect sandbox status and runtime logs
• Restart a stalled or outdated gator agent

Diagnose unreachable or unhealthy OpenShell gateways and sandbox startup failures. Identify the underlying execution platform, then examine logs, authentication, certificates, and configuration with the matching tools to narrow down the cause.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate gateway connection and health check failures
• Find why a sandbox remains pending or fails to start
• Check Docker or Podman runtime and image problems

Run OpenShell’s Release Canary checks to verify that published development packages and Helm charts install and support basic sandbox operations. Use workflow logs and local Kubernetes reproduction steps to investigate failures before a public release.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking published development artifacts before release
• Testing changes to the Release Canary workflow
• Investigating installation or sandbox test failures

Prepare a clean Doris package and run Docker regression tests, which check whether changes break existing behavior. Restore configuration and startup files from Git, build the test image, and investigate failures using configuration checks and runtime logs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run Docker regression tests before submitting Doris changes
• Test without local configuration changes affecting results
• Investigate missing test suites or startup failures

Run the current working copy locally with a real language model and Postgres database. Choose web, Slack, or both to test a branch end to end, with separate Slack apps for concurrent instances.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test a branch through Slack
• Check web and admin screens locally
• Run several working copies at once

Downloads CARLA release packages, nightly builds, source code, or Docker images, then reports their locations and environment variables for follow-up setup. Supports extra maps and resumable downloads, helping prepare the files needed for subsequent installation or building.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting CARLA for the first time
• Downloading an older version to reproduce a bug
• Fetching additional maps

Add a message type to CARLA's native ROS 2 interface. Create its C++ data structure, serialization code for transmission, type identity hash, registration, and tests, with Docker-based hash calculation and build checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a standard ROS 2 message type missing from CARLA
• Defining a custom carla_msgs message
• Investigating type-hash warnings

Inspect data published by a ROS 2-enabled CARLA server using Docker, without installing ROS 2 locally. Check topic contents and rates, run a sensor-equipped vehicle demo, and view lidar data and supported map markers in RViz2.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether CARLA is publishing ROS 2 data
• Inspecting sensor data contents and publishing rates
• Viewing lidar data and road markers in RViz2

Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building document retrieval for AI answers
• Combining similarity search with category or date filters
• Reducing memory use for large vector collections

Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate AI application problems using execution traces
• Evaluate answer quality across a test dataset
• Compare prompts and models through experiments

Build AI agents by connecting workflow blocks in AutoGPT's visual editor. This skill covers multi-step automation, scheduled runs, webhooks that start work after external events, execution monitoring, and custom agent development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an AI workflow in a visual editor
• Start an agent when an external event occurs
• Run a multi-step workflow on a schedule