스킬 찾기

Deploy language model APIs and run batch generation with vLLM. Configure GPU memory use, quantization—lower precision model storage—and distribution across GPUs, then test response times and monitor how many requests the server handles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying an OpenAI-compatible language model API
• Generating responses for a large set of prompts
• Fitting a large model into limited GPU memory

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

Evaluate code generation models with HumanEval, MBPP, and multilingual benchmarks. The skill guides test execution and model comparisons using pass@k, an estimate of whether at least one of k generated solutions passes the tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare code generation models on shared benchmarks
• Measure code generation performance across languages
• Evaluate instruction-tuned coding models

Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing models on the same benchmark tasks
• Running a small evaluation sample before a full benchmark
• Running large evaluations on a Slurm cluster

Set up reinforcement learning, training guided by rewards, for language models with slime. The skill covers Megatron-LM training, SGLang response generation, data preparation, asynchronous execution, and custom workflows for agents that use tools across multiple turns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare GRPO training for GLM or Qwen3 models
• Overlap response generation and model training
• Train agents with multi-turn tool use

Guides large language model reinforcement learning with miles, including MoE models that route work to specialized components. Covers low-precision training, matching training and inference behavior, and accelerating training response generation with draft models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up reinforcement learning for large MoE models
• Configuring FP8 or INT4 training
• Checking consistency between training and inference

Guides you through running large language models on CPUs, Apple Silicon, and AMD or Intel GPUs. Covers choosing GGUF model files, reducing memory through quantization, and starting an OpenAI-compatible chat server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running a local LLM on an Apple Silicon Mac
• Trying LLM inference on a CPU-only machine
• Choosing a model format that fits available memory

Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a training method for human preference alignment
• Setting up distributed training across multiple GPUs
• Training a reward model before PPO

Build, test, and format CubeSandbox components using make targets and a Docker builder. Also covers the web dashboard’s development workflow, API type synchronization, and troubleshooting for missing services, outdated build tools, and environment requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build all components or a specific CubeSandbox component
• Run component tests or a single targeted test
• Format Go and Rust code and lint the web interface

Create Dockerfiles, automated build and deployment pipelines, Kubernetes configurations, and infrastructure templates. The skill also prepares deployment checks, rollback procedures, and incident response runbooks to support application releases and production operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up automated build and deployment pipelines
• Packaging applications with Docker
• Managing Kubernetes and cloud infrastructure as code

Build and maintain machine learning apps on Hugging Face Spaces. Choose a suitable app framework and computing hardware, load models, deploy files, and check logs and outputs to diagnose build or runtime problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publishing a machine learning demo
• Adapting an existing Gradio app for ZeroGPU
• Diagnosing Space build or runtime failures

Write and review Gradio demos for Hugging Face ZeroGPU. Configure GPU time limits and dependencies, and troubleshoot errors caused by separate worker processes, shared state, concurrent requests, or CUDA package installation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review GPU handlers in a Gradio demo
• Tune GPU duration and quota usage
• Fix PicklingError and stale state across worker processes

Build and run Omnigent’s server and Postgres together with Docker Compose on a laptop or existing Docker host. Use the supplied configuration and troubleshooting guidance to rebuild images, investigate startup problems, or adapt deployment to another platform.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running Omnigent locally with Postgres
• Starting the stack on an existing VPS or EC2 host
• Investigating startup and web interface problems

Inspect and manage Tencent Cloud resources with tccli, its command line tool. Covers servers, networking, DNS, certificates, permissions, monitoring, and application deployment, with supporting scripts for login and identifying the current cloud instance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking Lighthouse and CVM server status
• Reviewing domain expiry dates and SSL certificates
• Inspecting security groups and access permissions

Get help understanding and configuring Octop, a self-hosted AI assistant. The skill explains features, points to relevant documentation, and supports model switching, messaging connections, skill management, scheduled tasks, backups, and upgrades.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn about Octop and find installation instructions
• Switch AI models or configure providers
• Connect messaging services such as Discord

Prepare and coordinate Octop Python package releases, including version updates, a Chinese changelog, and a pull request. After merging, GitHub Actions handles release tags, package and container publishing, and branch synchronization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing an Octop package release
• Updating version numbers across release files
• Drafting a Chinese changelog from commits

Write and review Apache SeaTunnel unit tests and E2E tests that check complete jobs using Testcontainers. It provides concrete rules for container setup, waiting, resource cleanup, and assertions to address intermittent failures and resource leaks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing a new connector E2E test
• Reviewing a test diff before a pull request
• Fixing intermittent failures or resource leaks in tests

Navigate Apache Beam contributions from finding an issue to submitting a pull request, a proposed code change, and responding to reviews. Covers environment setup, tests, formatting, licensing requirements, and closer evaluation of changes to core components.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a first Apache Beam contribution
• Organize a pull request and its related issue
• Check tests and formatting before submission

Develop and troubleshoot Apache Beam's YAML SDK. Understand its source files, run data processing pipelines locally or on Dataflow, test changes, and investigate provider issues or mismatched record fields.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find source files for Beam YAML changes
• Run a YAML pipeline locally or on Dataflow
• Run unit tests and external service integration tests

Build and test Apache Beam with Gradle, the system that manages its project tasks. Find relevant configuration files, inspect library dependencies, run formatting checks, publish locally, and investigate build failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build or test a specific Apache Beam module
• Inspect library dependencies and version conflicts
• Run formatting and pre-commit checks

Investigate a Sandcastle GitHub issue, classify the report, check for duplicates or existing fixes, and attempt reproduction with Docker. Return a minimal reproduction script, observed results, and a likely cause, noting any environment limitations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classifying a reported Sandcastle issue
• Reproducing a bug in Docker
• Checking for duplicate reports or existing fixes

Run OpenClaw tests and reproduce bugs on remote machines through Crabbox. Choose a suitable execution provider, verify realistic user workflows, and report the actual provider, environment ID, logs, and timing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run broad OpenClaw tests in a remote CI environment
• Reproduce installation or Docker bugs
• Verify behavior on macOS, Windows, or WSL2

Set up Git workflows for Gitee, Coding.net, 极狐 GitLab, and CNB with platform-specific connection and authentication examples. Choose branching rules, standardize Chinese commit messages, and adapt automated testing and deployment configurations to your team's workflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure connections and authentication for Chinese Git platforms
• Choose branching rules that fit the team
• Standardize Chinese commit messages and review templates

Design an OpenRig agent team around a project goal. Create team and agent specifications, role guidance, and collaboration rules, then validate the setup and diagnose problems with startup instructions or agent coordination.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing an implementation and QA pair
• Creating a team with development and independent review
• Writing role guidance and team collaboration rules