'recipes' 검색 결과

Find animation, short-video, and motion-effect references on 1human, including items saved in a shared human-agent library. Review sources and licenses to guide creative work, and publish creations only within the owner's explicit permission.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find references for a loading animation
• Use shared favorites to guide motion design
• Check source tutorials and creation recipes

Prepare and review LoRA or QLoRA settings for adapting language models using example responses. Choose trainable layers, adapter capacity, learning rate, and memory-related options, then produce configuration values for a downstream training script.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a LoRA configuration for supervised fine-tuning
• Reviewing rank, alpha, and learning rate settings
• Choosing LoRA or QLoRA based on GPU memory

Add a model page to the SGLang Cookbook using shared templates. Organize verified launch settings and measured benchmarks, create configuration files and documentation, and update navigation, vendor cards, and page validation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add documentation for a newly supported model
• Organize verified launch recipes by hardware
• Publish measured speed and accuracy results

Inspect, run, and organize project commands with just. This skill explains how to find available recipes—named tasks in a justfile—check their contents, pass arguments, and define reusable commands with dependencies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding available project commands
• Running builds and tests with arguments
• Turning frequent commands into reusable tasks

Investigate OpenSEO production errors in Cloudflare Workers Observability. Count worker invocations accurately, compare periods and deployment versions, and filter previously investigated noise to focus analysis on errors that need attention.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a spike in production errors
• Counting out-of-memory events and worker failures
• Comparing error rates across periods or deployments

Keep coding tasks small by checking whether new code is needed, reusing existing helpers, and preferring standard libraries or built-in platform features. Apply the same approach to feature development, bug fixes, refactoring, and reviews.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a feature with minimal code
• Reviewing unnecessary dependencies
• Simplifying an overcomplicated implementation

Plan and troubleshoot large language and vision model training and inference. This guide uses hardware measurements to identify bottlenecks, address memory shortages and unstable training, and improve checkpointing, recovery, and performance across multiple GPUs and machines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnosing slow training and GPU memory shortages
• Investigating loss spikes and invalid numerical values
• Debugging communication hangs across GPUs and machines

Create product videos from real webpage screenshots using shot recipes and a ready-made template. Combine camera movement, cuts timed to music, and sound effects, or adapt a single shot for use in another video.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a website into a product video
• Adapt the Ink Press template to a product
• Create one animated shot from a recipe card

Diagnose unexpected terminal-tools results, including empty output, missing exit codes, expired output handles, and busy sessions. Use returned status fields to distinguish ongoing work, output limits, shell behavior, and failures, then choose a recovery step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate empty or truncated command output
• Interpret missing exit codes and conflicting status fields
• Resolve job limits and busy terminal sessions

Create Native SDK interfaces with .native markup, connecting layouts, widgets, and user actions to app state and messages. Covers TypeScript core integration, explicit Zig alternatives, menus, scrolling, embedded web panes, and interface verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building screens and connecting them to app state
• Adding context menus and menu-bar items
• Displaying long lists with virtualized rendering

Turn ordered steps into a vertical or horizontal timeline whose progress line and active step update as readers scroll. Keep the sequence readable across screen sizes, with keyboard navigation and support for reduced-motion preferences.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Present onboarding or service steps as a scroll timeline
• Show a roadmap or history with visible progress
• Adapt a timeline for small screens

Build consistent web interfaces with Tailwind CSS using small styling classes. Apply layout, typography, responsive behavior, interaction states, and dark mode patterns, with examples for buttons, page sections, and reusable components.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building responsive page layouts
• Standardizing buttons and shared components
• Adding dark mode styles

Find API patterns and examples for coding agents with ADK, the Agent Development Kit. Covers tools, state, callbacks, multi-agent coordination, and graph workflows, with Python and Go references plus guidance on studying existing implementations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding tools and callbacks to an ADK agent
• Implementing state management and agent coordination
• Designing branching and parallel graph workflows

Investigate code with the lsp tool, which uses a language server to understand names, imports, and types. Find definitions and usages, inspect signatures and file outlines, and check compiler or type errors after edits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding where a function or variable is defined
• Tracing symbol usages across imports and aliases
• Reading type signatures and documentation

Manage terminal work across panes: open jobs, run commands, read output, and wait for completion. Report agent status, exchange messages, and request human decisions through tuios, a terminal window manager with a background service.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run tests in a separate terminal pane
• Wait for command completion or specific output
• Report progress and requests for human input

Turn an AI short drama script into timed segments and shots, with frame prompts and video prompts for MiniMax H3 and Seedance. Validate dialogue coverage and timing, then produce review reports, generation batches, and voice alignment lists.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking a short drama script into timed shots
• Preparing MiniMax H3 or Seedance video prompts
• Checking dialogue coverage and shot duration

Write and improve Playwright tests for browser workflows, APIs, components, visual changes, and accessibility. Provides TypeScript and JavaScript patterns for selecting elements, waiting reliably, managing authentication and test data, and investigating intermittent failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing tests for login, forms, and CRUD workflows
• Improving tests that fail intermittently
• Checking visual changes and accessibility

Create Playwright tests for user workflows, APIs, and visual changes. Use TypeScript or JavaScript examples to choose reliable page elements, manage login state, diagnose intermittent failures, and configure automated test runs in CI.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing login, forms, and other user workflows
• Checking APIs, visual changes, and accessibility
• Diagnosing tests that fail intermittently

Verify BB workflows in an isolated development app using browser interactions and the matching source CLI. Select relevant checks, collect screenshots and persisted-state evidence, and report passes, failures, untested cases, and blockers separately.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check affected workflows after a BB feature change
• Run a smoke test of BB's main interactions
• Audit verification coverage against source changes

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, comparing library and benchmark configs, resizing parallelism for a GPU allocation, or distinguishing convergence changes, semantics-preserving execution tuning, and benchmark-only shortcuts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.