'model debugging' 검색 결과

Use this skill when the user is doing hands-on DOCA RDMI (RDMA Initiator) programming — picking doca-rdmi vs doca-rdma for an accelerator-initiated one-sided RDMA flow, standing up a doca_rdmi_connection or doca_rdmi_poster, attaching a doca_dpa_completion or doca_verbs_cq before doca_ctx_start(), retrieving the DPA-side handle for a DPA kernel, auditing whether a doca_rdmi_* symbol is EXPERIMENTAL on this DOCA, or debugging DOCA_ERROR_* returns from RDMI calls. Trigger even when the user does not say "DOCA RDMI" or "initiator" — implicit phrasings include "my DPA kernel needs to post RDMA writes to a remote responder", "DPA kernel sees no completions", "function not found on doca_rdmi_* at link time", "DOCA_ERROR_BAD_STATE from completion attach", or "the DPA posted but the work request never arrived". Refuse and route elsewhere for two-sided or host-CPU RDMA, the DPA programming model, GPU-side RDMA initiation, or general RDMA/IB/RoCE concepts — those belong to other skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution, global-state-free testing, and prompt-injection awareness. Use when writing an MCP server, exposing a tool or CLI to an LLM client, debugging tool registration/packaging, or testing MCP tools.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). Use proactively when debugging a training pipeline that shows no improvement, loss anomalies, reward stagnation, NaN gradients, or other unexpected behavior during reinforcement learning fine-tuning. Work through all pipeline stages — reward, advantages, log-probs, loss, generation/decoding — before concluding the diagnosis is complete; stopping after one or two fixes is a common failure mode. Covers log-probability math, advantage estimation, numerical stability, reward processing, and generation/decoding pipeline issues.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use for formulating, solving, debugging, and validating mixed-integer linear optimization models with open-source solvers, including variable indexing, sparse constraints, linearized costs, solver limits, MIP gaps, incumbent extraction, numerical tolerances, and deterministic output reporting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Stand up a three.js scene: import maps and the three/addons path, the Scene/PerspectiveCamera/WebGLRenderer trio, the setAnimationLoop render loop, responsive resize, and OrbitControls. Use when starting or debugging a three.js app — when the user mentions three.js, THREE.Scene, WebGLRenderer, PerspectiveCamera, the render loop, resizing, or OrbitControls. For models use threejs-gltf-loading; for materials/lights use threejs-materials-lighting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Deploys and operates a LiveKit agent in production: shipping a version to LiveKit Cloud and rolling it back, secrets and configuration, the worker process model and prewarming, safe async inside worker processes, provider timeouts and degradation, graceful shutdown, SDK upgrades, and observability. Use when the user says "deploy my agent", "roll back the deployment", "tail the agent logs", "the first call after a restart is slow", "attached to a different loop / event loop is closed", "prewarm the VAD", "shut down without dropping calls", "upgrade livekit-agents safely", "correlate logs by session", or is changing an agent codebase that is already live. Not for designing the agent (building-livekit-agents) or reproducing one bad conversation locally (debugging-livekit-agents).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Builds voice and chat AI agents with LiveKit Agents on LiveKit Cloud or a self-hosted server. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI to my app", "implement handoffs", "structure an agent workflow", "my agent is slow / too chatty", "it says it booked but nothing was saved", "make it confirm before committing", "it keeps re-asking things the caller already said", or is writing code against the LiveKit Agents SDK. Covers architecture: designing for latency, keeping context small, splitting a monolithic agent into handoffs and tasks, and designing for voice. Also covers keeping the model in charge of meaning while code owns state, approvals, and effects. For API specifics use reading-livekit-docs. To check behavior use debugging-livekit-agents and testing-livekit-agents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when building or debugging Geometry Nodes, headless or live: procedural modeling, scattering objects on a surface, arrays along a curve, repeat or for-each loops, simulation zones, 5.2 physics (cloth, colliders, forces, effectors), closures, bundles, matrices, node-group assets with gizmos. Also when a GN script links nothing, shows red links, ignores modifier inputs, loses instances in a bounding box, or a simulation resets or jumps.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

On-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt. Read it when a task lands in one of these areas. subgraph boundary rails and blueprint reuse, merging or composing workflows across tabs, pinning your edits to one workflow, opening staged or downloaded workflow files, untangling Get/Set-bus and rgthree toggle-heavy graphs, authoring rgthree Fast Groups nodes, the LoRA Manager autocomplete-node limitation, the CivitAI browser flow, downloading model weights, reading hardware and runtime stats, Prompt Director audits, custom-node crash recovery, run-to-node render debugging, and multi-stage pipeline chaining. Each section is a lookup, not background reading. Reach for the one you need instead of guessing, and follow the tool's own description for parameter detail.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

SwiftUI's actual mental model — view identity, lifetime, and dependencies (the Demystify canon), state ownership decision rules, Observation's per-property tracking, body-performance discipline, and the main-actor concurrency contract. Use when state resets mysteriously, views re-render too often, animations glitch between branches, choosing @State vs @Bindable vs plain property, or debugging "why did body run."

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use ONLY when calling the `browser_execute` tool or driving a real browser via the Chrome DevTools Protocol. Required reading before the first `browser_execute` call in a session. Covers the three connection methods (local Chrome with remote debugging, isolated debug-port profile, Browser Use cloud), the in-process `session` / `console` snippet model, attaching to a page target, common CDP commands, the per-project `.bcode/agent-workspace/` for reusable scripts, and screenshot auto-attachment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Primary router skill for broad .NET work. Classify the repo by app model and cross-cutting concern first, then switch to the narrowest matching .NET skill instead of staying at a generic layer. USE FOR: general .NET requests without a narrower framework; C# implementation, debugging, review, or refactoring; routing to framework and tooling skills. DO NOT USE FOR: unrelated stacks; tasks already covered by a narrower .NET skill. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnose recommendation quality, traffic, feature, model, retrieval, ranking, latency, timeout, overload, degradation, or logging regressions using an evidence-first decision tree.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), console error monitoring, global setup/teardown, test annotations (skip, fixme, slow), test tags (@smoke, @fast, @critical, filtering with --grep), project dependencies, security testing (XSS, CSRF, auth), performance budgets (Web Vitals, Lighthouse), iframes, component testing, canvas/WebGL, service workers/PWA, test coverage, i18n/localization, Electron apps, or browser extension testing. Covers E2E, component, API, visual, accessibility, security, Electron, and extension testing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Provides Qwen Coder CLI delegation workflows for coding tasks using Qwen2.5-Coder and QwQ models, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Qwen for tasks such as code generation, refactoring, debugging, or architectural analysis. Triggers on "use qwen", "use qwen coder", "delegate to qwen", "ask qwen", "second opinion from qwen", "qwen opinion", "continue with qwen", "qwen session".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use detrex for detection-transformer configs, training/evaluation, demos, model zoo conversion, and package API debugging.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operate Core ML Tools workflows for model conversion, Core ML artifact I/O, optimization, MIL debugging, and platform-aware troubleshooting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Explain why counterexamples violate specifications by analyzing formal specifications (temporal logic, invariants, pre/postconditions, code contracts), informal requirements (user stories, acceptance criteria), test specifications (assertions, property-based tests), and providing step-by-step traces showing state changes, comparing expected vs actual behavior, identifying root causes, and assessing violation impact. Use when debugging test failures, understanding model checker output, explaining runtime assertion violations, analyzing static analysis warnings, or teaching specification concepts. Produces structured markdown explanations with traces, comparisons, state diagrams, and cause chains. Triggers when users ask why something failed, explain a violation, understand a counterexample, debug a specification, or analyze why a test fails.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use MiniMax's first-party Hailuo video API safely and reproducibly across global and mainland-China platforms. Covers current text-to-video, image-to-video, first/last-frame, and subject-reference models; prompt and camera craft; region/account routing; exact cost approval; asynchronous jobs and callbacks; artifact provenance; and rights, likeness, disclosure, and data-governance review. Use when designing, implementing, debugging, or evaluating direct MiniMax/Hailuo video-generation API workflows. Do not use for the consumer Hailuo site, Video Agent templates, gateways, or unrelated MiniMax modalities.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operate Stability AI image generation, image-to-image, edit, control, background, and upscale APIs safely and reproducibly. Use when selecting or calling Stable Image Ultra, Core, Stable Diffusion 3.5, v2beta image edit/control services, or Stability open-weight image models; when debugging schemas, moderation, rate limits, cost, lifecycle, licenses, privacy, provenance, or migrations; and when planning production QA for Stability-generated images.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build and trace AI agents in Python with AgentScope, an open-source agent framework with a ReAct loop, tools, middleware, team pipelines and OpenTelemetry tracing. Use when building production agents that need observability, debugging an agent's model and tool calls, capping token spend per reply, or coordinating a leader with specialist agents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.