'model debugging' 검색 결과

AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching `acopf-math-model.md` and MATPOWER branch fields. Use when computing branch flows in either direction, aggregating bus injections for nodal balance, checking MVA (rateA) limits, computing branch loading %, or debugging sign/units issues in AC power flow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Answer a hard question by fanning it out to a PANEL of models running in parallel — each answering independently with web search and bash, none seeing the others' work — then having Opus 4.8 judge every response into a structured analysis (consensus, contradictions, partial coverage, unique insights, blind spots) and write a final answer grounded in it. The panel is two independent Opus 4.8 runs (slug opus4.8-4.8), Opus 4.8 + GPT-5.5 via codex (opus4.8-gpt5.5), Opus 4.8 + Gemini 3.1 Pro via agy (opus4.8-gemini3.1pro), or all three (opus4.8-gpt5.5-gemini3.1pro). Opus always judges and writes the final answer — the pipeline can't be reversed. Runs on local CLI subscriptions (no metered API), and saves a timestamped provenance .md per run. Use this whenever the user asks to "run it through Fusion", says /fusion, wants a multi-model / panel / ensemble answer, wants a question cross-checked across models, or wants a higher-confidence answer with consensus and blind spots surfaced — even if they don't say "fusion". General-purpose: any topic (research, law, strategy, technical, personal). Best for high-stakes research, design calls, and debugging where being confidently wrong is expensive.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite loop, "model got dumber after upgrade"). The skill enforces a 30-second inspect step BEFORE any prompt edit, model swap, retry, or temperature tweak. Cross-framework cheat sheet: DSPy `inspect_history`, LangGraph `get_state_history`, CrewAI `step_callback`, LangChain `set_debug`/`set_verbose`, Aider `/diff`+`--verbose`, raw OpenAI/Anthropic via `OPENAI_LOG=debug`/`ANTHROPIC_LOG=debug` or HTTPX event hooks. Do NOT activate for first-time prompt authoring, exploratory prompt design, or non-LM bugs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit a .glb or .gltf and make it small, correct, and fast to load in a browser, with a measured before/after report. Use when a model is "too big" or "slow to load", when the user asks to "optimize this GLB", "compress this glTF", or "export for web", or when they mention Draco, meshopt, gltfpack, KTX2, Basis, texture VRAM, draw calls, or a Blender / CAD / photogrammetry / Pascal export headed for Three.js, React Three Fiber (drei useGLTF), Babylon.js, or model-viewer. Covers inspection, spec validation, geometry and texture compression, scene-graph cleanup, and the correctness checks (metres, Y-up, node names, animations, PBR fidelity, alpha modes, vertex colors) that must not regress. Not for editing or modelling geometry, authoring or laying out a scene, generating 3D from text or images, converting from FBX/OBJ/CAD, or debugging a runtime frame rate that has nothing to do with asset size.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Time-travel debugging for DAG executions. Inspect agent state at any node, replay decisions with modified inputs, compare execution traces side-by-side, and identify where reasoning diverged. Inspired by LangGraph Studio's state-editing model and Temporal's event history. Activate on "debug DAG", "replay execution", "time travel debug", "inspect node state", "what went wrong at step", "compare runs", "execution diff". NOT for live monitoring (use dag-runtime + websocket-streaming), failure analysis (use dag-ops), or general code debugging.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Visualize métricas de treinamento, depure modelos com histogramas, compare experimentos, visualize grafos de modelos e perfil de desempenho com TensorBoard - kit de visualização de ML do Google

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operational guide for the NV oOS Model Foundry (Proposal 067) — the cluster fine-tuning flywheel. Phase 1 shipped: the Corpus Foundry (Pro addon, addons/pro/includes/model-foundry/) — consent-gated, deduplicated, PII-scrubbed corpus exporters (trajectory_v1, preference_v1, docs_v1) with deterministic holdout splits and R12 provenance manifests. Covers the governance contract, row schemas, output layout, filter seams, the registration pattern for foundry tool slices, how to add a new exporter, and the test/validation gates. Use when extending the Corpus Foundry, debugging corpus exports, wiring a new data source, or continuing Phases 2–6 (train-worker, registry/serving, eval gate, fleet sharing).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI 어시스턴트에 외부 기능과 데이터를 제공하는 MCP 서버의 구축과 유지보수를 돕습니다. Node/TypeScript 기능 등록, 입력 검증, 통신 방식 선택을 다룹니다.

• AI용 MCP 서버를 구축할 때
• 작업, 데이터, 지시 템플릿을 추가할 때
• 로컬과 원격 연결 방식을 선택할 때

Build and debug Apify Actors, cloud programs for web scraping, automation, and data processing. Get guidance on language templates, input and output schemas, runtime code, local testing, and deployment, with practices for handling credentials and external data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an Actor for web scraping
• Defining Actor inputs and structured outputs
• Debugging an Actor with local test data

Add monitoring to AI agents with response times, token usage, estimated costs, and error metrics. Trace records follow model and tool calls step by step, helping teams investigate failures and understand operating costs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate slow agent responses
• Track token usage and estimated costs
• Trace failures in model and tool calls

Choose a model training method and configuration from paired response preferences or individual positive and negative ratings. Covers DPO, ORPO, KTO, and SimPO, including pair construction, repeated training rounds, and troubleshooting learning settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a training method for paired response preferences
• Select a method for individual positive and negative ratings
• Review learning settings when DPO training loses general capability

Build and troubleshoot MCP servers, which connect AI agents to external tools, for codewhale. Covers local and remote connections, credential configuration, tool validation, and testing both successful requests and failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an MCP server for a local tool
• Connecting codewhale to a remote service
• Configuring credentials and connection headers

Use OpenViking MCP tools to retrieve relevant knowledge before substantial tasks and save lasting preferences, decisions, and lessons during or after work. Import documents as searchable resources so later tasks can draw on previous findings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieve previous fixes before debugging
• Save lasting preferences and working conventions
• Record decisions and their rationale

Generate database relationship diagrams from Entity Framework Core models, mappings, and migrations. Produce D2 diagram source showing tables, keys, relationships, and constraints, with display options for columns and grouping. The d2 CLI can render SVG or PNG images.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Document an EF Core project's database structure
• Review primary keys and foreign key relationships
• Visualize owned types and many-to-many join tables

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

Use LangSmith to record LLM application inputs, outputs, and timing, investigate failures, evaluate answers against test datasets, and monitor production usage. It also guides automated quality checks and analysis of token usage and costs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failures in LLM applications
• Evaluating answers against test datasets
• Monitoring production latency and costs

Query documents and conversations stored in cognee to retrieve answers, supporting passages, or context for an AI model. This skill guides search method selection, source filtering, result interpretation, and troubleshooting empty or unexpected results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Searching selected datasets or conversation sessions
• Retrieving supporting passages or model context
• Choosing a search method for a question

Build AI features for Dart and Flutter applications with the Genkit Dart SDK. Provides code and documentation for conversational agents, reusable processing flows, prompt files, model integrations, interactive interfaces, and debugging through recorded execution traces.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a conversational AI agent to a Flutter app
• Building AI processing flows in Dart
• Managing prompts in separate files

Build AI applications in Python with Genkit, including conversational agents, generation workflows, streaming responses, and tool use. The skill also guides setup and debugging through traces, recorded details of model inputs, outputs, and actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a chatbot that keeps conversation history
• Implement streaming responses and tool calls
• Investigate Genkit import and API errors

Helps AI agents recover from repeated failures by reviewing previous attempts, checking original sources, testing different hypotheses, and verifying results. It combines structured troubleshooting with performance review rhetoric modeled on large technology companies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Breaking out of repeated failed attempts
• Investigating configuration or deployment failures
• Verifying an agent's claimed completion

Learn how instructions, documents, tool results, and conversation history form an AI model’s context. Understand attention limits, why information in the middle can be missed, and how relevance and placement inform decisions about what to include.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning the basics of context engineering
• Understanding why more input does not always help
• Explaining how instruction placement affects attention