「vin」の検索結果

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

日本語の概要は準備中です。原文の説明を表示しています。

Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attention (Mamba / GDN / KDA) model's two serving memory pools, from the workload and serving config. Use when a user asks what ratio to set, why concurrency is clamped, or how to size the state vs KV pools for a hybrid model.

日本語の概要は準備中です。原文の説明を表示しています。

Detect abuse of legitimate Windows binaries (LOLBins) used for living off the land attacks. Monitors process creation, command-line arguments, and parent-child relationships to identify suspicious LOLBin execution patterns.

日本語の概要は準備中です。原文の説明を表示しています。

Detect Living Off the Land Binaries (LOLBins/LOLBAS) abuse including certutil, regsvr32, mshta, and rundll32 via process telemetry, Sigma rules, and parent-child process analysis with Sysmon endpoint data. Use when hunting for adversaries abusing built-in Windows binaries to download, execute, or proxy malicious code while evading traditional executable-based detection.

日本語の概要は準備中です。原文の説明を表示しています。

Detects fileless malware and in-memory attacks that execute entirely in RAM without writing persistent files to disk, evading traditional antivirus. Use when building detections for PowerShell-based attacks, reflective DLL injection, WMI persistence, and registry-resident malware. Activates for requests involving fileless malware detection, in-memory attacks, PowerShell exploitation, or living-off-the-land techniques.

日本語の概要は準備中です。原文の説明を表示しています。

Detects and analyzes fileless malware that operates entirely in memory using PowerShell, WMI, .NET reflection, registry-resident payloads, and living-off-the-land binaries (LOLBins) without writing traditional executable files to disk. Use for requests involving fileless threat detection, in-memory malware investigation, LOLBin abuse analysis, or WMI persistence examination.

日本語の概要は準備中です。原文の説明を表示しています。

Create forensically sound bit-for-bit disk images with dd or dcfldd on a Linux forensic workstation, preserving evidence integrity through hash verification (MD5/SHA) during acquisition. Use when imaging a suspect drive, USB device, or memory card for investigation, preserving volatile disk evidence during incident response, or producing a verified copy for legal or law-enforcement proceedings before any destructive analysis.

日本語の概要は準備中です。原文の説明を表示しています。

Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when an organization handles Controlled Unclassified Information (CUI) under a DoD contract, when a contract carries DFARS clause 252.204-7012/7019/7020/7021, when preparing for or responding to a CMMC assessment, when computing or improving an SPRS score, when building a System Security Plan or POA&M for 800-171, or when scoping which systems are in the CUI boundary. Keywords: CMMC, CMMC Level 2, NIST 800-171, SP 800-171 Rev 2, CUI, FCI, SPRS, DFARS 7012, C3PAO, POA&M, System Security Plan, DoD Assessment Methodology, 110 controls, defense industrial base, DIB, FedRAMP equivalency.

日本語の概要は準備中です。原文の説明を表示しています。

Use this skill whenever a developer wants to turn an idea into a complete, production-ready, end-to-end system plan BEFORE writing any code. Trigger on 'plan this system', 'design the architecture for', 'help me blueprint', 'deep plan for X', 'break this idea into components', 'expand into action points', 'full implementation plan', or when the user pastes a project idea wanting architecture, components, pipelines, and file-level execution mapped out. Casual phrasing also triggers: 'help me think this through end-to-end', 'plan before coding'. Also covers living-workspace patterns: self-improving knowledge bases, reflection loops with auditor agents, four-agent teams, schema-as-code, wiki health scoring. **Resume triggers**: 'where did we leave off', 'continue this plan', 'resume my blueprint' - rehydrates state from disk via SESSION.md/NEXT.md/decisions/. Web research is mandatory every invocation.

日本語の概要は準備中です。原文の説明を表示しています。

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

日本語の概要は準備中です。原文の説明を表示しています。

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

日本語の概要は準備中です。原文の説明を表示しています。

Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model evaluations.

日本語の概要は準備中です。原文の説明を表示しています。

Put your AI on a Performance Improvement Plan. Forces exhaustive problem-solving with Western big-tech performance culture rhetoric and structured debugging. Trigger when: (1) task failed 2+ times or stuck tweaking same approach; (2) about to say 'I cannot', suggest manual work, or blame environment without verifying; (3) being passive—not searching, not reading source, just waiting; (4) user frustration: 'try harder', 'stop giving up', 'figure it out', 'again???', or similar. Also for complex debugging, env issues, config/deployment failures. All task types: code, config, research, writing, deployment, infra, API. Do NOT trigger on first-attempt failures or when a known fix is executing.

日本語の概要は準備中です。原文の説明を表示しています。

Installs the CARLA Autonomous Driving Leaderboard (leaderboard.carla.org) at a chosen version — 1.0, 2.0 or 2.1 — together with the exact scenario_runner branch and CARLA build each one requires, then wires the four-root PYTHONPATH and verifies the whole stack imports. Detects which version an existing checkout is by reading its code, not its branch name. Use when the user asks to "install the leaderboard", "set up the CARLA challenge", "evaluate my driving agent", "reproduce my leaderboard score", or names a leaderboard version.

日本語の概要は準備中です。原文の説明を表示しています。

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

日本語の概要は準備中です。原文の説明を表示しています。

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.

日本語の概要は準備中です。原文の説明を表示しています。

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

日本語の概要は準備中です。原文の説明を表示しています。

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnose and draft or explicitly apply paid-ad optimizations using evidence, financial constraints, experiments, and capability-gated adapters. Use for campaign optimization, budget reallocation, bid changes, pausing or archiving ads, requests to delete campaigns, search-term or negative-keyword actions, creative rotation, or improving CPA and ROAS.

日本語の概要は準備中です。原文の説明を表示しています。

Configures mewt or muton campaigns, analyzes surviving mutants, and investigates bugs exposed by testing gaps. Use when setting up mutation testing, reviewing campaign results, identifying equivalent mutants, or finding bugs from surviving mutations.

日本語の概要は準備中です。原文の説明を表示しています。

Create or update reusable iPolloWork templates through conversation for Design, Slides/native editable PPT, and HyperFrames Video. Use when planning, generating, repairing, validating, or saving a template package, manifest, reusable variables, cover, slide/PPT markers, video composition, or design-system token integration.

日本語の概要は準備中です。原文の説明を表示しています。

Reconcile bounded Stripe payment and payout records with supplied business records while preserving object IDs, currency, time zone, and discrepancy evidence.

日本語の概要は準備中です。原文の説明を表示しています。

Verify a production fix by linking the changed code and release to Sentry issue state and post-release event trends without resolving issues prematurely.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user explicitly chooses iPollo Onto or starts an Onto workbench task. Build and maintain business systems directly in its connected tables, relationships and documents, saving useful results progressively. A generic CRM, search or writing request alone does not activate this workflow.

日本語の概要は準備中です。原文の説明を表示しています。