「llm」の検索結果

Add fast, local, typed decisions to any project with Laya, an open-source non-generative decision model (pip install laya). It classifies, routes, scores and answers yes/no questions about a piece of text, returning calibrated probabilities in roughly 20-35 ms on a laptop GPU, with no LLM call and no data leaving the machine. Use this skill whenever the user wants to classify or route text, triage tickets or emails, detect spam, phishing, toxicity or intent, put a guardrail in front of an agent or LLM, score something against a rubric, or replace an LLM-based classifier to cut latency or cost. Also use it when they mention Laya, Jev, a "System 1 model", "typed decisions" or a "decision model", even if they never name Laya.

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。

Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels. Establish quantization and cache differences, preserve upstream structure, and distinguish shared upstream bugs from adaptation defects. Use for model support work, not standalone monkey-patch or registry audits.

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。

Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades. Use as the common prerequisite of the patch, attention, registry and model upgrade skills, or for an explicitly requested MetaX environment preflight; it does not perform domain-specific adaptations.

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。

You are an expert in Crawl4AI, the open-source web crawler built for AI applications. You help developers extract clean, structured data from websites for LLM training, RAG pipelines, and content analysis — with automatic markdown conversion, JavaScript rendering, CSS-based extraction, LLM-powered structured extraction, and session management for multi-page crawling.

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。

Expert guidance for DeepEval, the open-source framework for unit testing LLM applications. Helps developers write test cases, define custom metrics, and integrate LLM quality checks into CI/CD pipelines using a pytest-like interface.

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。

Braintrust is a hosted platform for evaluating and tracing LLM applications: it runs a task over a dataset, scores the outputs, stores each run as an experiment and logs production traces. Use when a user asks to write or run a Braintrust eval, score LLM outputs with autoevals, compare prompt or model versions as experiments, run evals in CI and fail on regressions, trace OpenAI or Anthropic calls with Braintrust, manage evaluation datasets, or use the bt CLI.

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。

Arize is an AI observability platform, and Phoenix is its open-source tracing and evaluation tool for LLM applications. Use this skill when the user wants to trace OpenAI or LangChain calls, run a local Phoenix server, score RAG answers for faithfulness, debug slow or wrong LLM responses, or send OpenTelemetry traces to Arize for production monitoring.

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。

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementations. The LLM never sees your code - it only sees the schema and description. Use when "agent tool, function calling, tool schema, tool design, mcp server, mcp tool, tool use, build tool for agent, define function, input_schema, tool_use, tool_result, agents, tools, function-calling, mcp, json-schema, anthropic, openai, llm-tools" mentioned.

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。

Generate and maintain llms.txt files for AI discoverability. Scans repos to create curated content maps that help AI answer engines surface your project accurately. Implements the llms.txt specification from Answer.AI.

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。

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".

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。

AI 短剧 (AI 微短剧) (AI 短剧 (AI 微短剧) (从业者视角) — 用 AIGC 工具（AI 视频生成 / AI 脚本 / AI 生图 / AI 配音 / 对口型 / 角色一致性）制作竖屏微短剧并变现的新兴行业。覆盖: (a) 创作工作流 — 选题→剧本/分镜→AI 生图→图生视频(首尾帧/运镜/参考)→配音/对口型→剪辑/调色→成片，其中角色/场景一致性是第一性难题; (b) 工具栈 — 视频生成(可灵 Kling / 即梦 Seedance / 海螺 Hailuo / Vidu / Runway Gen / OpenAI Sora / Pika / Luma / Pixverse)、脚本(LLM)、生图(Midjourney/SD/即梦)、配音(TTS)、对口型、剪辑(剪映/CapCut); (c) 商业/变现 — 国内付费投流(IAP + ROI + 平台分账, 抖音/快手/红果/微信小程序短剧)与海外订阅(ReelShort/DramaBox/ShortMax/GoodShort)两套打法、品牌定制、成本结构; (d) 合规 — 中国《人工智能生成合成内容标识办法》(2025-09 强制 AI 标识)、广电微短剧备案与分类分层审核、版权与肖像权。主战场 = 抖音/快手/视频号/B站 + 海外短剧 App。学派分歧: 纯 AI vs AI+实拍混合、国内投流 vs 海外订阅、视频工具派之争、「AI 短剧是真需求还是伪风口」。不含: 传统实拍短剧制作、通用影视编剧(已有 scriptwriting skill)、短视频信息流投放(已有 short-video-ads skill)、纯 AI 视频底层技术研发。) Master OS — automated mastery of AI 短剧 (AI 微短剧) (从业者视角) — 用 AIGC 工具（AI 视频生成 / AI 脚本 / AI 生图 / AI 配音 / 对口型 / 角色一致性）制作竖屏微短剧并变现的新兴行业。覆盖: (a) 创作工作流 — 选题→剧本/分镜→AI 生图→图生视频(首尾帧/运镜/参考)→配音/对口型→剪辑/调色→成片，其中角色/场景一致性是第一性难题; (b) 工具栈 — 视频生成(可灵 Kling / 即梦 Seedance / 海螺 Hailuo / Vidu / Runway Gen / OpenAI Sora / Pika / Luma / Pixverse)、脚本(LLM)、生图(Midjourney/SD/即梦)、配音(TTS)、对口型、剪辑(剪映/CapCut); (c) 商业/变现 — 国内付费投流(IAP + ROI + 平台分账, 抖音/快手/红果/微信小程序短剧)与海外订阅(ReelShort/DramaBox/ShortMax/GoodShort)两套打法、品牌定制、成本结构; (d) 合规 — 中国《人工智能生成合成内容标识办法》(2025-09 强制 AI 标识)、广电微短剧备案与分类分层审核、版权与肖像权。主战场 = 抖音/快手/视频号/B站 + 海外短剧 App。学派分歧: 纯 AI vs AI+实拍混合、国内投流 vs 海外订阅、视频工具派之争、「AI 短剧是真需求还是伪风口」。不含: 传统实拍短剧制作、通用影视编剧(已有 scriptwriting skill)、短视频信息流投放(已有 short-video-ads skill)、纯 AI 视频底层技术研发。: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on AI 短剧 (AI 微短剧) (从业者视角) — 用 AIGC 工具（AI 视频生成 / AI 脚本 / AI 生图 / AI 配音 / 对口型 / 角色一致性）制作竖屏微短剧并变现的新兴行业。覆盖: (a) 创作工作流 — 选题→剧本/分镜→AI 生图→图生视频(首尾帧/运镜/参考)→配音/对口型→剪辑/调色→成片，其中角色/场景一致性是第一性难题; (b) 工具栈 — 视频生成(可灵 Kling / 即梦 Seedance / 海螺 Hailuo / Vidu / Runway Gen / OpenAI Sora / Pika / Luma / Pixverse)、脚本(LLM)、生图(Midjourney/SD/即梦)、配音(TTS)、对口型、剪辑(剪映/CapCut); (c) 商业/变现 — 国内付费投流(IAP + ROI + 平台分账, 抖音/快手/红果/微信小程序短剧)与海外订阅(ReelShort/DramaBox/ShortMax/GoodShort)两套打法、品牌定制、成本结构; (d) 合规 — 中国《人工智能生成合成内容标识办法》(2025-09 强制 AI 标识)、广电微短剧备案与分类分层审核、版权与肖像权。主战场 = 抖音/快手/视频号/B站 + 海外短剧 App。学派分歧: 纯 AI vs AI+实拍混合、国内投流 vs 海外订阅、视频工具派之争、「AI 短剧是真需求还是伪风口」。不含: 传统实拍短剧制作、通用影视编剧(已有 scriptwriting skill)、短视频信息流投放(已有 short-video-ads skill)、纯 AI 视频底层技术研发。 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「ai 短剧」「ai 微短剧」「ai short drama」「ai 短剧制作」「ai 短剧工作流」

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。

Audits any landing or service page across 48 checks in 10 categories for LLM/AI discoverability, GEO readiness, content clarity, schema markup, internal linking, freshness signals, and technical crawlability. Produces an overall score out of 100, a per-category score out of 100, pass/warn/fail/ manual counts, and a prioritised fix list — all rendered as a standalone HTML report saved to disk. Use when a user provides a URL and asks to audit it, score it, check its GEO readiness, test its AI discoverability, run a landing page audit, or evaluate it for LLM citation potential. Also trigger on phrases like "audit this page", "score this URL", "check GEO for", "is this page AI-ready", "run a GEO audit", "LLM page check", "how would AI read this page", or "landing page score".

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。

Optimize Ollama configuration for the current machine's hardware. Use when asked to speed up Ollama, tune local LLM performance, or pick models that fit available GPU/RAM. Don't use for LM Studio, llama.cpp, vLLM, or hosted-API LLM providers.

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。

LLM serving for latency, batching, caching, quantization, and routing. Use when tuning vLLM or SGLang, sizing KV cache, adding speculative decoding, or cutting serving cost.

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。

LLMOps Architect: Run LLM features in production: model routing, evals, observability, caching, cost, safety.

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 common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

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 common LLM coding agent artifacts across four categories (tests, dead code, abstraction, style) over the project or changed files — using parallel subagents when the agent supports them, otherwise four sequential passes. Scans files changed since main by default; use --all for full-project scan. Triggers on LLM cruft cleanup, agent-generated code review, dead code sweeps, test-quality passes, or when the user asks to scan the whole repo.

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。

Applies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artifacts output when present to skip false positives.

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。

Confirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verification-protocol-style checks per finding. Use after a review run, when the user wants to reduce false positives, before fix-llm-artifacts on dead code, or when validating a full-project scan.

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。

Sichtbarkeit, Zitierung und Empfehlung in KI-Antwortsystemen für Deutschland und den DACH-Raum evidenzbasiert prüfen und verbessern. Nutze diesen Skill, wenn eine Marke oder Seite in KI-Overviews, ChatGPT, Perplexity, Gemini oder Copilot auftauchen soll, wenn Crawler-Freigaben für KI-Bots, llms.txt, strukturierte Daten oder die Extrahierbarkeit von Inhalten zu bewerten sind, oder wenn jemand nach AEO, GEO oder LLMO fragt. Trennt Abruf, Zitierung, Erwähnung und Empfehlung, prüft Behauptungen über KI-Rankingfaktoren gegen Primärquellen und verspricht keine Sichtbarkeit. Für klassisches technisches SEO ist seo-audit zuständig.

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。

Design an LLM eval — task schema, scoring rubric, dataset composition, and pass/fail thresholds. Use when asked to "design an LLM eval", "write a scoring rubric", or "how do we measure this 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。

Expert guide for AI FinOps, dynamic model routing (LiteLLM, Portkey, RouteLLM), cost optimization, budget enforcement, semantic caching, and latency-based fallback architectures / Panduan ahli untuk AI FinOps, routing model dinamis, optimasi biaya, penegakan anggaran, semantic caching, dan arsitektur fallback berbasis latensi.

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。

Expert guide for LLM observability in production — token cost tracking, hallucination rate monitoring, latency analysis, prompt/completion logging, model comparison dashboards, and AI-specific tracing (Langfuse, Helicone, Lunary, OpenTelemetry GenAI) / Panduan ahli observabilitas LLM di produksi — pelacakan biaya token, pemantauan tingkat halusinasi, analisis latensi, logging prompt/completion, dashboard perbandingan model, dan tracing khusus AI.

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。

Expert guide for integrating Large Language Models (LLMs), Model Context Protocol (MCP v1.x), hybrid reasoning models, RAG architecture, vector databases, and AI agents / Panduan ahli untuk integrasi LLM, Model Context Protocol (MCP), model hybrid reasoning, arsitektur RAG, vector database, dan agen AI.

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。