「llm」の検索結果

Manage LLM context windows deliberately — budgeting, prioritization, summarization, and retrieval instead of dumping everything in. Use when prompts grow long, costs rise, or the model loses track of key details.

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。

NLP on clinical text — de-identification, concept extraction, phenotyping from notes, and LLM safety guardrails.

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。

Ship AI features to production — model selection, evals, latency/cost optimization, guardrails, monitoring, and iteration loops. Use when turning an LLM prototype into a reliable product feature.

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。

Build data-centric LLM applications with indexing and retrieval frameworks — document ingestion, indices, query engines, and RAG pipelines. Use when the core problem is getting the right data in front of the 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。

Design and build LLM agents: ReAct loops, tool schemas, planning, memory, guardrails, evals, and human-in-the-loop. Use when building autonomous multi-step AI systems.

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。

Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.

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。

Convert between LaTeX and Microsoft Word for academic manuscripts in either direction, and assemble .tex from mixed sources. Fires on: converting .tex/LaTeX to Word/.docx ("tex to docx", "latex to word", "tex2docx", "convert to word", "pandoc convert"); converting .docx manuscripts to LaTeX for editing and back ("convert to latex", "manuscript", "footnotes", "reference doc", the docx-to-tex-to-docx round-trip / academic paper editing pipeline); high-fidelity delivery where plain pandoc loses tables, mangles cross-references, or fails on custom macros — booktabs/regression tables, OMML equations, cleveref, \estauto, \@@input, \thanks, TikZ, native Word tables, longtable, siunitx; and building .tex from mixed PDF/docx/LLM-generated sources. Replaces and reroutes the retired skills manuscript-editing-template-latex, latex-to-docx-fidelity, tex2docx, and latex-from-mixed-sources.

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。

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.

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。

Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

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。

使用 OpenUI 构建生成式 UI 应用 — 支持任意 LLM 提供商、任意后端语言。脚手架、集成、验证。

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。

Build generative UI with OpenUI — any LLM provider, any backend language. Scaffold, integrate, validate.

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。

Set up LLM-as-judge evaluation for ORC workflows

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 a task needs the judgment of an Education and Childcare Administrator for Preschool/Daycare settings — running a preschool or childcare center's operations, evaluating a curriculum or staffing decision, handling a licensing/regulatory compliance issue, or balancing enrollment/financial sustainability against program 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。

Use when a task needs the judgment of a Postsecondary Education Administrator (dean, department chair, provost-level, or program director) — making a program/curriculum decision, managing faculty and enrollment/budget tradeoffs, evaluating an accreditation or academic policy issue, or balancing academic mission against institutional financial sustainability.

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 a task needs the judgment of a Clinical Research Coordinator — managing patient recruitment/enrollment against a trial's screen-fail rate, handling a protocol deviation, tracking informed consent and regulatory documentation, or coordinating a multi-visit study schedule against patient retention risk.

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 a task needs the judgment of a postsecondary Anthropology or Archaeology professor — designing a gen-ed or major-track course, building a tenure or promotion dossier, defending a department against an enrollment-driven program review, mentoring a graduate student's fieldwork grant application, or writing an IRB/NAGPRA-compliant fieldwork plan.

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 a task needs the judgment of an Area, Ethnic, or Cultural Studies Professor — designing a joint-appointment course load across two departments, prepping a tenure or mid-tenure review file for interdisciplinary scholarship, deciding whether a course survives an enrollment or political-pressure threat, evaluating community-engaged research for a merit case, or writing a Title VI/FLAS-adjacent grant narrative.

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。

Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.

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工程师角色。关键词：AI/LLM/智能体/Prompt/上下文工程/多智能体/工作流/RAG/Function Call/效果评测。激活后设计提示词、构建智能体调用链、评测输出质量。

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。

Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", or any reference to Hickey, Simple Made Easy, or grey-box review.

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。

Provision free LLM API keys from 20+ providers. Health-checks existing keys, opens signup pages, validates new keys, and saves them to your project.

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 a government or public services system for compliance, fraud risk, and security — chains benefits processing review, fraud detection analysis, regulatory compliance check (ADA, Section 508, FISMA, Privacy Act), and PII-focused security audit. Use for benefits platforms, eligibility engines, enrollment portals, or inter-agency data systems.

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。

Convert any pile of documents (PDF, Word, HTML pages, wiki exports, PowerPoint slides) into clean, LLM-ready markdown context: inventories the sources, picks the right extractor per file type (pdftotext or PyMuPDF for PDF, pandoc or mammoth for docx, readability extraction for HTML.

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。

Autonomous SEO + AI-search optimization agent for 2026. Audits and fixes technical SEO, on-page metadata, structured data, Core Web Vitals (LCP/INP/CLS), llms.txt, Generative Engine Optimization (GEO) for ChatGPT/Perplexity/AI Overviews, E-E-A-T author signals.

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。