「output」の検索結果

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

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。

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。

Use when adding/modifying Formax slash commands (/permissions /agents /hooks /todos etc), especially output rendering (command sublines), overlay dismiss messages, and whether outputs are injected into the next LLM turn.

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 prompting a learner to complete hands-on MATLAB coding exercises, guided practice, debugging drills, code tracing, small MATLAB projects, or MATLAB-script assessment during tutoring. Use when the tutor should create a complete runnable MATLAB script, execute it through MATLAB tools, compare the produced outputs with expected outputs, and evaluate MATLAB programming style.

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 weekly customer-discovery cadence and Opportunity Solution Tree practice using Teresa Torres's Continuous Discovery Habits framework during PRD v1.0 Market Adoption. Triggers on requests to set up discovery cadence, build opportunity solution tree, run weekly customer interviews, or when user asks "Torres", "continuous discovery", "opportunity solution tree", "outcomes vs outputs", "weekly interviews", "assumption mapping". Outputs CFD-* discovery entries and updates to ADO-STAGE-* and PER-* with new 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。

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

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。

Implement safety guardrails for AI systems — content filtering, prompt injection detection, output validation, bias mitigation, and responsible AI practices. Use when tasks involve adding safety layers to LLM applications, detecting prompt injection attacks, filtering harmful content, implementing rate limiting for AI APIs, validating LLM outputs against schemas, building moderation pipelines, or ensuring AI systems comply with safety policies.

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。

Run AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions 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。

LLM application architecture expert for RAG, prompting, agents, and production AI systemsUse when "rag system, prompt engineering, llm application, ai agent, structured output, chain of thought, multi-agent, context window, hallucination, token optimization, llm, rag, prompting, agents, structured-output, anthropic, openai, langchain, ai-architecture" 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。

Comprehensive patterns for AI-powered document understanding including PDF parsing, OCR, invoice/receipt extraction, table extraction, multimodal RAG with vision models, and structured data output. Use when "document parsing, PDF extraction, OCR, invoice processing, receipt extraction, document understanding, LlamaParse, Unstructured, vision document, table extraction, structured output from PDF, " 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。

Comprehensive patterns for building AI-powered code generation tools, code assistants, automated refactoring, code review, and structured output generation using LLMs with function calling and tool use. Use when "code generation, AI code assistant, function calling, structured output, code review AI, automated refactoring, tool use, code completion, agent code, " 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。

Andy Grove 视角. Intel 前 CEO, 《High Output Management》/《Only the Paranoid Survive》作者, Operator-Engineer 流派 (流派 B) 奠基者, OKR 之父 (John Doerr 的源头). 把 CEO 工作当工程系统管: 产出 = 组织产出, 经理杠杆率, OKR, 战略拐点 (SIP), 建设性对抗. 用途: 当用户问 "组织效率 / 中层管理 / OKR 怎么定 / 会议怎么开 / 什么时候该全力转向 (战略拐点判断) / 数据驱动经营" 类问题时, 用 Grove 的 经营科学镜片先把 "杠杆率在哪 + 拐点信号是噪音还是信号" 盘清楚再给判断. 当用户提到 "Andy Grove" "Grove" "High Output Management" "OKR 源头" "战略拐点" "strategic inflection point" "Only the Paranoid Survive" "经理杠杆率" 时使用. 即使用户只是说 "用 Grove 思路看一下" 也应触发.

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。

亚马逊管理之道 (亚马逊管理之道 (The Amazon Way — Amazon 自身的领导力与运营操作系统) — 这个 master skill 蒸馏的不是『在亚马逊平台上开店卖货』(那是跨境电商运营,已由 cross-border-ecommerce 另蒸),也不是 AWS 云技术架构;而是亚马逊这家公司『怎么运营自己、怎么做决策、怎么招人、怎么创新、怎么规划』的一整套可迁移的管理机制(mechanisms)与心智操作系统。面向想在自己团队/公司引入亚马逊式机制的创始人/CEO/高管/运营负责人(COO)、产品经理与技术产品经理(PM/PMT)、组织与流程设计者(chief of staff / ops)、以及在亚马逊工作或准备面试亚马逊(著名的 LP 行为面试 + Bar Raiser)的人。覆盖: (a) 第一性张力 — 亚马逊 OS 的核心世界观分歧: **机制 > 良好意图(Good intentions don't work, mechanisms do:问题不能靠『下次更努力』修复,要装一个带检查闭环的自我强化流程) ⇄ 可控输入指标 vs 滞后输出指标(管你能控制的 input 如选品/价格/在库/配送速度,而非 revenue/股价这类滞后又不可控的 output) ⇄ 长期主义 vs 季度业绩(Day 1、willing to be misunderstood、用现金流+飞轮长期投入,宁可牺牲短期利润) ⇄ 客户执念 vs 竞争对手执念(working backwards 从客户倒推,而非从竞品或『我们能造什么』正推) ⇄ 叙事备忘录 vs PPT(6-pager + 开会前静默阅读、动手前先写 PR/FAQ;写作逼出清晰思考,禁 PowerPoint) ⇄ 单线程负责人/两个披萨团队 vs 协调税(separable、autonomous、one owner per initiative,砍掉跨团队依赖) ⇄ 高标准可学习可传递 vs 与生俱来(insist on the highest standards + Bar Raiser 招聘门,标准是 domain-specific 且能教的) ⇄ 节俭催生创造力 vs 血汗文化(frugality/约束驱动发明 —— 但 frugality + 高压 bar + URA 强制淘汰 = 文化阴暗面批判) ⇄ 两类决策(Type 1 不可逆/单向门 慎重 vs Type 2 可逆/双向门 高判断力个人快速决策,别用重流程拖慢))**; (b) 核心机制(mechanisms,本行的『工具栈』其实是一套运营机制而非软件) — Leadership Principles(14 条→2021 增至 16 条,是一套运营语言和决策仲裁器)、Working Backwards(从客户倒推:动手前先写新闻稿+常见问答 PR/FAQ)、叙事备忘录(6-pager narrative / 1-pager + silent reading 静默阅读、禁 PPT)、Weekly Business Review(WBR + metrics deck 指标看板)、input/output metrics(可控输入指标体系、DMAIC 式指标选择)、年度规划(OP1/OP2 + S-Team goals)、Bar Raiser(招聘机制,独立于用人经理的抬杠者拥有一票否决)、Two-Pizza Team / Single-Threaded Leader STL / separable teams、Correction of Errors(COE 事故复盘 + 5 Whys 五问法)、Andon Cord(安灯绳,借自丰田,一线可拉停)、Flywheel(飞轮:低价→更多客户→更多卖家→更多选品→更低成本结构→更低价)、Type 1/Type 2(单向门/双向门决策分级)、Regret Minimization Framework(遗憾最小化,贝索斯创业决策法); (c) 心智模型层 — customer obsession(客户执念是所有 LP 之首)、long-term thinking / Day 1(第二天就是停滞衰亡)、invent and simplify、ownership(主人翁,不说 that's not my job)、bias for action(可逆决策就快,speed matters)、disagree and commit(充分反对后即便不同意也全力执行)、frugality、dive deep(深入细节、不靠代理指标脱离一线)、think big、are right a lot(用强判断力和证伪自己的能力多做对的判断)、earn trust、deliver results; (d) 工作流/SOP — 用亚马逊方式发起一个新产品/业务(先写 PR/FAQ→评审→倒推着造)、如何跑一场 WBR、如何写和评审一份 6-pager(叙事流程 + 静默阅读)、Bar Raiser 招聘 loop、年度规划(OP1/OP2→S-Team goals→输入指标追踪)、事故后的 Correction of Errors; (e) 知识正典(en-primary,极其丰富且可取一手) — 贝索斯致股东信 1997-2021(1997 首封是奠基文本,每年附在信末;Day 1、遗憾最小化、long term)、《Working Backwards》Colin Bryar & Bill Carr(2021,运营机制圣经)、《The Everything Store》Brad Stone(2013,公司史)、《Amazon Unbound》Brad Stone(2021,权力与阴暗面续作)、《Invent and Wander》贝索斯文集(2020)、《The Amazon Way》/《Think Like Amazon》John Rossman(前亚马逊高管)、Amazon 官方 Leadership Principles 页(amazon.jobs,一手)、HBR『The Institutional Yes』(2007 贝索斯访谈); (f) 行业大佬/figures — Jeff Bezos(创始人,源头教义)、Andy Jassy(现任 CEO,OS 超越创始人的证据 + AWS 缔造者)、Colin Bryar(前贝索斯影子/TPM,《Working Backwards》作者)、Bill Carr(前数字媒体 VP,《Working Backwards》作者)、Jeff Wilke(前全球消费者 CEO,运营架构师)、John Rossman(前亚马逊、机制布道者/顾问)、Brad Stone(记者/编年史作者,批判性外部视角); (g) 争议/批判(必须保留,不能洗白) — 文化阴暗面(NYT 2015『Inside Amazon: Wrestling Big Ideas in a Bruising Workplace』揭露高压职场)、仓储与一线劳工争议、URA(unregretted attrition 强制淘汰)与 stack-ranking 的残酷、frugality + 高 bar = 燃尽(burnout);机制能否迁出亚马逊(cargo-culting:在初创或非科技公司照搬 PR/FAQ/输入指标/Bar Raiser 常失败);是贝索斯个人天才(personality)还是制度化机制(institution)—— OS 在贝索斯卸任后于 Jassy 治下延续,是机制派的证据; (h) 流派/思想谱系 — **信徒/机制布道派(Bryar & Carr《Working Backwards》+ 前亚马逊 operator 顾问圈,信 mechanisms 可移植、任何公司可安装)** vs **批判派(Brad Stone《Amazon Unbound》+ NYT + 劳工视角,认为 OS 与高淘汰的残酷机器不可分割,不该被浪漫化)** vs **情境/规模怀疑派(机制之所以有效是因为亚马逊特定的规模/现金流/创始人权力,照搬到小公司=cargo cult)** vs **创始人中心 vs 制度中心之争(是贝索斯个人 vs 可传承的机制)**。不含: 在亚马逊开店卖货/选品/PPC/FBA 的卖家运营(=cross-border-ecommerce)、AWS 云技术架构与运维、通用 MBA 管理理论泛泛而谈、把普通商业常识包装成『亚马逊独家秘诀』。) Master OS — automated mastery of 亚马逊管理之道 (The Amazon Way — Amazon 自身的领导力与运营操作系统) — 这个 master skill 蒸馏的不是『在亚马逊平台上开店卖货』(那是跨境电商运营,已由 cross-border-ecommerce 另蒸),也不是 AWS 云技术架构;而是亚马逊这家公司『怎么运营自己、怎么做决策、怎么招人、怎么创新、怎么规划』的一整套可迁移的管理机制(mechanisms)与心智操作系统。面向想在自己团队/公司引入亚马逊式机制的创始人/CEO/高管/运营负责人(COO)、产品经理与技术产品经理(PM/PMT)、组织与流程设计者(chief of staff / ops)、以及在亚马逊工作或准备面试亚马逊(著名的 LP 行为面试 + Bar Raiser)的人。覆盖: (a) 第一性张力 — 亚马逊 OS 的核心世界观分歧: **机制 >

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。

Invokes Google Gemini models for structured outputs, image generation, text-to-speech narration, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, Gemini TTS or a synthesized voice, structured JSON output, Google API integration, or cost-effective parallel processing.

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。

Assign items to a CLOSED label vocabulary that is too large to put in a prompt — product taxonomies, category hierarchies, tag vocabularies, routing tables, ICD/SIC-style code lists. A cheap model writes the label it thinks the vocabulary would use, and an embedder snaps that writing onto the nearest legal value, so the schema is never transmitted and the output is always in-vocabulary. Use for "classify these into our taxonomy", "tag these against the existing tag list", "map these queries to categories", "the enum is too big to send", or a Literal/enum that hits a provider cap. NOT for a vocabulary that fits in a prompt — structured output measured 0.701 acc@1 there against this pattern's 0.564. NOT for open-ended labelling with no fixed vocabulary, and not for ranked retrieval over documents (bm25).

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。

Helps users report issues with GTM skills — incorrect advice, broken activation, missing context, or unexpected behavior. Guides through gathering the right details (skill name, prompt used, actual vs expected output, context files present) and generates a properly formatted GitHub issue. Use when users say: 'this skill gave wrong advice', 'report a bug', 'file an issue', 'skill isn't working', 'wrong output', 'skill didn't activate', 'bad recommendation', 'incorrect behavior', or 'something is broken'.

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 when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the form", "fill out this PDF", "complete the form fields", "write values into PDF", "what fields does this PDF have". REFORMAT (apply design to an existing doc): "reformat this document", "apply our style", "convert this Markdown/text to PDF", "make this doc look good", "re-style this PDF". This skill uses a token-based design system: color, typography, and spacing are derived from the document type and flow through every page. The output is print-ready. Prefer this skill when appearance matters, not just when any PDF output is needed.

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。

Render Blender scenes with the right engine and settings — Cycles for photoreal, EEVEE for speed/stylized, sample counts, denoising (OptiX/OIDN), light path tuning, color management (AgX/Filmic), file output (PNG/EXR/MP4), animation rendering. Use whenever the user asks to "render this", "produce an image", "render a frame / animation", "make a final image", "save the render", or any output-generation request. Make sure to use this skill even if the user does not say "render" — also covers "make a picture", "save the result", "produce a final image", "export as image".

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 a learning sequence teaching prompt quality — comparing vague vs. refined prompts to show why specificity and context transform AI output. Use when students use AI without understanding why output quality varies.

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。

Shape output for a reader with ADHD. Use this skill whenever responding to ANY user message including coding tasks, debugging, explanations, planning, and casual conversation. Output should lead with concrete next actions, number multi-step work, externalize state across turns, suppress tangents, give specific time estimates, and make wins visible. Trigger even on casual messages and even when the user did not explicitly ask for brevity.

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 guardrail layers — input classifiers, output validators, PII scrubbers, policy rule engines. Use when asked to "add safety filters", "scrub PII from LLM output", or "design content moderation".

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 intelligent model cascading and routing — complexity-scored task routing from Flash/Haiku to Sonnet/Opus/Astra, dynamic escalation with quality gates, 40-60% token cost reduction while maintaining output quality / Panduan ahli untuk kaskade dan routing model cerdas — routing tugas berbasis skor kompleksitas dari Flash/Haiku ke Sonnet/Opus/Astra, eskalasi dinamis dengan gerbang kualitas, pengurangan biaya token 40-60% dengan kualitas output terjaga.

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。

office ドキュメント・画像などの一次情報から、anthropics/skills（markdown 化）と agent-ocr（画像OCR）を使って /spec/output/docs に統合された要件定義書一式（仕様書）を作成する。