3,741 件 ・ 関連度順
概要と使いどころ
Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.
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。
Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).
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。
Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minutes-live-sidekick. An ambiguous request such as "coach me live" requires one short surface clarification and must not automatically start Coach.
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。
Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.
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。
Select QA-approved canonical intent cells into a versioned AI-visibility tracking panel with partitions, variants, lanes, surfaces, locales, repetitions, separate exposure and priority weights, randomization, uncertainty, refresh rules, and campaign controls. Use after prompt QA or when revising an existing panel.
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 natural, controlled prompt variants from a target-blind design brief and prompt architecture while preserving approved jobs, acts, journeys, constraints, roles, locales, proximity bands, and evidence language. Use after architecture design and before contamination or semantic QA.
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 systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component, function, or line is faulty. Covers binary search debugging, git bisect for regressions, strategic logging with [TRACE] patterns, data and control flow tracing, component isolation, minimal reproduction cases, conditional breakpoints, and watch expressions across TypeScript, SQL, and bash.
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。
Security planning and plan-drift analysis for STRIDE, standards, controls, backlog handoff, current findings, and TM7 generation.
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。
Text-to-speech voice-over generation from YAML speaker notes using Azure Speech SDK with SSML pronunciation control, or an offline Piper engine that needs no credentials
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, update or review presentation-first HTML slide decks about HVE Core under slides/. Use for slide content research, deck styling, VS Code-style walkthroughs, presenter controls, or single-file HTML sharing in this repository.
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。
Programmatic screenshot capture on macOS. Find window IDs with Swift CGWindowListCopyWindowInfo, control application windows via AppleScript (zoom, scroll, select), and capture with screencapture. Use when automating screenshots, capturing application windows for documentation, or building multi-shot visual 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。
Creates formatted Excel reports with openpyxl, parses complex xlsm financial models with stdlib zipfile+xml when openpyxl fails, and controls Excel windows on macOS via AppleScript. Reconstructs images or scans of paper forms as editable XLSX files with printable layouts.
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。
Generates Chinese/Japanese speech with StepFun's Contextual TTS — default stepaudio-2.5-tts, stepaudio-3-tts for whisper/inline-() prosody. Replaces step-tts-2's voice_label with natural-language instruction. Use for emotional/prosody-controlled synthesis, batch voice lines, migrating from step-tts-2, or cloned voices (2.5/step-tts-2, not v3). Triggers on 阶跃 TTS, 语音合成, 配音. Not for transcription (use stepfun-asr).
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 asked 等保怎么做, 等保 2.0 定级, 等保备案和测评流程, 等保三级要求, 我们的系统需要过等保吗, or prepare an information system for China's Multi-Level Protection Scheme (MLPS 2.0, 网络安全等级保护). Produces a grading recommendation (定级) with the reasoning for the expert review, the filing (备案) and assessment (测评) steps and their usual timing, a gap checklist across the ten control areas of GB/T 22239-2019, and a remediation plan, marked as preparation for a licensed assessor.
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 asked 写8D报告, 客户投诉8D, 质量问题8D, 客诉回复报告, 8D 怎么写, 根本原因分析报告, or write an 8D problem-solving report for a customer complaint or internal quality issue in a Chinese factory. Produces a bilingual (Chinese and English) 8D report from D0 to D8 with the problem described by 5W2H, dated containment actions and suspect-stock quantities, root cause for both occurrence and escape (流出) with 5 Why and fishbone evidence, verified corrective actions, prevention through updated PFMEA, control plan and SOP, and closure criteria, in the format customers expect.
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。
Compare childcare options — nursery/daycare, childminder, nanny, family, or a mix — for your family's real needs, budget, and values. Use when asked to compare childcare options, nursery vs nanny, how to choose childcare, or find the right childcare. Produces a needs-and-values profile, a side-by-side of the realistic options on cost/flexibility/socialization/control, the questions to ask and red flags to check on visits, a total-cost read (including subsidies), and a decision that fits your priorities — not a generic ranking.
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 asked 回复询盘, 外贸询盘怎么回, 帮我回客户邮件, 阿里国际站询盘回复, 客户只问价格怎么回, 跟进没回复的客户, or reply to a foreign-trade inquiry from a Chinese exporter. Produces a reply email in English (or the buyer's language) with a Chinese version for the sales team, a read of the inquiry's quality and the buyer's likely type, the questions to qualify the buyer, a price or quotation approach without underselling, and a follow-up sequence for no reply, with export-control and sanctions checks flagged.
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 a realistic personal monthly budget from someone's income and expenses. Use when asked to make a budget, plan monthly spending, allocate income, or get finances under control. Produces a categorized budget (a 50/30/20-style allocation tuned to their reality), a surplus/shortfall number, and concrete next moves. Educational, not regulated financial advice.
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 the pre-flight checklist before an agent drives a browser — the untrusted-web-content threat (every page is attacker-controllable), the credential and session-cookie exposure, the action-confirmation gates for purchases and posts, and the sandboxing that limits the damage. Use when asked let my agent browse safely, is it safe to give the agent computer/browser use, guardrails before the agent uses my browser, or review my browser agent's setup. Produces the sandbox decision, the content-injection defenses, the action gates, and the credential-isolation rules.
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 a realistic recovery plan for burnout — address the causes, not just the symptoms — with changes you can actually make at work and outside it. Use when asked to help with burnout, I'm burnt out, how to recover from burnout, or I'm exhausted and dread work. Produces a read on what's driving the burnout (load, control, reward, fairness, values, community), immediate relief steps, the boundary and workload changes that address the root, a recovery timeline with realistic expectations, and a flag that severe or persistent burnout/depression warrants a professional. Not medical advice.
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。
Specify an autonomous or tool-using AI agent before building it. Use when asked to design an AI agent, define an agent's tools and guardrails, scope what an agent is allowed to do, or write an agent spec/PRD. Produces an agent spec — goal & scope, tools with permissions, the control loop, guardrails & approval gates, memory, escalation/handoff, evaluation, and failure handling.
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 an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.
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。
Help users interact with probabilistic models by designing interfaces that manage fluidity, intent, and agency while maintaining trust and control.
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。
Browser automation platform with 78 built-in scripts and full CLI. Turn any website into structured data with one command. Use when the user needs to scrape websites, extract data, automate browsers, run built-in scripts (Hacker News, GitHub trending, Bilibili, Zhihu, stock data, etc.), navigate pages, fill forms, take screenshots, or control Chrome programmatically. Triggers include "scrape", "extract data", "browser automation", "web data", "trending", "hot topics", "stock data", "run script", "open website", "fill form", "screenshot", "headless browser".
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。