「qa」の検索結果

Black-box QA audit of slop-guard across MCP, CLI, fit, docs, agent workflows, and writing-effectiveness. Files GitHub issues for real problems found.

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。

管理咨询 (管理咨询 (Management Consulting) — 战略与管理咨询的职业认知操作系统，从业者/咨询顾问/想入行者/采购咨询服务的客户视角。覆盖: (a) 第一性张力 — 假设驱动 (hypothesis-driven / answer-first / Day-1 answer) 的「先有答案再验证」⇄ 数据驱动 (data-led / bottom-up) 的「先穷尽事实再归纳」，这行的核心张力是「先射箭再画靶 vs 先画靶再射箭」，资深人偏 top-down 假设树减少 boil-the-ocean，但要时刻防 confirmation bias; 以及更深层的张力 — 「卖洞见 (insight / so-what) vs 卖工时 (analysis / 体力)」，「客户影响 (client impact / 落地) vs 智识严谨 (intellectual rigor / 漂亮 deck)」; (b) 方法论正典 (最标准化、最易蒸出高质量) — MECE (相互独立完全穷尽)、issue tree / logic tree (问题树/逻辑树)、hypothesis-driven problem solving (假设驱动)、Pyramid Principle (Minto 金字塔原理: SCQA 情境-冲突-疑问-回答 + 结论先行 + 自上而下 + 归纳/演绎)、80/20 (帕累托/抓大放小)、so-what (所以呢/洞见提炼)、storyline (故事线/ghost deck 鬼影稿)、driver tree / profit tree、2x2 矩阵、value chain、frameworks (Porter 五力/3C/4P/7S/BCG 矩阵/价值链) 既是脚手架也是陷阱 (套框架 vs 真洞见); (c) 行业结构 — MBB (McKinsey/BCG/Bain 战略三巨头) vs Big Four 咨询臂 (Deloitte/PwC Strategy&/EY-Parthenon/KPMG) vs 精品战略所 (Oliver Wyman/Kearney/Roland Berger/L.E.K./Arthur D. Little) vs 专业/职能 boutique (运营/数字化/PE 尽调); up-or-out (非升即走)、leverage model (杠杆模型: 1 个合伙人带多个 EM/咨询师/分析师的金字塔)、partner/principal/EM(项目经理)/associate(咨询师)/analyst(分析师) 职级; (d) 项目交付模型 (the case/study/engagement) — 提案/SOW (scope of work)、problem definition (问题定义/真问题 vs 表象问题)、workplan (工作计划)、hypothesis tree (假设树)、analysis (分析/建模)、synthesis (综合)、recommendation (建议)、implementation (落地); 客户管理 (steering committee 指导委员会、stakeholder 利益相关方、对齐); (e) 产出物 — the deck (PPT 幻灯片是咨询的母语)、executive summary、action title (行动标题/每页一句话结论)、ghost deck (先搭骨架后填数据)、Excel 财务模型、framework 图; (f) 职业/招聘 — case interview 生态 (案例面试: Victor Cheng LOMS/Case in Point/market sizing 市场估算/估算题/fit 行为面)、网申-笔试-案例面、up-or-out、exit options (退出路径: PE/VC/corp dev 企业发展/战略岗/创业/industry); (g) 争议/批判 — 咨询的价值之辩 (「借你的表告诉你时间」「frameworks 是剧场表演 vs 真洞见」Matthew Stewart《The Management Myth》)、McKinsey 的丑闻 (Purdue 阿片类/独裁政府/ICE/利益冲突, Bogdanich & Forsythe《When McKinsey Comes to Town》)、咨询 vs 自建战略部、generalist 通才 vs specialist 专才之争、AI/GenAI 对初级分析师工作的冲击; (h) 流派 — 战略经典 (Porter 定位学派/五力 vs 资源基础观 RBV vs 蓝海战略 Kim&Mauborgne vs 颠覆式创新 Christensen vs Mintzberg 应急战略批判 planning school); 三巨头气质分野 (McKinsey 事实驱动/CEO 信任/通才, BCG 概念/思想领导力/经验曲线/增长-份额矩阵, Bain 结果导向/NPS 净推荐值/PE 关系/与客户深度绑定)。不含: 投行 M&A/财务顾问 (估值/承销超出范畴)、纯 IT 实施/系统集成 (SI 人力外包)、纯审计/税务、纯人力 RPO/猎头、内部战略部 only (虽相关但本 skill 聚焦专业服务咨询的外部视角)。) Master OS — automated mastery of 管理咨询 (Management Consulting) — 战略与管理咨询的职业认知操作系统，从业者/咨询顾问/想入行者/采购咨询服务的客户视角。覆盖: (a) 第一性张力 — 假设驱动 (hypothesis-driven / answer-first / Day-1 answer) 的「先有答案再验证」⇄ 数据驱动 (data-led / bottom-up) 的「先穷尽事实再归纳」，这行的核心张力是「先射箭再画靶 vs 先画靶再射箭」，资深人偏 top-down 假设树减少 boil-the-ocean，但要时刻防 confirmation bias; 以及更深层的张力 — 「卖洞见 (insight / so-what) vs 卖工时 (analysis / 体力)」，「客户影响 (client impact / 落地) vs 智识严谨 (intellectual rigor / 漂亮 deck)」; (b) 方法论正典 (最标准化、最易蒸出高质量) — MECE (相互独立完全穷尽)、issue tree / logic tree (问题树/逻辑树)、hypothesis-driven problem solving (假设驱动)、Pyramid Principle (Minto 金字塔原理: SCQA 情境-冲突-疑问-回答 + 结论先行 + 自上而下 + 归纳/演绎)、80/20 (帕累托/抓大放小)、so-what (所以呢/洞见提炼)、storyline (故事线/ghost deck 鬼影稿)、driver tree / profit tree、2x2 矩阵、value chain、frameworks (Porter 五力/3C/4P/7S/BCG 矩阵/价值链) 既是脚手架也是陷阱 (套框架 vs 真洞见); (c) 行业结构 — MBB (McKinsey/BCG/Bain 战略三巨头) vs Big Four 咨询臂 (Deloitte/PwC Strategy&/EY-Parthenon/KPMG) vs 精品战略所 (Oliver Wyman/Kearney/Roland Berger/L.E.K./Arthur D. Little) vs 专业/职能 boutique (运营/数字化/PE 尽调); up-or-out (非升即走)、leverage model (杠杆模型: 1 个合伙人带多个 EM/咨询师/分析师的金字塔)、partner/principal/EM(项目经理)/associate(咨询师)/analyst(分析师) 职级; (d) 项目交付模型 (the case/study/engagement) — 提案/SOW (scope of work)、problem definition (问题定义/真问题 vs 表象问题)、workplan (工作计划)、hypothesis tree (假设树)、analysis (分析/建模)、synthesis (综合)、recommendation (建议)、implementation (落地); 客户管理 (steering committee 指导委员会、stakeholder 利益相关方、对齐); (e) 产出物 — the deck (PPT 幻灯片是咨询的母语)、executive summary、action title (行动标题/每页一句话结论)、ghost deck (先搭骨架后填数据)、Excel 财务模型、framework 图; (f) 职业/招聘 — case interview 生态 (案例面试: Victor Cheng LOMS/Case in Point/market sizing 市场估算/估算题/fit 行为面)、网申-笔试-案例面、up-or-out、exit options (退出路径: PE/VC/corp dev 企业发展/战略岗/创业/industry); (g) 争议/批判 — 咨询的

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 QA checklists for verifying design implementation accuracy.

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。

Maps topics and keywords from user questions to QwenPaw official documentation paths and common source code entry points, reducing blind searching. Intended for the built-in QA Agent to quickly identify which files to read when answering questions about installation, configuration, skills, MCP, multi-agent, memory, CLI, etc.

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。

将用户问题中的主题、关键词映射到 QwenPaw 官方文档路径与常见源码入口，减少盲目搜索。适用于内置 QA Agent 在回答安装、配置、技能、MCP、多智能体、记忆、CLI 等问题时快速选定要读的文件。

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。

Suede AI MCP release QA, scoped to this pack's own server (mcp/suede-skills-mcp.mjs) and its catalog, install, and docs surface. Runs the full JSON-RPC lifecycle against a live server (initialize, notifications/initialized, ping, tools/list, tools/call, resources/list, resources/read, prompts/list, prompts/get), plus protocol negotiation, closed input and output schemas, tool annotations, structuredContent with text fallbacks, malformed-input probes, clean stdio, catalog-to-folder agreement, and install-path language. Use when the MCP server, mcp/catalog.json, a tool, resource, or prompt definition, or the MCP install docs change, or before publishing an MCP release. A check that did not run against the live server is a FAIL, not a skip. NOT FOR: a generic third-party MCP server, which this skill's hardcoded surface does not describe; fixing or testing the public install path itself (use suede-launch-packaging).

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。

Suede AI full-stack surface builder that runs design, copy, and visual QA as one pass: landing pages, brand surfaces, product UI, dashboards, campaigns, launch pages, and reference-to-target restyles (suedify). Use when a build needs layout and words together, when a redesign or launch surface has to ship end to end, when the request is 'make this site look like that one', or when design, copy, asset, and QA lanes have to move at once. NOT FOR: a design-token, dark-mode, or single-component decision (use suede-design); copy with no layout work (use johnny-suede-write, or suede-copy for one standalone conversion surface); conversion and funnel architecture (use suede-site-alchemy); multi-agent orchestration protocols, WIP protection, and rollback trees (use suede-agent-teams).

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。

Suede-owned launch packaging and install verification. Use when finished software work needs a clean public package (README, docs page, install command, release note, GitHub Pages update, skill-pack release, MCP server, or launch/social copy) or when a release needs handoff notes, an install fails, a public user cannot add a skill, a raw-vs-blob URL returns HTML, or `@personal` or a local plugin alias leaks into public docs. Verifies the live URL and runs the exact install command from a clean temporary directory before anything is called live. NOT FOR: product, course, or artist campaign launches (use suede-campaign-in-a-box or suede-marketing-plan); writing announcement copy from scratch (use suede-copy); MCP tool-catalog QA (use suede-mcp-qa); landing-page conversion work (use suede-site-alchemy).

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 real browser QA with Playwright. Use when testing a frontend feature, verifying UI before PR, smoke testing after deploy, or investigating reported visual bugs.

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。

Coverage-design method for qa-engineer — pyramid ratios per archetype, equivalence/boundary/property case selection, mutation score as the real coverage signal, and a flake-quarantine policy. Turns "coverage is 90%" (a number with no method) into a defensible test plan. Emits TEST-STRATEGY-{slug}.md, which the QA gate checks exists.

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。

Plans mobile QA automation for iOS and Android apps. Use when planning automation frameworks, device matrix, flake control, or CI/CD release gates.

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。

Builds QA harnesses and agent evals. Use when evaluating tool, trace, red-team, regression, multi-agent, or carried-workspace coding trajectories. Not for metric design (ai-evals).

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 day-one patch for a game launch. Scopes, prioritises, implements, and QA-gates a focused patch addressing known issues discovered after gold master but before or immediately after public launch. Treats the patch as a mini-sprint with its own QA gate and rollback 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。

Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when starting a major 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。

Generate automated API and end-to-end tests for implemented features. Use when the user says "create qa automated tests for [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。

Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [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。

Expert guide for autonomous web agents (Browser-Use, Stagehand v0.4+), hardcore anti-bot evasion (Playwright Stealth, WebGL masking), and Vision LLM visual QA / Panduan ahli agen web otonom, penghindaran deteksi bot, dan QA visual berbasis Vision LLM.

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。

Quantum computing framework for building, simulating, optimizing, and executing quantum circuits. Use this skill when working with quantum algorithms, quantum circuit design, quantum simulation (noiseless or noisy), running on quantum hardware (Google, IonQ, AQT, Pasqal), circuit optimization and compilation, noise modeling and characterization, or quantum experiments and benchmarking (VQE, QAOA, QPE, randomized benchmarking).

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。

Browsertrix Crawler is a browser-based crawling system from Webrecorder for high-fidelity site capture, QA replay analysis, and configurable crawl behavior. It runs complex crawls in a single Docker container and uses Puppeteer plus Chrome DevTools Protocol under the hood.

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 Agent QA's CLI and MCP server to author, validate, run, debug, and triage natural-language web and mobile regression tests with persistent test memory and reviewable run 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。

Quality-assure integrated tdmcp features: run the four PR gates + recipe/bridge tests, cross-boundary coherence checks (tool schema↔CLI↔docs↔registry, operator↔createable, bridge↔client), and live TouchDesigner validation (preview + post-cook error check) when the bridge is reachable. Use when validating/QA-ing/testing tdmcp tools, checking a feature actually cooks in TD, verifying CLI matches a tool, or gating a release.

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。

Orchestrates the tdmcp Anthropic Connectors Directory (Desktop Extension / MCPB) submission prep — designs the package, writes the privacy page, migrates .dxt→.mcpb, drafts all form answers, and QAs the result. Use for ANY work on the tdmcp directory/marketplace submission, including re-runs after a rejection ("update the submission", "redo the form answers", "re-migrate the bundle", "fix the privacy page", "the directory rejected us"). Drives a 4-agent pipeline (architect → docs-author ∥ bundle-engineer → 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。

Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy pipeline. Also use for follow-ups: re-run, continue, update, fix, or improve a feature/batch, ship the next version, or rebuild just one part of a previous run. Single feature or a whole batch.

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。

Plan and implement native RayTK (t3kt/raytk) raymarching/SDF toolkit integration into tdmcp — beyond the existing package-manager staging, into AI-driven RayTK operator (ROP) node graphs. Use whenever the user wants to build, plan, design, implement, continue, fix, QA, or ship RayTK support: create/wire RayTK ROPs, a RayTK operator knowledge catalog, a RayTK-native raymarch/SDF scene tool, RayTK recipes, or the RayTK setup/doctor flow — including follow-ups (re-run, continue, refresh after a new RayTK release, re-QA, docs). Also triggers on 'raytk', 'raymarching toolkit', 'SDF toolkit', 't3kt', 'montar um build para o raytk', 'integrar o raytk'. This owns RayTK integration specifically; use it before the generic tdmcp-pipeline for this feature. Simple questions about RayTK can be answered directly.

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。