「model quality」の検索結果

Advanced Evaluation workflow skill. Use this skill when the user needs This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

投行并购 (投行并购 / 交易撮合 (Investment Banking M&A / Dealmaking) — 面向并购顾问、企业融资、卖方/买方交易执行的职业认知操作系统，从业者(分析师 Analyst / 经理 Associate / 副总裁 VP / 董事 Director / 董事总经理 MD / 内部公司发展 Corp Dev / PE 投资人)、想入行者、以及服务这行(法律/会计/估值/咨询)的视角。覆盖: (a) 第一性张力 — 投行 M&A 的核心世界观分歧: **价格 vs 价值 (price 是市场愿意付的, value 是内在的, deal 在两者缝隙里成交) ⇄ 确定性 vs 最高价 (certainty of close 对卖方常胜过纸面最高报价) ⇄ 顾问/中介 vs 委托代理 (banker 是 agent, 客户利益 vs 成交费的激励冲突真实存在, 「banker 总想成交」是行业原罪批判)**; 更深层 — 「过程/竞价纪律 (controlled auction 制造竞争张力、信息不对称管理) ⇄ 关系/信任 (relationship banking、长期 coverage、reputational capital)」, 「叙事/包装 (the story, equity story, positioning) ⇄ 数字/尽调 (the numbers, diligence, quality of earnings)」, 「估值的科学外衣 (DCF/comps 的伪精确) ⇄ 谈判的真实定价 (价格由 leverage、竞争、时机决定)」; (b) 估值与分析正典 (最标准化、最易蒸出高质量+CLI 化) — DCF (折现现金流: FCF 预测/WACC 折现率/terminal value 终值/Gordon growth vs exit multiple), Comparable Companies (可比公司/trading comps: EV/EBITDA, EV/Revenue, P/E), Precedent Transactions (先例交易/deal comps: control premium 控制权溢价), LBO (杠杆收购模型: IRR/MOIC/debt schedule/sources & uses), Accretion/Dilution (增厚/摊薄分析: EPS 影响、pro forma), Sum-of-the-Parts (分部估值/SOTP), Football Field (估值区间图), Merger Model (合并模型: synergies 协同/purchase accounting/goodwill), Sensitivity/scenario; (c) 交易流程与产出物 — 卖方流程 (sell-side: teaser 简介 → NDA → CIM/IM 信息备忘录 → management presentation → IOI 意向函 → data room 数据室 → LOI/term sheet → confirmatory diligence → SPA 买卖协议 → signing → closing), 买方流程 (buy-side: thesis/sourcing → outreach → valuation → bid → exclusivity → diligence → financing → close), auction 类型 (broad/targeted/negotiated/preemptive bid); 产出物: pitchbook 推介材料、CIM、fairness opinion 公平意见、board presentation、fee letter、engagement letter; (d) 交易结构与条款 — consideration (cash/stock/mix/earnout 对赌)、deal protections (breakup fee 分手费/go-shop/no-shop/MAC 重大不利变化条款)、representations & warranties 陈述与保证、escrow 托管、working capital adjustment 营运资金调整、reverse termination fee、collar 价格区间、tender offer vs merger、hostile vs friendly、defensive tactics (poison pill 毒丸/white knight 白衣骑士/staggered board); (e) 行业结构与角色 — bulge bracket (高盛/摩根士丹利/JPM/BofA/花旗) vs elite boutique (Centerview/Evercore/Moelis/Lazard/PJT/Perella) vs middle market (Houlihan Lokey/William Blair/Harris Williams) vs regional/independent; analyst→associate→VP→director→MD 晋升金字塔; coverage (行业组) vs product (M&A/ECM/DCM/leveraged finance/restructuring); sponsors group (服务 PE); 买方包括 PE/strategic acquirer/corp dev; (f) 量化指标与节奏 — deal fee (success fee 业内通常约 1-2% 视规模递减/retainer/Lehman formula)、league table 排行榜、pitch→mandate 转化、deal velocity、hours culture (analyst 80-100h/week 文化批判)、bonus/comp 结构、deal sheet (简历上的成交清单); (g) 争议/批判 — fairness opinion 是否橡皮图章 (利益冲突: 出意见的 banker 也收成交费)、estimate 的伪精确 (DCF garbage in garbage out、假设驱动结论)、banker 永远建议成交 (deal 偏见、empire building 助推 CEO 自利并购)、协同效应系统性高估 (大量并购毁灭价值、winner's curse 赢家诅咒)、analyst 血汗工厂文化 (2021 高盛 13 人 deck 事件、过劳死争议)、advisory 价值 vs 中介寻租之争、bulge vs boutique 的利益独立性叙事 (boutique 标榜「无承销利益冲突」)、SPAC 泡沫与 de-SPAC 教训; (h) 流派/思想谱系 — 估值学派 (Aswath Damodaran 估值教父/纽大、Tim Koller McKinsey《Valuation》、McKinsey valuation 体系) vs 公司金融教科书派 (Rosenbaum & Pearl《Investment Banking》行业圣经、Brealey Myers Allen、CFI/WSP/BIWS 培训体系) vs 交易实战派 (Bruce Wasserstein《Big Deal》、Joseph Perella/Felix Rohatyn 老派 dealmaker、现代 boutique 创始人) vs 行为/批判派 (并购毁灭价值的学术证据、Damodaran 对协同/控制权溢价的批判、Matt Levine《Money Stuff》解构华尔街逻辑) vs PE/buy-side 视角 (LBO 数学、value creation 杠杆/运营/multiple expansion)。不含: 二级市场股票交易/卖方研究 (equity research)、零售财富管理/private banking、纯 ECM/IPO 承销执行 (虽相关但聚焦 M&A advisory)、纯 PE 投后运营、量化交易/对冲基金策略、纯公司财务报表会计。) Master OS — automated mastery of 投行并购 / 交易撮合 (Investment Banking M&A / Dealmaking) — 面向并购顾问、企业融资、卖方/买方交易执行的职业认知操作系统，从业者(分析师 Analyst / 经理 Associate / 副总裁 VP / 董事 Director / 董事总经理 MD / 内部公司发展 Corp Dev / PE 投资人)、想入行者、以及服务这行(法律/会计/估值/咨询)的视角。覆盖: (a) 第一性张力 — 投行 M&A 的核心世界观分歧: **价格 vs 价值 (price 是市场愿意付的, value 是内在的, deal 在两者缝隙里成交) ⇄ 确定性 vs 最高价 (certainty of close 对卖方常胜过纸面最高报价) ⇄ 顾问/中介 vs 委托代理 (banker 是 agent, 客户利益 vs 成交费的激励冲突真实存在, 「banker 总想成交」是行业原罪批判)**; 更深层 — 「过程/竞价纪律 (controlled auction 制造竞争张力、信息不对称管理) ⇄ 关系/信任 (rela

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。

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

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 writing tests for data or ML code — what to test at each layer (transforms, schemas, properties, pipeline smoke, model-quality thresholds, determinism and parity), how to build small synthetic fixtures, and what not to test

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。

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

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 analytics engineering layers for metrics, contracts, and BI-ready models. Use when shaping dbt or SQLMesh marts, metric governance, lineage, or data 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。

Switch model profile for GSD agents (quality/balanced/budget/inherit)

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。

Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a stripped or prior version, quality against a rubric, and trigger accuracy of the description with an optional optimization loop. Use when the user asks to evaluate, benchmark, test the triggers of, grade, or compare versions of a skill, or when the bmad-toolsmith skill asks for an eval of a skill it built.

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。

End-to-end production workflow guidance for Blender — the order to assemble scenes (block-out → camera → light → forms → materials → detail → render → composite → export), critique protocols, time budgets, and recovery patterns. Use whenever the user asks to "make a complete scene / hero shot / production-quality render", "what's the right order to do this", "set up a full pipeline", or has a multi-step request crossing modeling + lighting + materials + rendering. Make sure to use this skill for any request that spans multiple phases of 3D work, even if the user does not say "workflow" — also covers "make a final image of X", "produce a hero render", "professional-looking result".

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-driven image generation and editing tool for creating high-quality product images. Triggered when users ask to generate images, create product pictures, edit photos, text-to-image, image-to-image, replace backgrounds, transform styles, composite products into scenes, swap models, or create any type of AI-generated visual content. Even if the user does not explicitly say "AI image," this skill should be triggered whenever the request involves creating, modifying, or transforming images.

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。

Analyze and improve processes or systems using an explicit semantic model, adaptive instruction resolution, evidence-driven change, and claim-level validation. Use when reviewing process quality, resolving ambiguity or gaps, deciding how much procedural detail is necessary, or validating consequential process behavior.

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。

Analysis criteria, transformation patterns, output format, and validation checklist for refactoring Claude Code agent prompt files. Load this skill when preparing to run the subagent-refactorer agent or when reviewing agent prompt files for structural, model optimization, or instruction quality improvements.

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。

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

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 ElevenLabs conversational AI agents for real estate applications. Use when creating new agents, improving conversation quality, selecting voices, engineering system prompts, configuring agent parameters, or analyzing agent performance metrics. Includes voice selection, model tuning, prompt engineering, and A/B testing strategies.

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 sales operations and analytics guidance for revenue teams. Use when designing CRM workflows, building sales dashboards, optimizing pipeline analytics, creating lead routing rules, designing territories, calculating commissions, managing data quality, building forecasting models, or integrating sales tech stack. Covers Salesforce, HubSpot, Outreach, Gong, and RevOps best practices.

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。

Automatically optimize AI agent credit usage by routing tasks to the most cost-efficient execution path. Use when you want to reduce AI API costs by 30-75% without quality loss, classify task complexity before execution, route simple tasks to free or low-cost models, split complex tasks into optimized sub-tasks, or detect vague prompts before wasting credits.

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 working on or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).

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 working on imp's quantization formats, loaders, or dequant paths - GGUF Q4_0...Q8_0/Q*_K/IQ4/MXFP4, NVFP4 two-level scaling (Modelopt vs compressed-tensors layouts), FP8 E4M3, StorageTier, decode cache, KV-cache dtypes (auto/fp16/fp8/int8/int4/nvfp4/mxfp4), "which quant should I use", "which KV dtype", scale-factor layout, dequant kernel wiring, imp-quantize / AWQ, judging quant quality (PPL). Do NOT use for writing/optimizing GEMM/GEMV kernels (sm120-cuda-expert) or measuring quant perf (benchmark-cuda).

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。

Deconstructs customer cohort behavior with retention curves, LTV progression, and vintage-over-vintage comparison analysis. Use when analyzing cohort data, assessing customer quality, or modeling lifetime value trajectories.

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 complete, optimized Claude prompts and Project scaffolds from task descriptions. Use when building, designing, creating, or structuring a Claude prompt or system prompt. Trigger on: "build me a prompt," "compile a prompt for," "create a system prompt," "write a Claude prompt," "design a prompt for," "help me write a prompt," "scaffold a Claude Project," "design a Project for." Uses a four-stage methodology (Parse, Select, Construct, Validate) and a tested 5-layer architecture (Identity, Objective, Context, Reasoning, Output + Quality Control). In Project Mode, the Compiler is global-layer-aware — checks User Preferences, installed Skills, and MCP Connectors to avoid redundancy and flag gaps. Do NOT use for auditing existing prompts (use rootnode-prompt-validation if available) or diagnosing existing Projects (use rootnode-project-audit if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.

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。

Director-level AI art prompt creation for Eastern beauty series, including Eastern fantasy / gu feng Chinese beauty character art, classical Eastern beauty, realistic and modern Eastern beauty, Cosplay展会摄影 / official convention cosplay photography with AAA game character campaign and Vogue editorial quality, 古风闺蜜 / AncientFemaleCompanionship two-person ancient Chinese female companionship photography, 东方美学图鉴 / 小红书图鉴 cover and content systems for 四大美人、四大才女、十二花神、东方神女、敦煌飞天、朝代服饰、东方器物、东方神话, 甜系纯欲生活写真 / SweetHomeGirl lifestyle portraits built around realism, feminine charm, romantic feeling, story moment, and natural attraction, new-Chinese-style fashion editorials, magazine portraits, worldbuilding, mythic role design, costume/styling systems, cinematic composition, lighting, negative prompts, and model-specific prompt variants. Use when the user asks for 东方美人, 东方审美, 东方美学图鉴, 小红书图鉴, 图鉴封面, 图鉴正文, 四大美人, 四大才女, 十二花神, 东方神女, 敦煌飞天, 朝代服饰, 东方器物, 东方神话, Cosplay展会摄影, coser, Coser, 漫展摄影, 展会摄影, ChinaJoy, Bilibili World, Tokyo Game Show, 游戏展台, 官方展会摄影, AAA游戏角色Cosplay, 古风闺蜜, AncientFemaleCompanionship, Ancient Female Companionship, 闺阁夜话, 姐妹古风写真, 古代闺阁生活, 灯下梳发, 共读, 夏夜纳凉, 守夜, 江南同行, 湖亭共伞, 山寺同行, 灯会夜游, 柔美, 妩媚, 成熟, 优雅, 高贵, 清冷, 温婉, 英气, 神性, 慵懒, 东方幻想, 古风美女, 古典东方美人, 宋韵, 唐宫, 江南, 洛神, 青瓷, 昆曲, 国风人物, 汉服女子, 写实东方美人, 现代东方审美, 新中式, 东方高级感, SweetHomeGirl, 甜系纯欲生活写真, 甜系纯欲, 甜美女友感, 真实女生, 自然抓拍, 故事感, 女友视角, lifestyle girlfriend portrait, 仙侠/武侠/宫廷/江南/敦煌风 AI 绘画提示词, image prompt optimization, style word expansion, character series concepts, or prompt packs for Midjourney, Stable Diffusion, ComfyUI, DALL-E, Gemini, Seedream, or other image generation tools.

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。

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible 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。

TypeScript and JavaScript performance and code-quality rules, usable in any framework. Use when writing, reviewing, or refactoring hot paths, data-structure choices, async flows, or bundle-size-sensitive code. Triggers include "optimize this function", "too slow", "reduce allocations", "bundle size", "lazy load", "speed up imports", or general code review of utilities and services.

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 you need to know where a piece of reporting actually came from — the user gives an article URL and asks "where does this come from?", "who is the original source?", "is this just a rewrite?", or another skill needs the provenance chain before grading or citing a report. Follows an article's links and named attributions back to the originating vendor, government, victim or actor document and returns the chain, the primary's stated access and confidence language, publication dates, and every hop it could not resolve. Deterministic — a script or the Liberty91 platform resolves the chain; the model does not reconstruct it from memory. Invoked by /quality-of-information-check, /threat-actor-profiling, /campaign-tracking and /intelligence-writing. Works on any URL with no API key.

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。