「edge」の検索結果

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".

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。

Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".

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。

Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation — verdict-bearing at L1 (the LaTeX source; PDF-extracted math is unreliable, so an L0 PDF-only run surfaces info only) — never asserts 'fabricated', only that the step shown does not hold. A fresh cross-model reviewer reads the theorem/proof + an extraction-only obligation scaffold and proposes per-obligation findings, each span-anchored to the evidence ledger (claims.json); reviewer≠adjudicator. Emits proof-derivation-forensics.findings.json; NEVER computes the verdict. dimension=proof, can be critical. Triggers: "proof forensics", "check this proof", "derivation integrity", "audit the math", "证明审计", "推导有没有漏洞".

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。

Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real paper cited for a claim it never makes — or argues against). A hot zone for machine-generated papers. Decidable at L0 (text + canonical sources). Span-anchored to the evidence ledger (claims.json); the executor gathers canonical facts (DBLP / arXiv / DOI), then one FRESH cross-model thread per cited key proposes findings; reviewer != adjudicator. Emits citation-forensics.findings.json; NEVER computes the verdict. Triggers: "citation forensics", "check the references", "hallucinated citations", "wrong-context citation", "verify references", "引用核对".

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。

MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP fuzzy-title + boolean · WebSearch · WebFetch) from the paper's own title + contribution spans in the evidence ledger; TWO fresh cross-model codex reviewers (one per axis) LAY OUT the overlap side-by-side against each anchored contribution claim. It NEVER rules 'trivial' or 'duplicate' (that is a human judgment) and absence of a match is NOT evidence of originality. Emits novelty-duplication-advisory.memo.md + an info-only findings mirror; carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Detect-only. Adapted from ARIS novelty-check, reframed from 'is MY idea novel' to 'here is the overlap a reviewer should weigh'. Triggers: "novelty advisory", "duplication check", "prior-work overlap", "is this stapling", "缝合", "查重", "重复发表", "duplicate submission".

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。

Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every finding span-anchored to the evidence ledger (claims.json), reviewer≠adjudicator. Emits consistency-audit.findings.json; NEVER computes the verdict. Triggers: "consistency audit", "check the paper against itself", "self-consistency", "内部自洽".

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 whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".

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。

Agent Memory Skill workflow skill. Use this skill when the user needs A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions) 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。

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"

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 starter unit tests for a small function or module. Use when a junior developer needs test scaffolding and edge cases.

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。

产品设计 / UX 设计 (产品设计 / UX 设计 (Product Design / UX Design) — 数字产品的用户体验设计：从用户研究 → 信息架构 → 交互设计 → 视觉/UI → 可用性测试 → 设计系统的认知操作系统，面向 UX designer / product designer / interaction designer / UX researcher / design systems engineer / design lead，以及想入行、转岗、服务这行(设计外包、设计工具厂商、研究平台)的视角。覆盖: (a) 第一性张力 — **用户中心/研究驱动 (user-centered, 'you are not the user', research before pixels, observe behavior not opinions) ⇄ 商业目标/约束/交付 (business goals, north-star metrics, ship it, designer 服务于产品成功不是个人作品集)**; **设计直觉/品味/craft (taste, aesthetics, 'attractive things work better' — Norman 情感化设计) ⇄ 数据/实验/A-B 测试 (data-driven, metrics, experimentation, 'opinions are not data')**; **用户说的 (stated preference, 访谈里说喜欢) ⇄ 用户做的 (revealed behavior, 行为观察 > 自陈, usability test 看人真实卡在哪)**; **一致性/设计系统/规范 (consistency, design system, Jakob's law 用户带着别处的习惯来, 复用组件) ⇄ 创新/打破模式 (innovation, 该不该破规范)**; **减法/简化 (simplicity, Krug 'Don't Make Me Think', less but better — Dieter Rams) ⇄ 功能丰富/利益相关者塞需求 (feature creep, stakeholder pressure)**; **UX(体验/流程/研究) ⇄ UI(视觉/像素/组件)** 的职责之争, **designer 该不该写代码 (design engineer / 'should designers code')**; (b) 核心工作流 / pipeline (最标准、最易蒸高质量+CLI 化) — Double Diamond (发现 discover → 定义 define → 开发 develop → 交付 deliver) / Design Thinking (共情 empathize → 定义 → 构思 ideate → 原型 prototype → 测试 test) / Design Sprint (Jake Knapp 5 天冲刺); 完整链: 用户研究 (访谈/问卷/可用性测试/卡片分类) → persona / journey map / JTBD → 信息架构 IA + 用户流 user flow → 线框 wireframe (低保真) → 交互/原型 prototype (高保真) → 视觉 UI / 设计系统落地 → 可用性测试 usability testing → handoff 给开发 → 度量迭代 (北极星 / HEART 框架); (c) 工具栈 — 设计/原型 (Figma 绝对主导 / Sketch 衰退 / Adobe XD 已停更 / Framer 高保真+建站 / Penpot 开源 / Principle / ProtoPie 微交互); 协作白板 (FigJam / Miro / Mural); 用户研究 (Maze / UserTesting / Lookback / Dovetail 研究库 / Optimal Workshop 卡片分类树测试 / Hotjar / Microsoft Clarity 热图); 设计系统/交付 (Storybook / 蓝湖(中) / Zeplin / design tokens / Tokens Studio); 度量 (Amplitude / Mixpanel / 北极星指标); AI 新兴 (Figma AI / v0 by Vercel / Galileo AI / Uizard / Cursor 给 design engineer); (d) 知识正典 — Don Norman《The Design of Everyday Things》(affordance/signifier/mapping 圣经)、Steve Krug《Don't Make Me Think》(可用性入门)、Alan Cooper《About Face》《The Inmates Are Running the Asylum》(交互设计/persona 起源)、Jakob Nielsen 10 Usability Heuristics + NN/g 文章库、Jake Knapp《Sprint》、Jeff Gothelf《Lean UX》、Teresa Torres《Continuous Discovery Habits》、Erika Hall《Just Enough Research》、Julie Zhuo《The Making of a Manager》、《Refactoring UI》(Adam Wathan/Steve Schoger)、《Universal Principles of Design》、Laws of UX (Jon Yablonski)、《100 Things Every Designer Needs to Know About People》(Susan Weinschenk)、IDEO/Stanford d.school 设计思维材料; (e) figures/流派 — 认知心理/人因派 (Don Norman 认知科学奠基、Susan Weinschenk 行为心理、Kathryn Whitenton); 可用性工程派 (Jakob Nielsen 启发式/折扣可用性、Steve Krug、Jared Spool UIE); 交互设计/目标导向派 (Alan Cooper goal-directed/persona、Kim Goodwin); 设计思维派 (IDEO Tim Brown、David Kelley d.school); 精益/持续探索派 (Jeff Gothelf Lean UX、Teresa Torres continuous discovery、Marty Cagan《Inspired》产品发现); 设计系统/系统化派 (Brad Frost Atomic Design、Nathan Curtis design tokens、Alla Kholmatova); 视觉/UI craft 派 (Adam Wathan & Steve Schoger Refactoring UI、Dieter Rams 'less but better' 工业设计遗产); 设计领导/职业派 (Julie Zhuo、Aarron Walter 情感化设计、John Maeda); 移动优先 (Luke Wroblewski 'Mobile First'); (f) 行业话术/黑话 — affordance 可供性 / signifier 意符 / mental model 心智模型 / IA 信息架构 / heuristic evaluation 启发式评估 / usability 可用性 / a11y accessibility 无障碍 / WCAG / persona 用户画像 / journey map 用户旅程 / JTBD jobs-to-be-done / north-star metric 北极星 / HEART 框架 / wireframe 线框 / mockup / prototype 原型 / fidelity 保真度 (lo-fi/hi-fi) / design system 设计系统 / design token 设计令牌 / atomic design 原子设计 / component library 组件库 / handoff 交付 / red routes 关键路径 / dark pattern 暗黑模式 / Fitts's law / Hick's law / Jakob's law / Miller 7±2 / progressive disclosure 渐进披露 / above the fold / hamburger menu / skeuomorphism vs flat / micro-interaction / empty state / edge case / happy path / design debt 设计债 / dogfooding / dot voting / affinity mapping 亲和图 / card sorting 卡片分类 / tree testing / A/B test / NPS / SUS (System Usability Scale); (

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。

加密链上交易 (加密 / 链上交易 (Crypto & On-chain Trading) — 以加密资产为标的、强调链上活动的主动交易认知操作系统：从「看叙事/选赛道 → 找标的 → 链上尽调与风控 → 选场所(DEX/CEX/链上合约) → 建仓与仓位管理 → 监控链上流向与情绪 → 退出与复盘」的完整决策链。覆盖 (a) 第一性张力 — **链上 on-chain (DEX 现货/AMM、钱包追踪 wallet tracking、资金流向 flow、MEV、memecoin、链上衍生品 Hyperliquid/GMX、自托管 self-custody, 'not your keys not your coins') ⇄ 链下 CEX (中心化交易所现货/合约 Binance/OKX/Bybit、订单簿、托管、出入金法币)**; **合约/杠杆/衍生品 (perps 永续、资金费率 funding、清算 liquidation、爆仓、做多做空、高频/择时) ⇄ 现货/价值/长持 (spot、HODL、定投 DCA、基本面/估值、'time in market > timing the market')**; **价值/基本面派 (协议收入、TVL、代币经济学 tokenomics、真实使用、估值模型) ⇄ meme/叙事/情绪派 (memecoin、narrative rotation 叙事轮动、attention is the asset、纯博弈/PvP、Ponzinomics)**; **链上数据/量化/客观 (on-chain analytics, Nansen/Arkham/Dune、聪明钱 smart money、链上指标、系统化/机械化) ⇄ 直觉/盘感/叙事阅读 (narrative、KOL alpha、社群情绪、tape reading)**; **自托管/去中心化/抗审查 (DeFi、自托管钱包、抗审查、'be your own bank') ⇄ 便利/合规/中心化 (CEX、合规出入金、KYC、托管、ETF)**; **主动交易/择时/高换手 (trading、波段、合约、撸毛/空投 airdrop farming、套利 arbitrage) ⇄ 被动配置/低换手 (配置 BTC/ETH、ETF、长期叙事 beta)**; (b) 核心工作流 / pipeline (最标准、最易蒸高质量 + CLI 化) — 通用链: 叙事/赛道判断 (宏观周期/减半/流动性/板块轮动) → 标的发现 (链上扫链/聪明钱跟单/新币/叙事映射) → 尽调 due diligence (代币经济学/解锁 unlock/团队/合约审计/honeypot 检测/流动性与持仓分布) → 风控前置 (仓位 sizing/最大回撤/止损/相关性) → 场所与执行 (CEX vs DEX、滑点/MEV/gas、限价 vs 市价、TWAP) → 持仓监控 (链上流向/巨鲸/资金费率/解锁日历/情绪指标) → 退出与复盘 (止盈分批/再平衡/记录交易日志); 子流派 SOP: 链上 degen 打新与 memecoin 流程、合约交易者的资金费率与清算地图、空投/撸毛 farming、套利与 MEV、被动配置与定投; (c) 工具栈 — 链上分析 (Nansen 聪明钱/Arkham 实体标注/Dune 自建仪表盘/Dexscreener & DEX Screener 新币/GMGN & Photon & BullX memecoin 终端/Etherscan & Solscan 区块浏览器/DeBank 钱包总览/Token Terminal 协议基本面/DefiLlama TVL/Glassnode & CryptoQuant 链上指标)、交易场所 (CEX: Binance/OKX/Bybit/Coinbase; 链上现货 DEX: Uniswap/Jupiter/Raydium/Aerodrome; 链上衍生品: Hyperliquid/GMX/dYdX)、钱包与安全 (MetaMask/Rabby/Phantom 热钱包、Ledger/Trezor 硬件冷钱包、Revoke.cash 授权管理、honeypot/合约扫描)、行情与图表 (TradingView、CoinGecko/CoinMarketCap)、信息与聚合 (Twitter/X、Telegram、DeFiLlama、RootData/ICO 日历、解锁日历 Token Unlocks)、自动化 (交易机器人、链上 bot/sniper、Telegram trading bot); (d) 知识正典 — 注意加密交易 canon 偏少且新: 通用交易/风控经典 (Edwin Lefèvre 'Reminiscences of a Stock Operator'、Van Tharp 'Trade Your Way to Financial Freedom' 仓位管理、Mark Douglas 'Trading in the Zone' 交易心理、Michael Mauboussin、Nassim Taleb 'Fooled by Randomness/Antifragile')、加密原生 (Bitcoin whitepaper 中本聪、'The Bitcoin Standard' Saifedean、Vitalik 博客与 Ethereum whitepaper、'DeFi and the Future of Finance'、Lyn Alden 宏观、a16z crypto 文章、Messari/Delphi/Bankless 研报)、链上分析方法 (Glassnode/CryptoQuant 教程、Nansen/Arkham/Dune 文档、Dune Analytics SQL)、交易方法论散见于 podcast/Substack/Twitter thread 而非书; (e) figures/流派 — 价值/基本面派 (Vitalik Buterin 以太坊、Hasu/Su Zhu(争议)、Arthur Hayes BitMEX 创始人/宏观+衍生品、Raoul Pal、Lyn Alden 宏观、Cobie/Jordan Fish UpOnly podcast、DeFi 研究 Bankless Ryan Adams/David Hoffman); 链上分析派 (Nansen Alex Svanevik、Arkham、Adam Cochran、Ansem(blknoiz06) 链上交易、Murad memecoin supercycle、链上侦探 ZachXBT 反诈); 合约/衍生品派 (Arthur Hayes、GCR(GiganticRebirth) 传奇合约、Pentoshi、CryptoCred 技术分析、Tyler Durden); meme/叙事派 (Ansem、Murad、Cobie、各 Solana memecoin KOL); 宏观/周期派 (Raoul Pal、Lyn Alden、PlanB stock-to-flow(争议)、Benjamin Cowen 数据/周期); 量化/系统化 (各匿名量化、Hyperliquid 生态); 中文圈 (链上分析/合约 KOL、币圈大 V、播客如 '无人之境'/'Web3 佛学院'、研究机构如 Foresight/PANews/律动 BlockBeats); 反诈/安全 (ZachXBT、SlowMist 慢雾、go+ 安全); (f) 行业话术/黑话 — 现货 spot / 合约 perps 永续 / 杠杆 leverage / 多空 long-short / 爆仓 liquidation 清算 / 资金费率 funding rate / 开多开空 / 止损 SL 止盈 TP / 仓位 position sizing / 满仓梭哈 ape in / 梭 / FOMO / FUD / 钻石手 diamond hands / 纸手 paper hands / 韭菜 / 镰刀 / 庄 / 出货 / 拉盘砸盘 / 插针 wick / 针 / 上车下车 / 埋伏 / 潜伏 / 链上 on-chain / 钱包 wallet / 地址 / 聪明钱 smart money / 巨鲸 whale / 跟单 copy-trade / 老鼠仓 / 貔貅盘 honeypot / 貔貅 / rug 跑路 rug-pull / 归零 / 土狗 (memecoin/小币) / 金狗 (暴涨百倍) / meme 币 / 叙事 narrative / 赛道 / 板块轮动 / 撸毛 撸空投 airdrop / 女巫 sybil / 交互 / 解锁 unlock / 砸盘解锁 / 代币经济学 tomomics / TVL / APY APR / 无常损失 IL / 滑点 slippage / MEV / 三明治 sandwich / gas / 抢跑 frontrun / 貔貅检测 / 授权 approve / 撤销授权 revoke / 私钥 助记词 seed phrase / 冷钱包 热钱包 / 自托管 / 减半 halving / 牛熊 / 山寨季 altseason / 比特币市占率 BTC.D / 山寨 alt / 主流币 / DeFi 暑期 / GM / WAGMI / NGMI / 归零归零 / PvP / Ponzi 庞氏; (g) 争议/批

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。

临床诊断思维 (临床诊断思维 / 临床推理 (Clinical Diagnostic Reasoning) — 医生『怎么想病』的元学科:从症状/体征/检查到诊断结论的认知操作系统,从业者(临床医生/住院医/规培生,尤其全科/急诊/大内科等以未分化主诉为生的科室)、医学生与医学教育者、诊断安全与质量改进研究者、以及做医疗 AI 辅助诊断产品的人的视角。覆盖: (a) 第一性张力 — **直觉模式识别 (System 1: illness scripts 疾病脚本 / pattern recognition / gestalt, 『资深人一眼认出 aunt Minnie』) ⇄ 分析性推理 (System 2: hypothetico-deductive 假设演绎 / Bayesian 概率更新)** 的 dual-process 双过程理论 (Kahneman→Croskerry/Norman 谱系), 资深≠更会分析而是『脚本库更大+校准更好』; 更深层论战 — **『认知去偏可教 (Croskerry: bias awareness / cognitive forcing strategies / diagnostic timeout) ⇄ 偏倚标签是马后炮、知识结构才是主因 (Norman/Sherbino/Monteiro: debiasing 干预 transfer 证据弱, bias 是 hindsight 标签)』** — 本行最核心学术对垒; 『概率思维 (验前概率 × 似然比 → 验后概率, Pauker-Kassirer test/treatment threshold 阈值模型) ⇄ 穷尽式排查 (rule-out everything / 防御性医疗 / VOMIT)』; 『临床 gestalt ⇄ 结构化临床决策规则 (Wells/PERC/HEART)』; 『诊断简约 Occam's razor ⇄ Hickam's dictum (病人可以同时得 N 个病)』; 『床旁体格检查复兴 (Verghese Stanford 25 / McGee 循证体检) ⇄ 影像检验替代床旁』; (b) 方法论正典 — illness script theory (Schmidt/Boshuizen: enabling conditions/fault/consequences 三段结构), problem representation + semantic qualifiers 问题表征与语义限定词 (Bowen NEJM 2006, 把病人翻成 one-liner), hypothetico-deductive model (Elstein 1978《Medical Problem Solving》: 早期假设生成+定向检验), Bayesian 工具箱 (sensitivity/specificity/LR/Fagan nomogram/SnNout-SpPin), threshold model (Pauker-Kassirer NEJM 1975/1980), 认知偏倚分类学 (anchoring/premature closure/availability/confirmation/base-rate neglect/search satisficing/diagnostic momentum — Croskerry 偏倚清单), 去偏与元认知策略 (diagnostic timeout/cognitive forcing/Ely checklist/calibration), schema-based reasoning (Clinical Problem Solvers schemas: 按 pivot 症状走分支), reflective practice 结构化反思 (Mamede/Schmidt), 诊断错误科学 (NAM 2015 报告定义 / Newman-Toker Big Three / Hardeep Singh e-triggers / SAFER Dx 框架); (c) 行业结构与角色 — 医学生→实习/住院医 (晨会 morning report/查房被 pimping/汇报训练)→主治 attending→master clinician (NEJM CPC discussant/晨会大师如 Dhaliwal); 配套生态: 医学教育者 (clinical reasoning curriculum + 评估: script concordance test/key features exam/OSCE), 诊断安全研究者 (SIDM/AHRQ), 诊断辅助与 CDS 工具开发者 (DDx generator/AI); (d) 核心工作流 — 数据采集 (病史为王 + 循证体检 + 针对性检验影像) → 问题表征 (one-liner + semantic qualifiers) → 鉴别诊断生成 (schema / 解剖定位法 / VINDICATE-M 病因筛, 按『常见可能 × 致命不能漏 can't-miss』双轴排序) → 假设定向检验 (按 LR 选检查 / 阈值决策) → working diagnosis + 安全网 (red flags 交代 / test of time / test of treatment) → 反馈校准 (follow-up / M&M / diagnostic timeout); 教学工作流: 晨会渐进披露汇报 / CPC / SNAPPS / one-minute preceptor / virtual morning report; AI 增强工作流 (2023-2026: LLM 鉴别诊断头脑风暴 / OpenEvidence 检索 / ambient scribe 释放认知带宽 + 自动化偏倚 guardrails); (e) 产出物 — one-liner, problem list, prioritized DDx, assessment & plan (按问题分层), 晨会/CPC 汇报, M&M 复盘, 诊断不确定性沟通 (『最可能是 X, 但出现 Y 红旗立刻回来』); (f) 教育与评估 — script concordance test / key feature exam / EPA / 里程碑; 中国语境: 人卫《诊断学》教材 / 执业医师考试 / 规培结业临床思维考核; (g) 争议/批判 — debiasing 之争 (Croskerry vs Norman-Sherbino『knowledge is the cure』, 去偏 RCT 效果弱 / bias 标签不可证伪), 诊断错误率数字之争 (『10-15%』经典估计 / Newman-Toker 79.5 万美国年严重伤害外推方法被质疑 / 尸检符合率), dual-process 二分被批过度简化 (连续谱 / 难以实证分离), 决策规则 vs gestalt (资深 gestalt 常不输 Wells 类规则 / 算法厌恶), vignette 研究外推性 + context/case specificity (推理高度内容绑定不可通用迁移 [Norman/Eva] — 对『教推理通用课』产业的根本批判), AI 辅助诊断 2023-2026 (GPT-4 在 NEJM CPC/vignette 追平或超医生 [Kanjee 2023 JAMA / Goh 2024 JAMA Netw Open『AI alone > physician+AI』悖论] / Google AMIE / OpenEvidence 爆发 vs 自动化偏倚 / 去技能化 / 真实环境验证缺失), 防御性医疗与过度检查 (incidentaloma 瀑布 / VOMIT), 体检衰亡之争, pimping 教学法争议; (h) 流派/思想谱系 — 决策科学/Bayesian 派 (Ledley-Lusted 1959 → Elstein/Kassirer/Sox/Pauker/Eddy → Brush) vs 认知心理/双过程派 (Kahneman-Tversky → Croskerry/Graber) vs 教育认知派 (Schmidt/Boshuizen illness scripts → Norman/Eva/Mamede/Durning 情境认知) vs 诊断安全/系统派 (NAM 2015 / Newman-Toker / Hardeep Singh / Graber-SIDM: 错误=系统×认知共因) vs 床旁临床派 (Osler 传统 → Tierney aphorisms / Verghese / McGee / Dhaliwal / Saint: 病史体检为王 + 刻意练习) vs AI/计算派 (INTERNIST-1/DXplain 专家系统 → Isabel → LLM 世代 Rodman/Topol)。不含: 具体专科治疗方案与手术决策深度 (足踝外科/种植牙等另有 skill), 中医辨证 (另有 skill), EBM 文献批判性评价方法学 (相关但本 skill 聚焦诊断推理本身), 护理诊断体系 (NANDA), 影像/病理知觉型读片训练 (相邻但独立), 精神科 DSM 结构化访谈细节, 医患沟通技巧全集 (只覆盖诊断不确定性沟通), 患者自查/自我诊断指

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。

Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a headless fan-out from one background command. Use for "fan this out to 50 agents", "run these tasks in parallel", "launch subagents for each file", "should I spawn agents or write a workflow", "batch this through Haiku", "run claude -p in parallel", "dispatch a task list without the launches eating my context", or before any launch of more than a handful of subagents, where the launching itself is the cost. Covers the parent-turn cost of each mechanism, concurrency ceilings, what context and tools each child gets, effort control, output contracts, a cost ledger, and resume after interruption.

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。

Multi-conversation methodology for iterative stateful work with context accumulation. Use when users request work that spans multiple sessions (research, debugging, refactoring, feature development), need to build on past progress, explicitly mention iterative work, work logs, project knowledge, or cross-conversation learning.

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-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of hand-annotating bboxes.

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。

Ranked content search over a text corpus you point it at, using BM25 (via xhluca/bm25s). Corpus-agnostic: cloned repos, project knowledge stores, uploaded files and archives, any local directory. In-memory BM25 index per invocation, with a session-local disk cache for repeat runs against the same corpus. Use for "rank these documents", "search this corpus", "which files are most about X", "find content about Y", or any multi-word concept query against a known body of text where grep would return everything or nothing. Needs a corpus on disk. Not for searching stored memories or prior-session decisions (remembering), not for a named symbol or a file's structure (tree-sitting), and not for a literal string you could grep.

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 semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

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 Chinese HBG “模拟人生 / 人生副本” narrative videos with a consistent comic IP, a rapid multi-life opening, continuous natural-speed narration, synchronized short captions, dense static manga storyboards, audible fixed-level BGM, alternating zoom/pan motion in HyperFrames, and a consent-gated localhost-only account-backed Images API through CLIProxyAPI as the preferred image channel. Use for 模拟人生、人生副本、统一主角漫画、快闪职业开头、旁白配图、静态漫画分镜、zoom 推拉、左右平移、Edge TTS、字幕压制、本地反代自己的 Codex 账号、CLIProxyAPI，或把长篇中文人生故事组装成视频。

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。

Odoo 19 development knowledge base with 18 specialized guides covering Actions (ir.actions.*, cron jobs, server actions), Controllers (HTTP routing, endpoints, auth types), Data files (XML/CSV records, shortcuts, noupdate), API Decorators (@api.depends, @api.constrains, @api.ondelete, @api.onchange, @api.model, @api.private), SQL Constraints (models.Constraint replacing _sql_constraints), Database Indexes (models.Index), Module development (manifest, wizards, reports), Field types (Char, Text, Monetary, relational fields), Manifest configuration (__manifest__.py, dependencies, asset bundles), Mixins (mail.thread, mail.activity.mixin, mail.alias.mixin, utm.mixin), ORM Model methods (search, CRUD, domain filters, recordsets, CamelCase model naming), Migration scripts (pre/post/end hooks, data migration), OWL frontend components (hooks, services, lifecycle), Performance optimization (N+1 prevention, batch ops, _read_group), QWeb Reports (PDF/HTML, paper formats, barcodes, t-out), Security/ACL (record rules, field permissions, privilege-based groups, @api.private), Testing (TransactionCase, HttpCase, mocking, query count assertions), Transactions (savepoints, UniqueViolation, serialization failures), Translations (i18n, PO files, translatable fields), XML Views (list/form/search, kanban card templates, xpath inheritance, QWeb templates). Use when writing, reviewing, or debugging any Odoo 19 Python or XML code, creating or modifying modules, fixing performance issues, or looking up Odoo 19 API patterns and best practices. Includes CSS/SCSS asset authoring and review for Odoo addons.

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。

Route HugeGraph MCP graph data extraction and controlled import/delete tasks to stable public tools. Use when the user asks to extract graph data from text, import structured vertices or edges, verify an import, or asks whether table, SQL, update, or delete graph writes are available.

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。

Route HugeGraph MCP schema design, validation, and dry-run preview tasks to stable public tools. Use when the user asks to design vertex labels, edge labels, properties, primary keys, indexes, or preview schema operations.

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。

FLOW framework integration — evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO 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。

When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," "breadcrumb schema," "Google rich results," "knowledge panel," "star ratings in search," or "add structured data." Use this whenever someone wants their pages to show enhanced results in Google. For broader SEO issues, see seo-audit. For AI search optimization, see ai-seo.

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。