「sem」の検索結果

Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe paper".

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。

John Gottman (Gottman Institute) 视角. 循证婚姻研究派代表. Four Horsemen + 5:1 Magic Ratio + Cascade Model. 调用此 skill 时, 用 Gottman 框架做关系健康度判断.

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。

影视编剧 (Scriptwriting / Screenwriting) — 为电影 / 电视 / 流媒体剧集写戏剧蓝本的从业者认知操作系统: 决定「讲什么故事、人物是谁为何转变、场景如何被戏剧化、主题为何重要」的学科 —— 区别于导演 (调度 / 视觉实现)、制片 (融资 / 排期)、小说 (无格式 / 场景 / 视觉动作约束)。覆盖 (a) 故事与结构理论 (亚里士多德《诗学》情节 / 人物 / 思想 + 突转 peripeteia / 发现 anagnorisis + 净化 catharsis; Syd Field 范式 / 三幕 / 情节点; Freytag 金字塔; Egri 前提; McKee《故事》掌控性理念 / 鸿沟 / 价值正负转变 / 激励事件 / 渐进式复杂化; Truby《故事剖析》22 步 + 道德论证; Vogler/Campbell 英雄之旅; Blake Snyder《救猫咪》15 拍节拍表; Dan Harmon 故事环; John Yorke 五幕《进入森林》; Frank Daniel 八序列法; 起承转合东亚戏剧结构), (b) 人物 (想要 vs 需要 / 外在目标 vs 内在缺失, 人物弧光 正 / 负 / 平, flaw-wound-ghost 创伤背景, 主动 vs 被动主角的能动性, Egri 三维人物 生理 / 社会 / 心理, 反派是主角的镜子, 群像与关系网, 人物在压力下的选择中显形), (c) 对白 (潜台词 subtext, 对白即动作与冲突而非信息, 避免太直白 on the nose, 人物独特声口, 信息植入 exposition, Mamet/Sorkin 意图-阻碍式对白, 展示而非告知, 中文剧台词工艺), (d) 场景与序列工艺 (场景是有目标 / 冲突 / 转折的微型故事, 场景价值充能与转折点, 晚进早出, 八序列法, set piece, 转场, 场景头 / 动作行 / 括号提示 格式工艺), (e) 主题与前提 (掌控性理念 / 前提, 主题是被戏剧化的论证而非说教, 道德论证 Truby, 主题统一性, 这到底在讲什么), (f) 类型 (类型惯例是对观众的承诺, Snyder 10 类故事, 颠覆 vs 尊重套路, 类型片 vs 文艺片, 中国类型 主旋律 / 古装 / 年代 / 悬疑 / 甜宠 / 都市 / 军旅 / 历史正剧), (g) 格式与工业流程 (好莱坞剧本格式与 Final Draft, logline 一句话故事, treatment 故事大纲, 节拍表, 分场 / 分集大纲, spec 原创剧本 vs 委托, pitch, coverage, 美剧编剧室与 showrunner 制; 中国 大纲→人物小传→分集大纲→剧本, 长剧集 40 集结构, 网络电影 / 网大, 分账剧, 平台定制剧, 微短剧竖屏短剧), (h) 改稿与开发 (写作就是改写, 改稿 / 润色 / 推倒重写, 处理意见 / 改稿意见, 片方与平台 notes, 杀死你的宝贝, 围读, 开发地狱), (i) 改编 (IP改编 小说 / 漫画 / 游戏改编, 忠于精神而非字句, 压缩, 中国网文 IP 热), (j) 中国影视编剧产业现实 (审查 / 广电总局约束, 备案 / 立项, 平台定制剧 爱优腾芒, 分账, 编剧维权 署名权 / 欠薪 / 枪手, 注水剧, 流量 + 大IP 资本逻辑 vs 原创工艺, 导演中心制 vs 编剧话语权), (k) 编剧职业与工艺生涯 (spec vs 委托, 编剧 vs 编审 / 策划, 单兵 vs 编剧室, 在开发链条中的位置, WGA 与署名仲裁规范, 入行, 中国编剧地位与权益)。跨 电影 / 美剧流媒体 / 中国电影与长剧集。不含 导演 / 摄影 / 制片 / 融资 / 表演 / 电影理论批评为终点 / 泛小说写作 / 纪录片 / 新闻 —— 本 skill 是「戏剧化编剧」工艺: 故事 / 人物 / 场景 / 对白 / 主题 / 结构 / 格式 与围绕它们的产业流程。 (Scriptwriting / Screenwriting for film & TV (影视编剧) — the cognitive operating system of practitioners who write the dramatic blueprint of films, television, and streaming series: the discipline of deciding WHAT story is told, WHO the characters are and why they change, HOW the scenes are dramatized, and WHY it matters thematically — distinct from directing (staging/visual realization), producing (financing/scheduling), and prose fiction (which has no format/scene/visual-action constraints). Covers (a) story & structure theory (Aristotle's Poetics — plot/character/thought + reversal peripeteia/recognition anagnorisis + catharsis; Syd Field's paradigm/three-act/plot points; Freytag's pyramid; Lajos Egri's premise; Robert McKee's Story — controlling idea/the gap/value charge/inciting incident/progressive complications; John Truby's 22 steps & moral argument; Christopher Vogler/Joseph Campbell hero's journey; Blake Snyder's Save the Cat 15-beat sheet; Dan Harmon's story circle; John Yorke's 5-act Into the Woods; Frank Daniel's 8-sequence method; 起承转合 East-Asian dramatic structure), (b) character (want vs need/external goal vs internal lack, character arc positive/negative/flat, 人物弧光, flaw-wound-ghost backstory, agency active vs passive protagonist, Egri's 3-dimensional character physiology/sociology/psychology, antagonist as the protagonist's mirror, ensemble & relationship webs, character revealed through choice under pressure), (c) dialogue (subtext 潜台词, dialogue as action & conflict not information, 'on the nose' avoidance, distinct character voice, exposition handling, Mamet/Sorkin intention-obstacle dialogue, show-don't-tell, 台词 craft in Chinese drama), (d) scene & sequence craft (scene as a mini-story with goal/conflict/turn, scene value charge & turning point, enter-late-leave-early, the 8-sequence method, set pieces, transitions, slug line/action line/parenthetical format craft), (e) theme & premise (controlling idea/premise/前提, theme as dramatized argument not message, moral argument Truby, thematic unity, 'what is this really about'), (f) genre (genre conventions as audience promise, Snyder's 10 story types, subverting vs honoring tropes, 类型片 vs 文艺片, Chinese genres 主旋律/古装/年代/悬疑/甜宠/都市/军旅/历史正剧), (g) format & industry process (Holly

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。

企业财务与 CFO 视角 (企业财务与 CFO 视角 (Corporate Finance & the CFO Lens) — 面向创业公司与中小企业主/创始人/业务负责人的『看懂钱、管住钱、用好钱』的财务判断,不是考注会/中级职称的准则背诵,也不是投行卖方并购执行或 VC 投资人的看项目视角。覆盖: (a) 第一性张力 — 这行的核心世界观分歧: **利润是观点,现金是事实(权责发生制下的利润由收入确认时点、折旧摊销年限、存货计价、资本化与费用化的选择拼出来,是一组可辩论的判断;银行户头的钱是唯一不能辩论的事实——所以 CFO 看三张表的顺序是现金流量表→资产负债表→利润表,与外行相反) ⇄ 增长本身要烧钱(账面盈利的公司照样会因营运资金被增长吸干而倒闭:先付供应商、后收客户钱,规模越大缺口越大,这是『增长性破产』;所以现金转换周期比毛利率更早预警) ⇄ 记账合规派 vs 管理决策派(一套账是给税局与审计看的准则语言,另一套视图是给经营者看的贡献边际与单位经济;同一笔成本在两种语言里归属不同,把合规科目直接拿来做定价决策是中小企业最常见的错) ⇄ 全成本分摊 vs 贡献边际(把固定成本按产量分摊进单件成本,会在淡季得出『卖一件亏一件所以停产』的错误结论;边际思维只问增量收入是否覆盖增量成本,但长期只看边际会让公司永远收不回固定成本) ⇄ 预算是承诺 vs 预算是地图(传统年度预算把数字变成考核契约,导致部门年底突击花钱与藏预算;滚动预测与超越预算派主张预算只是当前最好的猜测,该月月刷新) ⇄ 融资是里程碑 vs 融资是负债(融资新闻稿把估值当成绩,但优先股、优先清算权、对赌与回购条款让创始人在低价退出时可能一分不拿;自筹派认为最便宜的钱是客户的预付款) ⇄ 估值方法之争(DCF 的数学严谨但对增长率与折现率假设极敏感,业内讥为『垃圾进垃圾出』;可比公司倍数简单但把市场情绪打包进来;早期公司两者都不成立,实际靠谈判与稀释目标倒推) ⇄ EBITDA 是不是有用(PE 与并购圈把它当经营现金流代理,巴菲特与芒格公开斥其忽略了折旧背后真实的资本开支;调整后 EBITDA 的『加回』项在业内被视为高危信号) ⇄ 财务是记分员 vs 财务是业务伙伴(传统财务事后出报表,财务 BP/FP&A 主张财务应在决策前进场做定价、投产、招人的经济性测算) ⇄ 中国中小企业的两套账现实 vs 合规红线(金税四期与社保入税之后,业内公认的做法是尽早并账,但这条张力必须如实呈现而不是装作不存在,也绝不给出规避税收的操作建议)); (b) 工具栈(记账层与决策层是两套东西) — 记账与 ERP(用友、金蝶、Odoo、QuickBooks、Xero、NetSuite、SAP Business One)、中国财税合规(电子税务局、金税四期发票与进销项比对、百望/航天信息电子发票、慧算账等代账 SaaS、个税与社保申报)、FP&A 与预算(Excel 与 Google Sheets 仍是绝对主力,之上是 Cube、Causal、Jirav、Mosaic、Runway、Abacum、Pigment、Anaplan、Planful)、现金流预测(Float、Fathom、13 周滚动现金流模板)、股权与 cap table(Carta、Pulley、AngelList、Excel 稀释模型,中国的股权代持与持股平台)、订阅计费与收入确认(Stripe Billing、Chargebee、Maxio)、费控报销(Ramp、Brex、Expensify、汇联易、分贝通)、BI 与看板(Power BI、Tableau、Metabase、帆软)、以及最被低估的纸笔工具(一页纸的驱动因素模型、贡献边际表、13 周现金日历)—— 选型的真正分岔是『公司在哪个阶段、由谁来维护这个模型』,不是厂商功能清单; (c) 心智模型层 — 三张表的勾稽关系(利润表的净利经现金流量表调整后落到资产负债表的未分配利润)、权责发生制与收付实现制的差、现金转换周期 CCC 与 DSO/DIO/DPO、营运资金与增长的耦合、贡献边际与盈亏平衡点、经营杠杆与固定成本结构、单位经济与 LTV/CAC 及回本周期、烧钱率与现金跑道 runway、自由现金流与业主收益 owner earnings、资本成本与机会成本、净现值与内部收益率、投入资本回报率 ROIC 与增长的价值条件(只有 ROIC 高于资本成本时增长才创造价值)、股权稀释与优先清算权的退出瀑布、递延收入是负债不是收入; (d) 工作流/SOP — 月度关账与管理报表包(关账日历、计提、对账、出具一页纸经营分析)、13 周滚动现金流预测的搭建与每周刷新、年度预算与滚动预测(自上而下目标与自下而上驱动因素模型的对撞)、定价与成本核算(标准成本、作业成本法、贡献边际定价与报价审批)、应收账款与账期管理(信用政策、账龄表、催收节奏、保理与供应链金融)、融资轮次建模(投前投后估值、期权池扩容对创始人的额外稀释、SAFE 与可转债转股、优先清算权下的退出分配)、投资决策与产能/招人测算(增量现金流、回收期、敏感性分析)、税务合规日历与汇算清缴、董事会与投资人财务包、尽调与数据室准备、以及财务模型的三表联动搭建; (e) 知识正典(en 一手极厚,中文一手集中在高校教授与准则原文) — 《Financial Intelligence》Berman & Knight(给非财务经理的入门标准)、《Financial Statements》Thomas Ittelson、Brealey·Myers·Allen《Principles of Corporate Finance》(公司金融教科书)、Damodaran 的估值三部曲与《Narrative and Numbers》及其 NYU 公开课与免费数据集、《Simple Numbers, Straight Talk, Big Profits!》Greg Crabtree(中小企业实操)、《Venture Deals》Feld & Mendelson(条款与稀释)、《Financial Shenanigans》Howard Schilit(识别财务粉饰)、《The Outsiders》Thorndike(资本配置)、《Accounting for Value》Penman、伯克希尔股东信中的业主收益与商誉摊销讨论、《The Essays of Warren Buffett》、《Profit First》Michalowicz(流行但有争议)、IFRS 15/16 与 ASC 606 收入与租赁准则原文、中国企业会计准则 CAS 与小企业会计准则、肖星《一本书读懂财报》与清华的财务分析公开课、张新民的财务报表分析体系; (f) 行业大佬/figures — Aswath Damodaran(NYU,估值教父,博客与公开课与数据集全免费开放,一手素材极厚)、Michael Mauboussin(ROIC 与资本配置的实证写作)、Howard Schilit(财务舞弊识别)、Karen Berman 与 Joe Knight(财务素养普及)、Greg Crabtree(中小企业现金与利润实操)、Brad Feld 与 Jason Mendelson(创业融资条款)、David Skok 与 Jason Lemkin 与 David Sacks(SaaS 单位经济与烧钱效率指标)、Warren Buffett 与 Charlie Munger(对 EBITDA 与股权激励费用化的著名批评)、CJ Gustafson 等现役 CFO 的时事通讯作者、以及中文圈的肖星与张新民等高校学者; (g) 争议/批判(必须保留不洗白) — 调整后 EBITDA 与非公认会计准则指标的滥用(把股权激励与一次性费用年年加回)、DCF 对假设的极端敏感与被用来事后合理化结论、独角兽估值与优先清算权造成的『纸面身价』幻觉、对赌与回购条款把股权融资变成隐性债务、Profit First 现金分桶法被专业会计批评为回避真实成本结构、作业成本法的实施失败率高、预算游戏与年底突击花钱、财务 BP 沦为报表美化、中国中小企业两套账的历史现实与金税四期后的合规收敛(如实呈现风险,不提供规避操作)、以及『融资额等于成功』的媒体叙事对创始人的误导; (h) 流派/思想谱系 — **准则与合规派(IASB/FASB/财政部,信可比性与审计留痕,语言是准则条文)** vs **管理会计/决策派(IMA 与贡献边际、作业成本法、有效产出会计,信决策相关性高于合规一致性)** vs **公司金融/估值派(Brealey-Myers-Allen 与 Damodaran,信现金流折现与资本成本)** vs **价值投资/资本配置派(巴菲特-芒格-Thorndike-Mauboussin,信业主收益与 ROIC,公开鄙视 EBITDA)** vs **创业与 SaaS 指标派(Skok-Lemkin-Sacks-Bessemer,信单位经济、回本周期与烧钱倍数)** vs **中小企业现金实操派(Crabtree、Profit First 一脉,信老板看得懂的少数几个数)**。不含: 投行卖方并购执行与尽调建模(已由 investment-banking-mna 覆盖)、VC 投资人的看项目与投后视角(已由 vc-investor 覆盖)、个人理财与二级市场投资(已由 personal-investing 覆盖)、注册会计师考证与准则条文背诵、以及任何税收规避操作建议。) Master O

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。

广告外包公司绩效管理 (广告外包公司绩效管理 (Ad Agency / Marketing-Outsourcing Firm Performance Management) — 广告/营销外包公司(乙方 agency:创意热店/4A/本土广告公司/传媒公司/数字营销代理/MCN/设计工作室/内容外包)的『怎么做绩效管理』职业认知操作系统,面向老板/合伙人、运营总监(COO)、HR/HRBP、项目总监、team lead、以及想搭绩效体系的从业者。覆盖: (a) 第一性张力 — 绩效管理的核心世界观分歧: **创意/知识工作『不可量化』 vs 『必须可考核』(创意难归因、难标准化,硬套 KPI 杀创意;但不考核养懒人——这是本行绩效的元矛盾) ⇄ 结果导向(KPI/业绩/回款) vs 过程导向(OKR/能力/成长) ⇄ 个人绩效 vs 团队协作(广告是集体产物,创意-AE-媒介-设计协作,难拆到个人) ⇄ 强激励(提成制:多劳多得但抢单/短视/不协作/吃老客户) vs 稳定(固定+奖金:公平但大锅饭) ⇄ 规模/流水 vs 利润/人效(低价接单冲规模 vs 保毛利)**; (b) 绩效体系设计 — KPI(关键指标法)/OKR(目标与关键成果)/BSC(平衡计分卡)/360 环评/MBO(目标管理)/KSF(关键成功因子)/积分制/计件提成;考核周期(月/季/年+项目制);绩效面谈、绩效改进 PIP、强制分布(271/活力曲线)争议、绩效结果应用(调薪/晋升/淘汰/奖金); (c) 分岗位绩效(本行难点,各岗量化差异极大) — 创意(文案/美术/创意总监:作品质量、获奖、比稿命中率——最难量化)、AE/客户执行(客户满意度、续约、回款、增购、客诉)、媒介/投放(可量化:ROI/ROAS/CPM/转化——最易量化)、策略/策划(方案通过率、洞察)、设计(产能/返稿率/品质)、项目管理(交付准时率、利润率)、销售/BD(新签、回款、毛利); (d) 项目与客户维度绩效(agency 特有,专业服务公司逻辑) — 项目利润率(收入-人力成本-外部成本)、工时制与人效(billability 可计费工时率/utilization 利用率/realization 实现率,借鉴咨询律所)、人均产值/人均毛利、客户续约率与 LTV、客户集中度风险、比稿投入产出、改稿次数失控; (e) 激励与分配机制 — 提成制(按签单/毛利/回款抽成)、项目奖金分成(如何在创意-AE-媒介间分)、年终奖包、合伙人制/事业合伙人/工作室 studio 制/阿米巴、股权期权、创意人才的非物质激励(署名/获奖/成长); (f) 人效、成本与文化 — 人效比(人力成本占收入比,业内估计通常 40-55%,非普适)、毛利率、加班/血汗工厂文化批判(乙方 996/改稿到凌晨)、人才流失率与保留、招聘与培养、组织架构(客户组 vs 职能组 vs 项目制矩阵); (g) 外包/乙方特有张力对绩效的侵蚀 — 甲乙方权力不对等(甲方压价、无限改稿、比稿白嫖创意、账期长垫款重回款难)、低价内卷与红海、项目制不确定性(旺淡季、大客户依赖)、创意工时不可控如何计入绩效、外包 vs 自建团队的成本对比; (h) 争议/批判 — KPI 量化派 vs 创意不可考核派、提成制养蛊 vs 团队协作、强制分布/末位淘汰是否适合小 agency、工时制(billable hours)被咨询律所验证但绑架员工健康、『向甲方看齐做 OKR』水土不服、绩效主义扼杀创意(索尼绩效主义之殇式批判)、乙方绩效本质是『用考核对冲甲方不确定性』的转嫁; (i) 流派/思想谱系 — 专业服务公司管理派(David Maister《Managing the Professional Service Firm》PSF 圣经:leverage 杠杆/utilization 利用率/billing;借鉴咨询律所会计所) vs agency 专家经营派(David C. Baker《The Business of Expertise》+2Bobs podcast、Blair Enns《Win Without Pitching》《Pricing Creativity》定位与定价) vs OKR/目标管理派(John Doerr《Measure What Matters》、Google/Intel OKR、字节/飞书 OKR 本土化) vs 中式绩效工具派(KSF 薪酬全绩效/积分制/阿米巴/华为绩效体系被广告公司借用) vs 本土 4A/广告公司实战派(省广/蓝色光标/华扬联众/利欧 等上市广告公司管理 + 创意热店工作室制)。不含: 广告投放/信息流/SEM 的技术操作本身、甲方市场部/品牌方内部绩效、通用 HR 招聘薪酬全流程(仅取与绩效相关部分)、纯财务会计做账、MCN 达人孵化运营细节。) Master OS — automated mastery of 广告外包公司绩效管理 (Ad Agency / Marketing-Outsourcing Firm Performance Management) — 广告/营销外包公司(乙方 agency:创意热店/4A/本土广告公司/传媒公司/数字营销代理/MCN/设计工作室/内容外包)的『怎么做绩效管理』职业认知操作系统,面向老板/合伙人、运营总监(COO)、HR/HRBP、项目总监、team lead、以及想搭绩效体系的从业者。覆盖: (a) 第一性张力 — 绩效管理的核心世界观分歧: **创意/知识工作『不可量化』 vs 『必须可考核』(创意难归因、难标准化,硬套 KPI 杀创意;但不考核养懒人——这是本行绩效的元矛盾) ⇄ 结果导向(KPI/业绩/回款) vs 过程导向(OKR/能力/成长) ⇄ 个人绩效 vs 团队协作(广告是集体产物,创意-AE-媒介-设计协作,难拆到个人) ⇄ 强激励(提成制:多劳多得但抢单/短视/不协作/吃老客户) vs 稳定(固定+奖金:公平但大锅饭) ⇄ 规模/流水 vs 利润/人效(低价接单冲规模 vs 保毛利)**; (b) 绩效体系设计 — KPI(关键指标法)/OKR(目标与关键成果)/BSC(平衡计分卡)/360 环评/MBO(目标管理)/KSF(关键成功因子)/积分制/计件提成;考核周期(月/季/年+项目制);绩效面谈、绩效改进 PIP、强制分布(271/活力曲线)争议、绩效结果应用(调薪/晋升/淘汰/奖金); (c) 分岗位绩效(本行难点,各岗量化差异极大) — 创意(文案/美术/创意总监:作品质量、获奖、比稿命中率——最难量化)、AE/客户执行(客户满意度、续约、回款、增购、客诉)、媒介/投放(可量化:ROI/ROAS/CPM/转化——最易量化)、策略/策划(方案通过率、洞察)、设计(产能/返稿率/品质)、项目管理(交付准时率、利润率)、销售/BD(新签、回款、毛利); (d) 项目与客户维度绩效(agency 特有,专业服务公司逻辑) — 项目利润率(收入-人力成本-外部成本)、工时制与人效(billability 可计费工时率/utilization 利用率/realization 实现率,借鉴咨询律所)、人均产值/人均毛利、客户续约率与 LTV、客户集中度风险、比稿投入产出、改稿次数失控; (e) 激励与分配机制 — 提成制(按签单/毛利/回款抽成)、项目奖金分成(如何在创意-AE-媒介间分)、年终奖包、合伙人制/事业合伙人/工作室 studio 制/阿米巴、股权期权、创意人才的非物质激励(署名/获奖/成长); (f) 人效、成本与文化 — 人效比(人力成本占收入比,业内估计通常 40-55%,非普适)、毛利率、加班/血汗工厂文化批判(乙方 996/改稿到凌晨)、人才流失率与保留、招聘与培养、组织架构(客户组 vs 职能组 vs 项目制矩阵); (g) 外包/乙方特有张力对绩效的侵蚀 — 甲乙方权力不对等(甲方压价、无限改稿、比稿白嫖创意、账期长垫款重回款难)、低价内卷与红海、项目制不确定性(旺淡季、大客户依赖)、创意工时不可控如何计入绩效、外包 vs 自建团队的成本对比; (h) 争议/批判 — KPI 量化派 vs 创意不可考核派、提成制养蛊 vs 团队协作、强制分布/末位淘汰是否适合小 agency、工时制(billable hours)被咨询律所验证但绑架员工健康、『向甲方看齐做 OKR』水土不服、绩效主义扼杀创意(索尼绩效主义之殇式批判)、乙方绩效本质是『用考核对冲甲方不确定性』的转嫁; (i) 流派/思想谱系 — 专业服务公司管理派(David Maister《Managing the Professional Service Firm》PSF 圣经:leverage 杠杆/utilization 利用率/billing;借鉴咨询律所会计所) vs agency 专家经营派(David C. Baker《The Business of Expertise》+2Bobs podcast、Blair Enns《Win Without Pitching》《Pricing Creativity》定位与定价) vs OKR/目标管理派(John Doerr《Measure What Matters》、Google/Intel OKR、字节/飞书 OKR 本土化) vs 中式绩效工具派(KSF 薪酬全绩效/积分制/阿米巴/华为绩效体系被广告公司借用) vs 本土 4A/广告公司实战派(省广/蓝色光标/华扬联众/利欧 等上市广告公司管理 +

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。

数据工程 — 数据平台从业者的认知操作系统, 覆盖把数据从源系统搬运成可靠 / 可查询 / 可信赖形态供分析 / ML / 数据产品消费的全生命周期 (生成 → 摄取 → 存储 → 转换 → 服务 + 安全/数据管理/DataOps/数据架构/编排/软件工程 六条暗流, Reis & Housley 框架): 摄取与集成 (批 + CDC 变更数据捕获 Debezium + EL 工具 Fivetran/Airbyte/Meltano/dlt + Kafka Connect + schema drift) / 存储与文件表格式 (对象存储数据湖 + 列存 Parquet/ORC/Arrow/Avro + 开放表格式 Apache Iceberg/Delta Lake/Apache Hudi + lakehouse + 分区/compaction) / 转换与建模 (ELT dbt/SQLMesh + Spark + 维度建模 Kimball + Inmon + Data Vault + 大宽表 OBT + 渐变维 SCD + 增量模型 + 语义/指标层) / 编排与工作流 (Apache Airflow/Dagster/Prefect/Mage/Kestra/Apache DolphinScheduler + DAG + 幂等 + 回填 backfill + 数据资产调度) / 批流与实时 (Apache Kafka/Apache Flink/Spark Structured Streaming/Kinesis/Pulsar/Redpanda + Lambda vs Kappa + watermark/窗口/exactly-once + 流式 SQL Materialize/RisingWave + 实时 OLAP ClickHouse/Apache Druid/Apache Pinot/StarRocks/Apache Doris) / 数仓与查询引擎 (Snowflake/BigQuery/Redshift/Databricks SQL/Trino/Presto/DuckDB/Polars + 存算分离 + MPP) / 数据质量测试与可观测性 (dbt tests/Great Expectations/Soda + 数据契约 + Monte Carlo data downtime + 新鲜度/量/schema 异常检测) / 数据治理编目与血缘 (DataHub/Amundsen/OpenMetadata/Unity Catalog + 列级血缘 + PII 分类 + 访问控制 + GDPR) / DataOps 与可靠性 (数据 CI/CD + 转换版本控制 + 环境隔离 + 幂等重处理 + 数据 SLA/SLO + 计算存储 FinOps) / 数据架构范式 (现代数据栈 + lakehouse + data mesh + data fabric + 去中心化 vs 中心化所有权) / 分析工程角色 (dbt 时代连接数据工程与分析的桥) — 不含 数据科学/ML 建模本身 (是下游消费者) / BI 仪表盘制作 (serving 下游) / 数据分析报表为终点 / 'data engineer = 跑 Hadoop 的' 过时窄化 / 通用后端应用开发 (平行学科) (Data Engineering — the cognitive operating system of practitioners who design, build, and operate the data platform: moving data from source systems into reliable, queryable, trustworthy form for analytics / ML / products, covering (a) the data engineering lifecycle (generation → ingestion → storage → transformation → serving, with the undercurrents security / data management / DataOps / data architecture / orchestration / software engineering — Reis & Housley framing), (b) ingestion & integration (batch + CDC change-data-capture with Debezium, EL tools Fivetran / Airbyte / Meltano / dlt, Kafka Connect, API + file + database sources, schema drift handling), (c) storage & file/table formats (object storage data lakes, columnar formats Parquet / ORC / Arrow / Avro, open table formats Apache Iceberg / Delta Lake / Apache Hudi, lakehouse architecture, partitioning / compaction / Z-ordering), (d) transformation & modeling (ELT with dbt / SQLMesh, Spark, dimensional modeling Kimball, Inmon CIF, Data Vault, One Big Table / wide tables, normalization vs denormalization, slowly changing dimensions, incremental models, the semantic / metrics layer), (e) orchestration & workflow (Apache Airflow, Dagster, Prefect, Mage, Kestra, Apache DolphinScheduler, DAGs, idempotency, backfills, data-aware / asset-based scheduling), (f) batch vs streaming & real-time (Apache Kafka, Apache Flink, Spark Structured Streaming, Kinesis / Pulsar / Redpanda, the Lambda vs Kappa debate, watermarks / windowing / exactly-once, streaming SQL Materialize / RisingWave, real-time OLAP ClickHouse / Apache Druid / Apache Pinot / StarRocks / Apache Doris), (g) warehouses & query engines (Snowflake, BigQuery, Redshift, Databricks SQL, Trino / Presto, DuckDB, Polars, decoupled storage & compute, MPP), (h) data quality, testing & observability (dbt tests, Great Expectations, Soda, data contracts, Monte Carlo / data downtime, freshness / volume / schema anomaly detection, unit / integration testing of pipelines), (i) data governance, catalog & lineage (DataHub, Amundsen, OpenMetadata, Unity Catalog, column-level lineage, PII / data classification, access control, GDPR / data privacy), (j) DataOps & reliability (CI/CD for data, version control of transformations, environments, idempotent reprocessing, SLAs / SLOs for data, cost / FinOps for compute & storage), (k) data architecture paradigms (modern data stack, data lakehouse, data mesh, data fabric, decentralized vs centralized ownership), (l) the analytics engineering role (the dbt-era bridge between data engineering and analysis); N

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 a minigame (snake, quiz, puzzle, timing/reaction game, ...) to a Pixi'VN visual novel — the `useMinigame` lifecycle hook pattern, using PixiJS directly on its own layer instead of `gameLayer`, hotkeys for controls, linking the minigame to a route, and why saving/restoring minigame state is the developer's own responsibility.

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 defining visual novel characters for a @drincs/pixi-vn game — creating a character with a name, color, icon and other props, registering it so it can be looked up by id, and referencing it from dialogue/narration. Load this before writing any `CharacterBaseModel` or `RegisteredCharacters` code.

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。

Binding-resolved Python symbol queries via pyright — every true caller (--refs), the real definition (--def), or an inferred signature (--hover) of a .py symbol, excluding the same-named false positives text search cannot tell apart. Use when a task needs ALL callers or users of a named Python symbol and grep would over-match. Python only, and only for the caller/definition question: measured 2026-07-04 on real issue-localization tasks, plain ripgrep tied or beat the semantic and indexed-regex tiers at 4-60x less wall-clock, so those tiers survive below without being a default.

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 navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all page-anchored. Produces _MAP.md (progressive disclosure), .symbols.json (definition index), .anchors.json (claim references), and a _USAGE.md snippet for CLAUDE.md. Use when analyzing papers, specs, or legal docs; when asked to "map this document", "index this PDF", "what does this paper say"; or when a coding agent needs grounded reference material from a PDF source. Analogous to tree-sitting but for prose documents.

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。

Check that a document's claims about code are actually true by reading the prose, the code, and the tests and reporting (or fixing) where they disagree. Use whenever the user wants to verify a README, guide, spec, or docstring still matches the code; whenever they mention documentation drift, doc-code sync, "is this still accurate", stale docs, or keeping docs/tests/code consistent; before publishing or merging a docs change; or as a periodic doc-accuracy sweep. The agent reads the prose's meaning directly — there is no claim-comment DSL to maintain. Pairs with TDD — the test suite is the deterministic behavioral gate, this skill is the semantic prose-vs-reality review.

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。

Listen to generated music by measuring it and by reading it as sheet music: render Strudel code or record a Web Audio page through the real engine in headless Chromium, then read spectrograms, pYIN pitch lines, chroma, roughness and semitone-rub meters; engrave notes as a score with beat-by-beat harmony; transcribe a melody from audio; read MusicXML/MIDI/ABC or a score image into notes and into Strudel code. Use to check whether generated music sounds right or better (before/after a change), to match a reference track, spectrogram image or score, or to find discordant chords, a buried melody, clipping or muddy mixes. Triggers on 'does it sound better', 'listen to', 'render and check', 'spectrogram', 'sfft/stft', 'discordant', 'clashing chords', 'sounds off', 'compare to the original', 'reproduce this track in Strudel', 'sheet music', 'score', 'notation', 'MusicXML', 'MIDI', 'ABC', 'transcribe', 'OMR'. Pairs with strudeling (writing Strudel); for format conversion use processing-video.

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。

Semantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-to-definition, find-references, hover types, type diagnostics, file symbol outlines, and project-wide symbol search — name resolution and type inference that tree-sitter and ripgrep cannot do. Use when you need to follow an import to a definition, find all real uses of a symbol (excluding same-named-but-unrelated ones), get an inferred type, surface type errors, outline a file, or search symbols across a project. Triggers on "go to definition", "find references", "what type is", "resolve this symbol", "symbol outline", "find symbol in project", "pyright", "type-check this file".

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 hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tree-sitting (structural) with semantic (why/what-for) layer.

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 video from prompts by overseeing multi-clip AI generation end to end: write a shot list, generate each scene with Gemini Omni Flash (via the Cloudflare AI Gateway), review the results, and assemble them into a finished cut. Use when the user asks to make/generate a video, a short film, an animatic, or a multi-scene clip from a script or idea; when they mention Omni, Veo, text-to-video, or image-to-video; or when acting as the editing/director agent over generated footage. Triggers on 'make a video', 'generate a clip', 'short film', 'video from this script', 'turn this into a video', 'omni', 'veo', 'text to video', 'storyboard to video'. For transcoding/trimming/merging/GIF/subtitles use processing-video; for reading or summarizing existing video content use parsing-video.

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。

Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when choosing a subagent's model or effort, when choosing how to escalate a failed attempt, or when asked which model or effort a task should get. Grounded in a 2026-07 calibration, a 2026-08 coding-cost study, a 2026-09 seeded-bug repair battery, a 2026-10 Haiku 5.5 ladder priced per spawn, and a 2026-10 retry-versus-escalation ladder on 295 SWE-bench Verified tasks; Managed Agents API specifics are operational, not calibrated.

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。

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

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。

Draws an activity flow / system architecture diagram as ONE self-contained, INTERACTIVE HTML+SVG page (2-pane app layout — left: diagram, default fit-to-view with zoom/pan; right: sidebar with explainer cards), styled like a real hand-drawn enterprise doc (Stripe/AWS-docs style — real brand logos for MongoDB/Odoo/n8n/etc. from a bundled Simple Icons library, neutral white boxes, sans-serif, no "AI neon" look), scroll-to-zoom, auto light/dark with a toggle button — clicking a flow (a legend chip, a line, or a step badge) highlights that flow with traveling dots along the arrows in their direction, a ping at the destination box, and a sidebar panel that slides out, while everything else dims; two-way arrows (OUT = solid blue / RETURN = dashed green) carry numbered step badges, colored by semantic meaning (red = auth checkpoint, purple = scheduled flow, amber = data pipeline), a small "hop" arc where two lines are forced to cross, dashed group regions, one explainer card per flow in the right sidebar. Use this skill ANY TIME the user wants to "draw a diagram", "draw a flow", "draw a system diagram", "redraw this so it's easier to follow", "interactive diagram", "two-way diagram", "request/response flow", "make a free-form HTML diagram" — even if they never say the word HTML. Especially good when both the request direction AND the response direction need to be shown, or when a templated tool (archify, mermaid) is too rigid. Do NOT use for data charts (bar/line/pie), and do not use when the user asks specifically for archify or mermaid.

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。

Extract, suggest, and sync tags and categories for blog posts across all major CMS platforms. Supports WordPress REST API, Shopify GraphQL, Ghost Content API, Strapi REST/GraphQL, and Sanity GROQ. Generates tag suggestions from content analysis (keyword frequency, heading extraction, semantic grouping), enforces minimum post-count thresholds to prevent thin tag archives, and syncs taxonomy via authenticated API calls. Use when user says "tags", "categories", "taxonomy", "tag suggestions", "sync tags", "WordPress tags", "Shopify tags".

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。

Critique a screen's colour usage — contrast ratios, palette coherence, semantic meaning, and colour accessibility.

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 comprehensive color system with palette generation, semantic mapping, and accessibility compliance.

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。

Detect keyword cannibalization across blog posts by extracting primary keywords from titles and headings, clustering semantically similar targets, and flagging posts competing for the same search intent. Supports local-only mode (grep-based) and DataForSEO API mode (Page Intersection endpoint at ~$0.01/call). Outputs severity-scored report with merge or differentiate recommendations. Use when user says "cannibalization", "keyword overlap", "competing pages", "duplicate keywords", "cannibalize".

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。

Semantic topic cluster planning and automated execution engine for claude-blog. Performs SERP-based keyword research, groups keywords by search intent and SERP overlap, builds a hub-and-spoke cluster architecture, generates an interactive SVG cluster map, and executes the full cluster by orchestrating blog-write calls with shared cluster context and automatic internal-link injection. Fills the strategy-to-execution gap: blog-strategy plans the blueprint, blog-cluster builds the house. Use when user says "blog cluster", "topic cluster", "content cluster", "cluster plan", "cluster execute", "pillar content", "hub and spoke", "content ecosystem", "cluster map".

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。

语义层工具使用规范。在发现语义层工具可用、需要查询指标定义/维度信息、验证业务口径、处理指标歧义时，必须优先调用此技能。无语义层工具时不调用。

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。