5,126 件 ・ 関連度順
概要と使いどころ
Analyzes large tasks for independent subtasks that can be safely parallelized. Produces a DAG-based dispatch plan with dependency ordering and maximum parallelism. Use when a task has 5+ subtasks touching independent files, or the user asks to speed up or parallelize the work.
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。
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。
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。
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。
Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the results", "check the eval code", "实验诚实度".
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 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。
Azure Machine Learning SDK v2 for Python workflow skill. Use this skill when the user needs Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines 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。
Azure Machine Learning SDK v2 for Python workflow skill. Use this skill when the user needs Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines 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。
Asana Automation via Rube MCP workflow skill. Use this skill when the user needs Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas 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。
Asana Automation via Rube MCP workflow skill. Use this skill when the user needs Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas 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。
Antigravity UI & Motion Design Expert workflow skill. Use this skill when the user needs Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS 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。
AgentFlow workflow skill. Use this skill when the user needs Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution 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。
AI UGC Ads workflow skill. Use this skill when the user needs When the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated content. Also use when the user mentions 'UGC,' 'user-generated content,' 'creator ads,' 'Spark Ads,' 'whitelisting,' 'AI UGC,' 'Arcads,' 'Creatify,' 'creator brief,' or 'UGC testing.' This skill covers the UGC growth framework from creator recruitment through AI-powered scaling. Do NOT use for technical implementation, code review, or software architecture 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。
🤖 Andru.ia Solutions Architect - Hybrid Engine (v2.0) workflow skill. Use this skill when the user needs Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para proyectos de IA en español 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。
🤖 Andru.ia Solutions Architect - Hybrid Engine (v2.0) workflow skill. Use this skill when the user needs Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para proyectos de IA en español 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。
Explain CSS layout issues and propose fixes. Use when a junior developer is struggling with alignment or spacing.
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。
半导体芯片制造工艺 (Semiconductor Process Engineering / 半导体芯片制造工艺 — 以「物理化学极限 + 良率经济双重约束」为特征的集成电路前道/后道制造工艺认知操作系统：从「器件架构与微缩路线（planar→FinFET→GAA nanosheet→CFET、等效微缩 DTCO/STCO、背面供电 BSPDN）→ 工艺整合（FEOL/MOL/BEOL 模块协同、PDK、流片 tape-out）→ 单元工艺（光刻 litho（DUV 浸没式 193i / EUV 13.5nm / 多重曝光 SADP-SAQP / OPC / mask）、刻蚀 etch（RIE/ICP/原子层刻蚀 ALE）、薄膜沉积 depo（CVD/PECVD/LPCVD/ALD/PVD/外延 epi/电镀 Cu）、掺杂 doping（离子注入 ion implant / 退火 RTA-laser anneal）、CMP 化学机械抛光、清洗 cleaning）→ 量测检测 metrology（CD-SEM / OCD / overlay / 椭偏 ellipsometry / 缺陷检测 defect inspection / e-beam）→ 良率工程 yield（缺陷密度 / SPC 统计过程控制 / FDC / APC / DOE 实验设计 / 良率爬坡 yield ramp）→ 先进封装 advanced packaging（2.5D/3D、CoWoS、HBM、混合键合 hybrid bonding、chiplet、TSV）」的完整器件-工艺-良率-量产决策链。覆盖 (a) 第一性张力 — **物理/化学/材料的硬约束（量子隧穿、短沟道效应、RC 延迟、热预算、缺陷物理、ppb 级污染控制）⇄ 良率/成本/产能的经济约束（每片晶圆成本、良率是主经济指标、D0 缺陷密度、wafer-per-hour、折旧）**；**持续微缩/摩尔定律（dimensional + equivalent scaling、节点路线图 N5/N3/N2/A16/A14、high-NA EUV）⇄ 物理极限/微缩放缓（原子尺度、漏电、功耗墙、成本墙、'摩尔定律已死'之争）**；**协同优化/整合（DTCO 设计-工艺协同、STCO 系统-工艺协同、模块间 trade-off）⇄ 单模块极致优化（单一 unit process 工艺窗口）**；**工艺配方的 tacit 手艺（process recipe 调试、工艺窗口、缺陷根因分析、量产 ramp 的经验）⇄ 可建模/可仿真/数据驱动（TCAD 仿真、ML 良率分析、APC/FDC、数字孪生）**；**性能-功耗-面积-成本 PPAC 四角权衡 ⇄ 良率/可制造性 DFM 优先**；**自主可控/国产替代（卡脖子、EUV 出口管制、设备/材料/EDA 国产化、SMIC/长江存储/长鑫/中微/北方华创/上海微电子）⇄ 全球高度分工（ASML 光刻垄断、AMAT/Lam/TEL/KLA 设备、TSMC/Samsung/Intel 代工、全球供应链）**。(b) 核心工作流 / pipeline（最标准、最易蒸高质量 + CLI 化）— 新节点/新工艺导入：器件目标与 PPAC 定义 → 工艺整合方案与 PDK → 单元工艺开发与配方调试（DOE 找工艺窗口）→ 量测建立与 SPC → 良率爬坡（缺陷分类 + 根因分析 + 工艺改善）→ 量产移交与持续改善。具体单元工艺 SOP：光刻（曝光条件 / OPC / overlay 控制 / 多重曝光分解）、刻蚀（选择比 / profile / loading effect / ALE）、沉积（台阶覆盖 / 应力 / 均匀性）、CMP（去除速率 / 碟形 dishing / 侵蚀 erosion）、量测与缺陷分析、良率分析与 FA 失效分析。(c) 工具栈 — 设备（光刻 ASML/上海微电子 SMEE；刻蚀+沉积 AMAT/Lam/TEL/中微 AMEC/北方华创 Naura；离子注入 AMAT/Axcelis；CMP AMAT/荏原 Ebara；量测检测 KLA/AMAT/中科飞测/上海精测）、EDA/TCAD/仿真（Synopsys Sentaurus/Silvaco/Coventor SEMulator3D、OPC Calibre/Synopsys）、良率与制造软件（SPC、MES、FDC/APC、缺陷分析 yield management、PWS）、材料（光刻胶 photoresist、CMP 浆料 slurry、特气、靶材、掩膜 mask blank）。(d) 知识正典 — 半导体工艺 canon 横跨器件物理与制造工程：核心教材（Plummer/Deal/Griffin《Silicon VLSI Technology》、Sze《Physics of Semiconductor Devices》《VLSI Technology》、Wolf & Tauber《Silicon Processing for the VLSI Era》、Campbell《Fabrication Engineering at the Micro and Nanoscale》、May & Spanos《Fundamentals of Semiconductor Manufacturing and Process Control》、Quirk & Serda《Semiconductor Manufacturing Technology》、肖国勇/施敏中文教材）、路线图（ITRS/IRDS、IEEE 国际器件与系统路线图）、顶会论文（IEDM、Symposium on VLSI Technology、IRPS 可靠性、SPIE Advanced Lithography、ISSCC、DAC）、行业分析（SemiAnalysis、TechInsights、IC Knowledge）。(e) figures/流派 — 学术与器件奠基（Gordon Moore 摩尔、Robert Dennard 登纳德微缩、胡正明 Chenming Hu FinFET/UTB-SOI 发明人 UC Berkeley、刘明 Tsu-Jae King Liu Berkeley、Krishna Saraswat Stanford、Mark Bohr Intel 工艺架构）、产业领袖与工艺大师（张忠谋 Morris Chang TSMC、林本坚 Burn-Jeng Lin 浸没式光刻、Martin van den Brink ASML、米玉杰/梁孟松 SMIC/三星工艺、Mark Liu/魏哲家 TSMC）、行业分析师（Dylan Patel SemiAnalysis、Scotten Jones IC Knowledge、TechInsights 拆解、Handel Jones）、科普与拆解（Asianometry、The Chip Letter、半导体行业观察）。流派分歧：等效微缩派 vs 摩尔定律已死派、前道微缩 vs 先进封装 chiplet 异构集成、dimensional scaling vs DTCO 协同优化、IDM vs 纯代工 foundry 模式、自主可控/国产替代路线 vs 全球分工。(f) 行业话术/黑话 — 制程节点 node / 流片 tape-out / 工艺窗口 process window / 良率 yield / 缺陷密度 D0 / 关键尺寸 CD / 套刻 overlay / 掩膜 reticle-mask / 光刻胶 PR / 浸没式 immersion / EUV/DUV / 多重曝光 multi-patterning SADP-SAQP / OPC / 刻蚀选择比 selectivity / profile / loading effect / 原子层刻蚀 ALE / 台阶覆盖 step coverage / 外延 epi / 离子注入 implant / 退火 anneal / RTA / CMP / dishing-erosion / FEOL-MOL-BEOL / FinFET / GAA / 纳米片 nanosheet / CFET / 背面供电 BSPDN / high-NA / PPAC / DTCO-STCO / DFM / SPC / FDC-APC / DOE / WAT-PCM / 良率爬坡 yield ramp / FA 失效分析 / particle 颗粒 / 洁净室 cleanroom-级别 / 12寸-8寸 wafer / chiplet / CoWoS / HBM / 混合键合 hybrid bonding / TSV / PDK / 等效微缩. (g) 争议/批判 — 「摩尔定律是否已死 vs 等效微缩继续」、「节点命名营销化（N3/N2 ≠ 物理 3nm/2nm，gate pitch/metal pitch 才是真尺度）」、「前道微缩 vs 先进封装异构集成谁是未来」、「自主可控/国产替代的现实（EUV 卡脖子、设备/材料/EDA 国产化进度、出口管制 entity list、良率与成熟度差距）」、「良率/成本/性能三角权衡」、「人才稀缺与工艺 know-how 的 tacit 性」、「中国大基金/产能扩张是否过剩」、「制裁与技术封锁」。(h) 大量隐性工艺手艺（process recipe 调试与工艺窗口寻找、缺陷根因分析与 FA、量产良率爬坡的经验判
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。
招聘与猎头 (招聘与猎头 (Recruiting & Executive Search) — 面向甲方招聘负责人/HR 与市场化猎头顾问「双侧视角」的『把一个模糊的用人需求，变成一个来得了、干得好、留得住的人』的判断体系；不是候选人一侧的求职与简历面经（那是 job-hunting-coach 的范围），也不是薪酬绩效/员工关系/组织发展的泛 HR 全模块，更不是劳动法条文解读。覆盖：(a) 第一性张力 —— 这行的核心世界观分歧：**需求诊断优先 ⇄ 快速供给优先**（用人经理提来的岗位需求几乎总是一张愿望清单，资深招聘先开 intake 会把『必须有』与『最好有』拆开、把画像逼成可证伪的成功标准；但按成单计酬的猎头把诊断时间压不进单价里，于是行业里同时存在『先诊断再搜寻』和『先扔简历再说』两种作业习惯）；**结构化面试 ⇄ 看人的直觉**（工业与组织心理学近一个世纪的效度元分析一致指向：结构化面试、工作样本、认知能力测验的预测效度明显高于非结构化面谈与经验年限，但一线用人经理绝大多数仍相信自己聊两句就能看准人——这是本行最大的知行落差，也是所有循证招聘流派的出发点；顺带一提，业内长期奉为圭臬的 Schmidt-Hunter 效度排序近年被重新校正，工作样本的效度被下调，这场修正本身就是本行必须如实呈现的争议）；**能力素质 ⇄ 文化匹配**（culture fit 既是最常被写在拒信里的理由，也是被批评得最凶的偏见外壳，Google 一派主张改口叫 culture add，看的是这个人补上了团队缺的东西，而不是像不像我们）；**主动寻访 sourcing ⇄ 被动投递漏斗**（高端与稀缺技能岗只有 outbound 人才地图一条路；量大岗位靠渠道效率、转化率与自动化，两条路的技能树几乎不重叠）；**人才地图是资产 ⇄ 人才地图是浪费**（保留制猎头把 mapping 当交付物的一部分，成功付费猎头认为地图做完单子已经黄了）；**保留制 retained ⇄ 成功付费 contingency**（按阶段预付、独家、深度地图 vs 多家赛马、入职才收钱、速度压倒深度；两种商业模式塑造出两种截然不同的作业节奏、候选人对待方式与职业道德边界，比如 off-limits 不挖回自己安置过的人）；**内部招聘团队 ⇄ 外部猎头与 RPO**（成本、速度、知识沉淀、雇主品牌归属谁的长期争论；embedded recruiter 是近年的折中）；**候选人体验 ⇄ 筛选效率**（漏斗越严体验越差，被拒者也是客户与口碑）；**AI 筛选的效率 ⇄ 合规与偏见**（简历解析、AI 面试评分、自动排序已在大规模使用，同时被监管盯上：纽约市 Local Law 144 要求自动化决策工具做偏见审计并公示、欧盟 AI 法案把招聘划为高风险场景、伊利诺伊州对 AI 视频面试单独立法；业内既离不开它，也在诉讼与审计里学做记录）；**offer 谈判的锚定 ⇄ 薪酬透明**（多地薪酬区间披露立法把谈判起点从『你现在多少』改成『这个岗位值多少』，问薪酬历史在不少法域已被禁止）；**counter-offer 该不该接**（猎头几乎一致反对，认为留下来的人多数一年内还是会走，但这条业内定论的证据基础本身也在被质疑）；**入职后早期流失算谁的**（保证期与退款条款把这场争论直接写进了合同）。(b) 工具栈 —— 申请人追踪系统 ATS（Greenhouse、Lever、Ashby、Workday Recruiting、SmartRecruiters、iCIMS、Taleo，中国侧 Moka、北森、大易、e成）、猎头 CRM 与交付系统（Bullhorn、Vincere、Loxo、Clockwork、Recruit CRM）、寻访与触达（LinkedIn Recruiter、SeekOut、hireEZ、Amazing Hiring、GitHub 与学术检索，中国侧 BOSS 直聘、猎聘、脉脉、拉勾、牛客）、评估与测评（HackerRank、CodeSignal、CoderPad、结构化面试题库与 scorecard 评分卡、Hogan、SHL、Predictive Index、Criteria、案例作业与工作样本）、面试调度与视频（GoodTime、Calendly、HireVue、Spark Hire）、背景调查与合规（HireRight、Checkr、Sterling，中国侧 i背调、八方锦程，以及个人信息保护法与 GDPR 下的授权链、FCRA 的不利行动通知）、数据与漏斗分析（time to fill 与 time to hire 的口径差异、offer 接受率、通过率与转化漏斗、quality of hire 的度量困境、招聘成本 cost per hire 的口径战争）、以及最被低估的纸笔工具（intake 提纲、成功标准清单、scorecard、人才地图表格、Boolean 检索式、一页纸的岗位价值主张）—— 选型的真正分岔从来不是功能清单，而是『你的岗位是靠触达赢还是靠转化赢』。(c) 心智模型层 —— 招聘是一次双向销售而不是一场考试；岗位画像要写成结果（这个人半年内要做成什么）而不是资历清单；信号与噪音（公司名与学历是弱信号，工作样本与具体行为证据是强信号）；结构化与评分卡的意义在于让判断可比而不是显得严谨；漏斗每一层都在丢人，所以要从入职倒推触达量；稀缺人才不看招聘广告，只在熟人与私域里流动；offer 是谈判也是承诺，谈崩与反悔的代价高度不对称；招聘的质量要到入职之后才结算。(d) 工作流 —— intake 需求诊断会、岗位画像与成功标准、渠道策略与人才地图 mapping、Boolean 与主动触达、简历筛选与电话初筛、结构化面试与 debrief 定校准、工作样本与技术评估、reference check 与背调、offer 设计与谈判、counter-offer 应对、入职前 no-show 防范与 pre-boarding、试用期与早期留存复盘、招聘漏斗与数据复盘、以及岗位关闭或撤销时的收尾。(e) 表达 DNA、质量基准（什么算一次好的招聘）、反模式（外行与新手最容易犯的错：照抄 JD、面试问脑筋急转弯、用薪酬历史锚定、把候选人当库存、背调走过场、offer 口头承诺）、智识谱系（工业与组织心理学的效度学派、循证与结构化招聘派、保留制高管寻访派、增长型 sourcing 与招聘运营派、雇主品牌与候选人体验派、中国互联网大厂的人才盘点与赛马派）。) Master OS — automated mastery of 招聘与猎头 (Recruiting & Executive Search) — 面向甲方招聘负责人/HR 与市场化猎头顾问「双侧视角」的『把一个模糊的用人需求，变成一个来得了、干得好、留得住的人』的判断体系；不是候选人一侧的求职与简历面经（那是 job-hunting-coach 的范围），也不是薪酬绩效/员工关系/组织发展的泛 HR 全模块，更不是劳动法条文解读。覆盖：(a) 第一性张力 —— 这行的核心世界观分歧：**需求诊断优先 ⇄ 快速供给优先**（用人经理提来的岗位需求几乎总是一张愿望清单，资深招聘先开 intake 会把『必须有』与『最好有』拆开、把画像逼成可证伪的成功标准；但按成单计酬的猎头把诊断时间压不进单价里，于是行业里同时存在『先诊断再搜寻』和『先扔简历再说』两种作业习惯）；**结构化面试 ⇄ 看人的直觉**（工业与组织心理学近一个世纪的效度元分析一致指向：结构化面试、工作样本、认知能力测验的预测效度明显高于非结构化面谈与经验年限，但一线用人经理绝大多数仍相信自己聊两句就能看准人——这是本行最大的知行落差，也是所有循证招聘流派的出发点；顺带一提，业内长期奉为圭臬的 Schmidt-Hunter 效度排序近年被重新校正，工作样本的效度被下调，这场修正本身就是本行必须如实呈现的争议）；**能力素质 ⇄ 文化匹配**（culture fit 既是最常被写在拒信里的理由，也是被批评得最凶的偏见外壳，Google 一派主张改口叫 culture add，看的是这个人补上了团队缺的东西，而不是像不像我们）；**主动寻访 sourcing ⇄ 被动投递漏斗**（高端与稀缺技能岗只有 outbound 人才地图一条路；量大岗位靠渠道效率、转化率与自动化，两条路的技能树几乎不重叠）；**人才地图是资产 ⇄ 人才地图是浪费**（保留制猎头把 mapping 当交付物的一部分，成功付费猎头认为地图做完单子已经黄了）；**保留制 retained ⇄ 成功付费 contingency**（按阶段预付、独家、深度地图 vs 多家赛马、入职才收钱、速度压倒深度；两种商业模式塑造出两种截然不同的作业节奏、候选人对待方式与职业道德边界，比如 off-limits 不挖回自己安置过的人）；**内部招聘团队 ⇄ 外部猎头与 RPO**（成本、速度、知识沉淀、雇主品牌归属谁的长期争论；embedded recruiter 是近年的折中）；**候选人体验 ⇄ 筛选效率**（漏斗越严体验越差，被拒者也是客户与口碑）；**AI 筛选的效率 ⇄ 合规与偏见**（简历解析、AI 面试评分、自动排序已在大规模使用，同时被监管盯上：纽约市 Local Law 144 要求自动化决策工具做偏见审计并公示、欧盟 AI 法案把招聘划为高风险场景、伊利诺伊州对 AI 视频面试单独立法；业内既离不开它，也在诉讼与审计里学做记录）；**offer 谈判的锚定 ⇄ 薪酬透明**（多地
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。
Rand Fishkin (Moz 创始人 + SparkToro) 视角. SEO 长期主义 + 跨平台视野 + 受众洞察派. 调用此 skill 时, 用 Rand 框架做战略级 SEO 决策.
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。
游戏设计 (Game Design) — 设计游戏的规则 / 系统 / 机制 / 体验 的从业者认知操作系统 (以电子游戏为主, 含桌游 / 卡牌 / 棋盘游戏): 决定「玩家做什么、为什么有意义、每一刻的体验如何」的学科 —— 区别于游戏程序 (引擎 / 代码)、游戏美术 (视觉 / 音频)、游戏制作 (排期 / 预算 / 团队)。覆盖 (a) 核心设计理论与框架 (MDA 机制-动态-美学 Hunicke/LeBlanc/Zubek + Schell 的「透镜」+ Koster「乐趣即学习」理论 + Sid Meier「一连串有趣的决策」+ Salen & Zimmerman「有意义的游玩」/「二阶设计」/「魔法圈」+ Costikyan 论不确定性 + Suits/Huizinga 游戏哲学), (b) 系统与机制设计 (核心循环 + 游戏经济 sink/source/产出-消耗 + 正负反馈环 + 资源与成长系统 + 涌现 vs 脚本 Will Wright「可能性空间」+ Machinations 经济建模 Dormans + 支配 / 退化策略 + 正交设计 Garfield), (c) 关卡与遭遇设计 (灰盒 blockout + 节奏与张力 + 预告 telegraphing + 主线 vs 探索 + 环境叙事 + 锁钥 gating + 难度曲线), (d) 游戏手感与「juice」(Steve Swink《Game Feel》+ 即时响应 + 屏震 / 反馈 / 打磨 + 输入与镜头 + 「手感」是设计出来的不是附带的), (e) 玩家心理与 UX (Celia Hodent《The Gamer's Brain》+ 心流通道 挑战 vs 技能 Csikszentmihalyi/陈星汉 Jenova Chen + Bartle 玩家类型 + 动机与奖励节奏 + 新手引导 FTUE / 教学化 + 认知负荷 + 无障碍), (f) 平衡与调优 (Ian Schreiber《Game Balance》+ 对称 / 非对称 + 动态难度 DDA + 传递 / 非传递平衡 + nerf/buff + 消除支配策略 + 测试驱动调优), (g) 叙事与任务设计 (ludonarrative 失调 / 和谐 + 环境与系统叙事 + 分支 vs 线性 + Amy Hennig 角色驱动 + 任务结构), (h) 以玩家为中心的迭代流程 (Tracy Fullerton《Game Design Workshop》playcentric + 纸面原型 + 垂直切片 + 测试协议「看而不说 / 你不是你的玩家」+ 快速迭代 + game jam), (i) 类型与形态工艺 (roguelike/roguelite 与程序生成 Derek Yu + 平台跳跃 + RPG 系统 + 策略 4X + 解谜设计 Jonathan Blow + 多人 / PvP 平衡 + 桌游 / 卡牌设计 Reiner Knizia/Richard Garfield/Brenda Romero), (j) F2P / 长线运营 / 商业化设计 (核心 / 元 / 经济循环 + 抽卡 gacha / 开箱 loot box / 战令 battle pass 机制 + 留存 D1/D7/D30 + 转化 + 鲸鱼 + live ops 内容节奏 —— 并诚实处理掠夺式暗黑模式 / 强迫循环 / 剥削式商业化的伦理), (k) 设计师角色与工艺职业 (系统 / 关卡 / 叙事 / UX 设计师之分 + 通才 vs 专才 + 独立作者 vs 3A 团队 + 设计文档 + 传达设计意图 + GDC 工艺社区)。跨 3A / 独立 / 手游 F2P / 桌游。不含 游戏程序 / 引擎 (Unity/Unreal 编码 / 图形 / 网络同步) / 游戏美术 / 动画 / 音频 / 游戏制作 / 项目管理 / 排期 / QA / 游戏作为生意 / 发行 / 市场 / 电竞运营为终点 / 泛泛「我想做游戏」的 game-dev 教程 —— 本 skill 是「设计」学科: 规则 / 系统 / 机制 / 体验。 (Game Design — the cognitive operating system of practitioners who design the rules, systems, mechanics, and experiences of games (video games primarily, plus tabletop/board/card games): the discipline of deciding WHAT the player does, WHY it is meaningful, and HOW the moment-to-moment experience feels — distinct from game programming (builds the engine/code), game art (visuals/audio), and game production (schedule/budget/team). Covers (a) core design theory & frameworks (MDA Mechanics-Dynamics-Aesthetics Hunicke/LeBlanc/Zubek, Schell's Lenses, Koster's theory of fun = learning, Sid Meier 'a series of interesting decisions', Salen & Zimmerman 'meaningful play'/'second-order design'/'magic circle', Costikyan on uncertainty, Suits/Huizinga play philosophy), (b) systems & mechanics design (core loops, game economy sink/source/faucet-drain, feedback loops positive/negative, resource & progression systems, emergence vs scripting Will Wright 'possibility space', Machinations economy modeling Dormans, dominant/degenerate strategy, orthogonal design Garfield), (c) level & encounter design (blockout/greybox, pacing & tension, telegraphing, critical path vs exploration, environmental storytelling, gating & lock-and-key, difficulty curve), (d) game feel & juice (Steve Swink 'Game Feel', moment-to-moment responsiveness, screenshake/feedback/polish, input & camera, the 'feel' is designed not incidental), (e) player psychology & UX (Celia Hodent 'The Gamer's Brain', flow channel challenge-vs-skill Csikszentmihalyi/Jenova Chen, Bartle player types, motivation & reward schedules, onboarding/FTUE/tutorialization, cognitive load, accessibility), (f) balancing & tuning (Ian Schreiber 'Game Balance', symmetry/asymmetry, dynamic difficulty adjustment DDA, transitive/intransitive balance, nerf/buff, dominant strategy elimination, playtesting-driven tuning), (g) narrative & quest design (ludonarrative dissonance/harmony, environmental & systemic storytelling, branching vs linear, Amy Hennig character-driven, quest structure), (h) player-centric iterative process (Tracy Fullerton 'Game Design Workshop' playcentric design, paper prototyping, vertical slice, playtesting protocol 'watch don't talk / you are not your play
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。
引導 Claude 產出高品質的前端設計，避免 AI 生成的通用風格（AI slop）。包含字型、色彩、動態、背景的設計指引。
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。