「dj」の検索結果

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。

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。

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。

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。

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。

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。

Audio and video processing with ffmpeg. Use when: user asks to convert, trim, merge, compress, or transcode video or audio files; extract audio from video; create GIFs or animated WebP from video; add subtitles or watermarks to video; change video resolution, framerate, or codec; normalize audio loudness; extract frames from video; concatenate clips; create thumbnails from video; strip or add audio tracks; convert between audio formats (MP3, AAC, FLAC, Opus, WAV); adjust volume; apply video filters; stabilize shaky video; generate waveform or spectrum visualizations; probe media file metadata. Triggers on 'ffmpeg', 'video', 'audio', 'transcode', 'MP4', 'MKV', 'WebM', 'MP3', 'AAC', 'FLAC', 'Opus', 'WAV', 'GIF from video', 'extract audio', 'add subtitles', 'video to gif', 'compress video', 'trim video', 'merge videos', 'normalize audio', 'framerate', 'resolution', 'bitrate', 'codec', 'ffprobe', 'waveform', 'spectrogram'.

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。

Dùng khi viết hoặc sửa prompt tạo video/ảnh AI (Veo 3, Google Flow, Kling, Runway, Sora, Midjourney, Hailuo, Luma): từ vựng chuẩn về góc máy, chuyển động camera, ánh sáng, bố cục, phong cách, màu, cảm xúc công thức ghép prompt, và bài học thực chiến về lỗi model AI hay gặp. Use when writing or fixing AI video/image prompts — cinematic camera angles, camera movement, lighting, composition, style, color grading, mood, a prompt formula, and real-world lessons on common AI video model failures.

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。

Dùng khi viết prompt ảnh/video cảnh tiên hiệp, cổ phong, mỹ học phương Đông (thiên cung, biển mây, cung điện, kiếm khách) cho Midjourney/SD/Flux/Veo. Bản Lite.

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。

Dùng khi cần prompt ảnh thiết kế nhân vật (3 góc toàn thân + cận mặt trong 1 ảnh) cho Midjourney/SD/Flux để giữ nhân vật nhất quán khi làm video AI. Bản Lite.

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 work starts from `site-analysis.json` and the user wants page-group authoring, grouping adjustments, or page-group approval.

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。

Prospects companies across developer-focused tech verticals for developer marketing agency outreach. Use this skill whenever a user provides a vertical (e.g. AI Agentic, IAC, DevTools, Observability, DevOps, FinOps, AI/SDLC, AI Orchestration, or any other tech vertical) and wants a list of prospect companies to target. Also trigger when the user says "prospect for", "find companies in", "give me leads for", "build a prospect list", or provides a vertical name alongside funding stage and headcount filters. Always use this skill — never attempt prospecting without following this structured workflow. The skill finds exact-fit companies only (never adjacent), maps a real outreach signal and email pain point for each, sources every data point with a URL, and outputs a unified nine-column table: Company, URL, LinkedIn, Headcount, Signal, Signal Sources, Geography, Pain Point, Pain Point Sources.

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。

Rewrite AI-generated text to sound natural, remove AI tells, and adjust tone. Use when user asks to make text less robotic, more natural, or humanize AI output. Covers tone matrix, filler words, sentence rhythm, and anti-AI-slop patterns.

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 reviewing Python changes - Django, Flask and FastAPI handlers, subprocess, SQL, Jinja2, format strings, and data/ML code that loads pickles, models, notebooks or remote model 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。

Use after the targeted cases pass - choosing the adjacent behaviour this change can break from the PR's files and the component's links, and the per-repository smoke set

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 user's technical level from first messages. Adjust all output language accordingly.

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。

Classify request as small/medium/large. Adjust workflow depth accordingly.

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。

Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM message receive, reactions, chat member changes, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marker contract — designed for AI agents running as subprocesses.

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。

The end-to-end procedure for one trade on the HyperGrok desk - from an idea to a reviewed, journaled result - with the ticket format, who owns each stage, and what "done" looks like. Use whenever the user wants to open, adjust or close a position, or whenever any Bot is about to touch the exchange write path.

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。

Daily triage accuracy calibration — use during scheduled calibration runs to verify triage classification accuracy against few-shot examples and adjust confidence thresholds

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 local-first note vault retrieval for Obsidian, markdown notebooks, and NotebookLM-adjacent exports. Use when packaging notes into LLM-ready context.

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。

Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full GDD authoring when a system GDD already exists or the change is too small to warrant one. Produces a Quick Design Spec that embeds directly into story files.

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。

Map a complex topic by placing factors on hexagonal tiles where adjacency signals a claimed relationship. Use when students need to surface hidden connections in a system before analysis or action.

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 create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets. Also use when the user mentions 'AI image generation,' 'generate an image,' 'create a graphic,' 'product mockup,' 'hero image,' 'social media graphic,' 'banner image,' 'cover photo,' 'profile banner,' 'listing screenshot,' 'Flux,' 'Flux Kontext,' 'Midjourney,' 'DALL-E,' 'GPT Image,' 'ChatGPT Images,' 'Ideogram,' 'Gemini image,' 'Nano Banana,' 'Recraft,' 'Stable Diffusion,' 'Canva,' 'Figma,' 'image optimization,' 'compress images,' 'WebP,' or 'OG image.' Use this for general-purpose marketing image creation and optimization. For paid ad image creative and platform-specific ad specs, see ad-creative. For video production, see 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。