Use when writing a finished intelligence product, the user asks for a flash-report / threat-assessment / briefing / FINTEL template, or wants the BLUF + active-voice + clear-sourcing conventions. Covers all product types.
中文简介正在准备中。当前显示原文说明。
不属于以上分类的技能(1.4万 个)
Use when writing a finished intelligence product, the user asks for a flash-report / threat-assessment / briefing / FINTEL template, or wants the BLUF + active-voice + clear-sourcing conventions. Covers all product types.
中文简介正在准备中。当前显示原文说明。
Use when the user asks "what is coming next?", wants strategic forecasting, or is hunting weak signals of emerging threats before they materialise. Covers signal identification, trend analysis, and scenario development.
中文简介正在准备中。当前显示原文说明。
Use when challenging a prevailing analytical judgment, the user asks "what is the opposing case?" / "argue the other side" / "play devil's advocate", or wants an assessment stress-tested before release. Takes the team's own lead judgment and builds the strongest case that it is wrong. A contrarian technique. It does not model what an adversary would do next, which is Red Team Analysis. Formerly /red-team-analysis.
中文简介正在准备中。当前显示原文说明。
Use when the user asks about North Korean state-sponsored cyber operations or specific DPRK actors (Lazarus, APT38, BlueNoroff, Andariel, Kimsuky, etc.), revenue-generation campaigns, IT-worker schemes, or DPRK targeting of cryptocurrency / supply chain. Self-updating knowledge cell.
中文简介正在准备中。当前显示原文说明。
Use when the user asks about infostealer families (LummaC2, RedLine, Vidar, Stealc, Raccoon, Rhadamanthys, etc.), log marketplaces (Russian Market, Genesis successors, BidenCash, Hudson Rock corpus), or stealer-driven incidents and credential exposure. Self-updating knowledge cell.
中文简介正在准备中。当前显示原文说明。
Use when phrasing a forward-looking statement, the user asks "how likely is X?" / "what's the likelihood?", or the tradecraft pipeline applies a probability yardstick to a finished product. Standardised likelihood language across all products.
中文简介正在准备中。当前显示原文说明。
Use when you need to submit a URL for live scanning via URLScan.io and retrieve results, or search existing scans for a domain. Returns verdict, final URL after redirects, resolved IP, contacted domains/IPs, and screenshot URL. Commonly invoked by /url-investigation and /domain-investigation.
中文简介正在准备中。当前显示原文说明。
Use when a report or article needs to be split into individual claims before it is graded, cited or used as evidence — the user asks "what does this report actually claim?", "split this into claims", "separate the facts from the judgements", or another skill needs a claim list. Turns one document into five to twelve atomic claims, each typed (observation, attribution, assessment, actor claim, victim disclosure) and anchored to the verbatim sentence it rests on, so every extraction can be checked against the source. Preserves the source's own hedging. Does not grade. Invoked by /quality-of-information-check; its output feeds /ach, /key-assumptions-check, /intelligence-writing, /writing-assessments and /threat-actor-profiling.
中文简介正在准备中。当前显示原文说明。
当用户纠结文案该写长还是写短时调用。适用于:规划广告/邮件/着陆页篇幅、 别人说"没人看长文案"时需要决策依据、产品复杂不知道该写多少。 核心信号:用户在问"文案写多长合适""会不会太长了"。 不适用于:已有明确篇幅要求、纯社交媒体短文案。
中文简介正在准备中。当前显示原文说明。
当用户需要按公式化方法构造广告标题,或想把产品信息转化为有力标题时调用。 适用于:从零开始写标题、把产品卖点转化为标题、需要快速产出多个标题方案。 不适用于:评估已有标题(用headline-four-functions)、分析竞品(用headline-eight-types)。
中文简介正在准备中。当前显示原文说明。
当用户在思考"文案应该说什么才能打动人"的根本方法论问题,或纠结于 "是创造需求还是满足需求"时调用。适用于:理解文案与消费者心理的关系、 制定文案策略方向、为新产品确定营销切入点。 不适用于:具体文案写作执行、标题创作(用headline相关skills)。
中文简介正在准备中。当前显示原文说明。
当用户需要让广告文案中的产品承诺更有说服力、更有"证据感"时调用。 适用于:写出产品好处但客户不信、需要在文案中加入"证明"元素、 做竞品对比文案。核心信号:用户在问"怎么让客户相信""怎么证明我的产品好"。 不适用于:纯品牌形象传播(不需要证明)、虚假宣传(造假不是伪逻辑)。
中文简介正在准备中。当前显示原文说明。
当用户需要为广告/邮件/着陆页创作标题,且需要选择标题的写法风格时调用。 适用于:标题创作卡壳、想尝试不同风格的标题、分析竞品标题属于哪种类型。 不适用于:标题评估(用headline-four-functions)、正文写作。
中文简介正在准备中。当前显示原文说明。
当用户需要将产品/服务/个人的特点转化为对受众有吸引力的利益点时调用。 适用于:写产品文案不知从何下笔、准备销售话术、撰写简历或自我介绍、 做产品定位思考。核心信号:用户在列举产品特点但不清楚"别人为什么要在乎"。 不适用于:纯技术文档、产品规格说明(此时特色本身就是目的)。
中文简介正在准备中。当前显示原文说明。
当用户需要找出产品/服务的独特竞争优势来写定位文案或广告主轴时调用。 适用于:产品同质化严重不知怎么差异化、新产品定位、重新审视现有产品的竞争优势。 核心信号:用户在问"我的产品和别人有什么不同""怎么让客户选我而不是对手"。 不适用于:已有明确USP只需要执行、不需要竞争分析的产品(如垄断市场)。
中文简介正在准备中。当前显示原文说明。
当用户需要撰写或评估广告标题/邮件主题/页面首屏文案时调用。 适用于:写产品标题但不知如何组织、评估现有标题是否有效、 设计直邮信封文案或网站首屏。核心判断:用户正在处理"第一印象"文案。 不适用于:正文写作、视觉设计、品牌策略讨论。
中文简介正在准备中。当前显示原文说明。
Use when a user wants to build an application with ClickHouse, set up a local ClickHouse development environment, install ClickHouse, create a local server, create tables, or start developing with ClickHouse. Covers the full flow from zero to a working local ClickHouse setup.
中文简介正在准备中。当前显示原文说明。
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 31 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
中文简介正在准备中。当前显示原文说明。
知識型 IG 輪播圖卡的獨立審核員(Joker)——預設有罪推定、禁止 LGTM。對一套輪播圖卡+文案,按「封面/結構/擴散/CTA/品牌」五類硬規則逐條 PASS/FAIL,指到卡給可照做的改法,並算社群擴散體質分。是 Social Post Producer 迴圈裡的「審」(寫審分離)。觸發詞:驗收這套輪播、這組圖卡會不會擴散、red team 這個 carousel、carousel joker、圖卡審核、這套 IG 圖文夠不夠好。立場是找碴不是稱讚。
中文简介正在准备中。当前显示原文说明。
迷因知識輪播的獨立審核員——用「幽默感」的可二元判定要素(不協調-解消/良性冒犯/切身共鳴/誇張反差/自嘲/三的法則/秒懂)+迷因 Hook+版權安全,對一套迷因圖卡逐條 PASS/FAIL、指到卡給改法。預設有罪推定、禁 LGTM。是迷因輪播 loop 的「審」。觸發:這張夠不夠好笑、驗收迷因圖、meme joker、這個梗會不會冷、迷因輪播審核。
中文简介正在准备中。当前显示原文说明。
Optimize resumes for software engineering, PM, and technical roles
中文简介正在准备中。当前显示原文说明。
Determines the candidate's primary role identity before any JD analysis. Classifies into role families, selects core tech identity, ranks projects by role relevance, and outputs a Candidate Position Brief consumed by all downstream stages. This is Phase -1 of the pipeline.
中文简介正在准备中。当前显示原文说明。
Write concise, evidence-backed resume bullets using concrete implementation detail and defensible outcomes. Metrics are optional and require provenance.
中文简介正在准备中。当前显示原文说明。
Track different resume versions, maintain master resume, manage tailored versions
中文简介正在准备中。当前显示原文说明。