调研与学习技能

当学生说"我想做个项目但不知道做什么"、"这个想法可行吗"、"帮我想想能做点什么"、"我有个点子想聊聊"、"这个课题值不值得做"时使用。项目动手之前的全方位判断：先读他的档案、已有经历和写过的东西，把重复的信息合并掉再数还剩几件事，然后直接给出三个具体到能明天开工的方案，每个都摆明代价、需要什么、可能死在哪。定方案之后落成长期事项加前三个里程碑，并存一份构思稿。不吹可行性，不替他选，不为了申请而编项目。

中文简介正在准备中。当前显示原文说明。

当学生说"我参加过一些活动但没整理过"、"帮我把经历录进去"、"我的活动档案是空的"时使用。让学生一口气把记得的活动说出来，直接把这段话拆成结构化的长期事项（角色、组织、起止时间、做了什么、结果、级别），说不清的字段留空标"待补"而不是编，再用一张选择题卡把级别判定与是否重复这类关键项一次问完，然后提案入库。只记录学生真正说出口的内容，级别按事实判定，绝不往高了写。

中文简介正在准备中。当前显示原文说明。

当学生说"下个月要考 IB 大考不知道怎么安排"、"这几个 DDL 撞在一起了"、"帮我排一下复习计划"时使用。从一个或多个截止日倒推出到期之前的可执行安排：先读清楚已有事项，直接按合理假设排出第一版有交付物的节点，同时把只有本人知道的岔路口（每天多少时间、哪些天动不了）一次问完，拿到答案后修订并提案进日程。不排满、不编造截止日、不给"每天学两小时"这种无法验收的任务。

中文简介正在准备中。当前显示原文说明。

当学生问"招生官会怎么看我的档案"、"我的背景还差什么"、"帮我评估一下现在的申请竞争力"时使用。以顶尖大学招生官的视角通读学生的档案、长期活动与已写下的反思，不问任何前置问题直接产出一份指名道姓的坦诚点评：这份材料的亮点、招生官真实的解读方式、明显的短板与空白、以及接下来最值得做的一到两件事。只读不写，不修改学生的任何数据，也不代写任何申请材料。

中文简介正在准备中。当前显示原文说明。

当使用者说“帮我整理建模论文结构”“这一段该放哪”“论文逻辑很乱”“怎么从模型讲到结论”“摘要和正文对不上”时使用。基于学生已有题面、模型、运行、图表和草稿建立主张—证据图，再给按问题驱动的章节蓝图、段落职责、图表计划与页数预算；保证摘要数字可追溯、结果与验证分开、结论强度不越过证据，不代写整篇竞赛论文，不用流畅叙事掩盖缺失分析。

中文简介正在准备中。当前显示原文说明。

当使用者说“这篇建模论文还能怎么提升”“按评分表排修改优先级”“时间不够先改什么”“给我一个论文改进清单”“要不要再加一个高级模型”时使用。基于现有草稿、模型工作包、批判 findings、评分规则和真实剩余资源建立可定位的 gap register，再按结论影响、评分关联、工作量、依赖与失败风险排序；每项写所需数据/代码/作者决定、验证与验收条件，先给一个最小可行修订，不用装饰复杂度替代证据，不编创新、实验或评委偏好。

中文简介正在准备中。当前显示原文说明。

当使用者说“整理建模论文 LaTeX”“修编译错误和引用”“统一公式、表格和图注”“按比赛模板排版”“检查交叉引用与缺图”时使用。先冻结内容并做基线编译，再在不改变数学含义、数字、引用或作者措辞的前提下修结构、符号格式、标签、表图、文献与版面；运行静态检查和实际编译，记录引擎、命令、警告与输出。只格式化和诊断，不补造公式、结果、来源或论文内容。

中文简介正在准备中。当前显示原文说明。

当使用者说“这题该用什么模型”“A 和 B 哪个更合适”“要不要上机器学习”“我的模型选得对吗”时使用。基于已拆清的目标、变量、数据与验证条件，区分模型家族、算法和求解器，建立简单基线，比较至少两个有意义的候选，并给出条件式推荐与最低成本判别测试；不凭流行度拍板、不编造性能、不替学生隐藏最终选择。

中文简介正在准备中。当前显示原文说明。

Investigate why a defect or insufficiency was introduced and accepted by tracing code, pull requests, task context, and accessible development sessions. Use for second-order learning after a fix, blameless root-cause analysis, or preventing a recurring class of engineering mistakes.

中文简介正在准备中。当前显示原文说明。

Facilitate structured post-incident reviews to identify root causes, document what worked and failed, and produce actionable recommendations to improve future incident response.

中文简介正在准备中。当前显示原文说明。

Use the Malpedia platform and API to research malware family relationships, track variant evolution, link families to threat actors, and integrate YARA rules for detection across malware lineages.

中文简介正在准备中。当前显示原文说明。

Run the full implement-review-fix loop using implementer and reviewer personas. Supports effort-based multi-reviewer scaling (1-5 reviewers) with automatic specialization selection. Includes memory-based feedback loop that learns from past review patterns. Loops until all reviewers find 0 issues of any severity.

中文简介正在准备中。当前显示原文说明。

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

中文简介正在准备中。当前显示原文说明。

Deep multi-source research synthesis — web, academic, patent, and internal KB cross-referencing

中文简介正在准备中。当前显示原文说明。

Automatically persist useful context — research, decisions, learnings, templates — to workspace files so knowledge survives across conversations.

中文简介正在准备中。当前显示原文说明。

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the findings it emitted, and assessing a scout's health and performance over time (cadence, success rate, emit rate, signal-to-noise). Read-only and exploratory — to write or tune a scout, use `authoring-signals-scouts` instead. Trigger on "what are my scouts doing", "how is my <x> scout performing", "show me recent scout runs", "why did this scout find/emit nothing", "what has the fleet learned", "explore scout run <id>", "is my scout working".

中文简介正在准备中。当前显示原文说明。

Meta-analysis / evidence synthesis — pool effect sizes across studies (odds ratios, risk ratios, hazard ratios, mean differences, correlations, GWAS betas) with fixed- or random-effects models, quantify heterogeneity (Q, I², τ²), and build a forest plot. Use when you have results from MULTIPLE studies and need a single pooled estimate, or to synthesize evidence from a systematic review / multiple GWAS / replicated experiments. Handles the error-prone effect-size + standard-error preparation (converting OR/HR/CI, two-group means±SD, proportions, and correlations into the (effect, SE) the pooling step needs).

中文简介正在准备中。当前显示原文说明。

Deep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports. Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations workflows.

中文简介正在准备中。当前显示原文说明。

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

中文简介正在准备中。当前显示原文说明。

Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.

中文简介正在准备中。当前显示原文说明。

Synthesize scientific evidence into a claim-to-source matrix, distinguish primary evidence from interpretation, assess disagreement and study limitations, and produce a calibrated research summary.

中文简介正在准备中。当前显示原文说明。

End-to-end observational epidemiology analysis — from research question (PECO Population/Exposure/Comparator/Outcome) to publication-ready statistical report. Covers cohort/case-control/cross-sectional design, regression with confounders, propensity scoring, sensitivity analysis. Writes Python code for every step. Use for epidemiology study analysis, NHANES/UK-Biobank-style analyses.

中文简介正在准备中。当前显示原文说明。

Mendelian randomization (MR) causal inference — does an exposure, risk factor, or biomarker CAUSALLY affect a disease/outcome, using genetic variants as instrumental variables (IEU OpenGWAS / EpiGraphDB MR-EvE). Use this whenever the user asks if X causes Y, whether an observational association is actually causal or just correlation, if a biomarker/trait is a causal risk factor, wants to triangulate epidemiology against genetic evidence, or mentions Mendelian randomization, instrumental-variable analysis, two-sample MR, or genetic causal evidence — even if they never say "MR" (e.g. "is LDL cholesterol actually causal for heart disease?", "does BMI cause type 2 diabetes or just correlate?", "is CRP a causal driver of stroke?"). Covers trait-label resolution, MR effect direction/magnitude, instrument quality (MOE score), method agreement (IVW vs MR-Egger vs weighted median), bidirectional MR for reverse causation, and distinguishing causation from genetic correlation. Not for plain GWAS association lookups (use the GWAS skills) or fitting your own instruments from raw summary statistics.

中文简介正在准备中。当前显示原文说明。

Plan and execute reproducible computational research with explicit inputs, environments, provenance, deterministic steps, validation, and workspace outputs. Use for analyses that must be rerun, audited, or handed to another researcher.

中文简介正在准备中。当前显示原文说明。