Data & Analytics

当用户需要做抖音竞品研究、抖音竞品分析、同赛道观察、内容角度对比、内容策略对比或品牌内容调研时使用。面向品牌、MCN、内容运营和创作者。

当用户需要做抖音评论分析、抖音评论洞察、抖音用户反馈分析、抖音需求挖掘、痛点总结、购买顾虑整理、FAQ 提炼、口碑分析、评论回复观察或内容讨论复盘时使用。基于用户提供的抖音作品链接或内容 ID 下的评论结果，面向内容运营、产品调研、品牌调研和创作者。

当用户需要做抖音账号诊断、抖音账号分析、抖音账号复盘、账号体检、播放低或不推流排查、近期作品表现整理和内容优化方向判断时使用。基于用户提供的抖音主页链接、分享文案或 sec_user_id，整理账号资料和近 30 天作品结果，输出可执行的账号分析报告。

当用户需要做 B站视频分析、爆款拆解、选题参考、竞品视频对比、趋势判断或素材整理时使用；需要时也可补充专栏结果。面向内容运营、品牌调研和创作者。

当用户需要做 B站评论分析、B站评论洞察、B站用户反馈分析、B站需求挖掘、痛点总结、购买顾虑整理、FAQ 提炼、口碑分析、评论回复观察或内容讨论复盘时使用。基于用户提供的 B站视频、专栏、动态链接或对应内容 ID 下的评论结果，面向内容运营、产品调研、品牌调研和创作者。

Review open GitHub issues for powerbi-autopilot (render bugs, design feedback, pilot and language requests), log them in docs/feedback-log.md, reproduce render bugs with quickstart, map design feedback to the review rubric, and propose fixes. Use when the user asks to check feedback, triage issues, or plan the next improvement.

Start a new Power BI report in this repo from a pre-built pilot. Asks the purpose (dashboard, measure table, metric-check matrix, deep dive), the design theme (seven presets: navy, paper, midnight, aurora, coast, ledger, contrast) and the language (English by default), copies the matching pilot spec, remaps only the missing fields, then generates and validates the PBIP. Use whenever the user asks for a new report, dashboard or table.

微信本地数据识别与分析（session-digger 子技能）。索引、搜索、分析、摘要、画像、关系网络、决策复盘、朋友圈、收藏夹——对已解密的微信数据库做全史检索与跨会话成文。 数据接入三来源：已解密 vault（离线库）/ wx-cli（在线查询）/ 导出文件，统一消息 schema。 触发：微信、群聊、聊天记录、群聊精华、群聊摘要、日报、周报、导出聊天、 联系人、会话列表、搜索聊天、谁说了算、关系网络、 情绪变化、群友画像、客户跟进、朋友圈、收藏夹、数据实验室、发言排行、词云、 关系分析、双人互动、wechat-digger、帮我看看这个群、这个群在聊什么、从上次继续、毒舌版摘要、 语音导出、转账红包、好友申请、图片还原、解密图片、extras。 DO NOT use when: - 写公众号/排版 HTML → wechat-humon-blogger / dbs-wechat-html - 微信读书（书/划线）→ taxue-weread - 仅操作剪映 → jianying-editor

Use when auditing, extracting, pruning, or writing Claude Code memory files. Triggers: "memory management", "记忆管理", "记忆格式", "MEMORY.md", "记忆文件", "how to save memories", "how to organize memories", "记忆归档". Covers memory file format, MEMORY.md index conventions, staleness scoring, claim extraction heuristics, destination routing, mutation rules, archive conventions, and auto-generated memory from `remember.py`.

[已整合至 env-master] 跨 AI 编码环境自检诊断工具箱。 核心思路：充分运用每个环境的原生诊断命令 + 薄脚本补盲区 + 模型推理综合。 推荐使用 /env-master 替代（更全面，含量化评分和统一入口）。 对未知环境使用通用降级探测。 触发：env-doctor、环境自检、环境诊断、体检、环境冲突、配置检查、 doctor、自检、环境健康、env health、infrastructure check、环境巡检

会话历史分析入口。回忆、挖掘、提炼、管理、分析、规则化、多源导入。 支持 Claude Code、Grok Build、Kimi Code、Codex、ZCode、WorkBuddy、Trae CN、 DIM、Reasonix 等多环境 + 通用对话导入。 触发：session-digger、回忆一下、查下历史、之前怎么做的、上次讨论过什么、 分析会话、挖掘 git 历史、管理记忆、之前那个、之前说的、上次那个、 之前讨论的、之前的版本、之前的方式、上次提到的、之前不是、 技能使用分析、技能洞察、哪些技能没用过、技能差距、优化 skill、 记不记得、之前看过、上次读的、之前写的、之前做的、导入对话、微信导入、 使用回顾、reflect、usage recap、用了多久、AI 使用习惯、使用报告、 token 用量、花了多少钱、模型消耗、缓存命中率

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Create visually rich PowerPoint (.pptx) presentations from academic papers, research notes, or any content the user wants in slide format. Uses PptxGenJS + LaTeX formula rendering. Always use this skill when the user wants PPT/PPTX output instead of Beamer/LaTeX slides. Trigger on: powerpoint, pptx, PPT, make a ppt, 做PPT, 做幻灯片, make slides (non-LaTeX), prepare a presentation (when context implies PPT), 做个报告, presentation slides, help me prepare a talk (when not Beamer), convert paper to slide...

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Use this skill for task coordination with WG. Triggers include "wg", task graphs, multi-step projects, tracking dependencies, coordinating agents, or when you see a .wg directory.

Create project plan using project-planner agent. No code writing - only

Tmux skill for running background tasks. Use this skill when: 1. Before any tasks that can potentially run for more than 2 minutes (e.g.: package install, many tests, model training) 2. Before any tasks that are expected to run indefinitely in background (e.g.: web servers, port forwarding) 3. Bash tool reports `timeout after 120000ms` 4. User request to run tasks in background

Skills to retrive weather forecast for Chinese locations

Ensure site/viewer/lib has correct symlinks to src/viewer/assets/lib