Data & Analytics

Use this skill when building data pipelines, ETL/ELT workflows, or data transformation layers. Triggers on Airflow DAG design, dbt model creation, Spark job optimization, streaming vs batch architecture decisions, data ingestion, data quality checks, pipeline orchestration, incremental loads, CDC (change data capture), schema evolution, and data warehouse modeling. Acts as a senior data engineer advisor for building reliable, scalable data infrastructure.

Use this skill when building computer vision applications, implementing image classification, object detection, or segmentation pipelines. Triggers on image classification, object detection, YOLO, semantic segmentation, image preprocessing, data augmentation, transfer learning, CNN architectures, vision transformers, and any task requiring visual recognition or image analysis.

Use this skill when building dbt models, designing semantic layers, defining metrics, creating self-serve analytics, or structuring a data warehouse for analyst consumption. Triggers on dbt project setup, model layering (staging, intermediate, marts), ref() and source() usage, YAML schema definitions, metrics definitions, semantic layer configuration, dimensional modeling, slowly changing dimensions, data testing, and any task requiring analytics engineering best practices.

Guided, interactive exploration of statistical data via SDMX providers (Eurostat, OECD, ECB, World Bank, ISTAT, and others) using the opensdmx CLI. Use this skill whenever the user asks a question about statistics that could be answered with SDMX data: demographics, economy, employment, births, deaths, population, prices, trade, health, agriculture, or any other topic. Also use it when the user mentions a specific dataflow ID they want to explore. The skill guides the user step by step: disco...

Use when the user asks to "read back" a paid campaign change, "did this ad change work", or "compare ROAS/CPA before and after"; reads ROAS/CPA against a control over a fixed readback window and returns a Promote / Keep-testing / Rollback / Unproven readback decision with the math delegated to roi-calculator. Not for RQS scoring or veto adjudication — use ad-account-auditor; not for the ROI ratio math — use roi-calculator; not for cross-channel rollups — use performance-analyzer. 付费广告复盘/ROAS回...

Use when the user asks to "is my ad fatiguing", "why is CTR dropping at scale", or "should I rotate creative / widen the audience"; reads frequency, CTR and CVR decay against an early-flight baseline and returns Rotate-creative / Widen-audience / Hold triggers with a per-ad-set fatigue read. Not for building the replacement creative — use ad-creative-builder; not for the RQS score or vetoes — use ad-account-auditor. 广告疲劳检测/频次管理/换素材还是扩人群

Use when the user asks to "check pacing", "am I over/under-spending", "is this campaign on track to hit budget", or "why did spend spike/stall mid-flight"; returns a spend-vs-target-curve read, learning-phase status, an over/under-delivery call, and a reallocation trigger. Not for initial budget allocation — use budget-optimizer; not for choosing the bid strategy — use bid-strategy-planner; not for the RQS gate — use ad-account-auditor. 付费广告预算节奏监控/跑量过快过慢/在途配速

查询监控 API 供应商/服务的额度、余额、消耗情况。支持官方供应商(Gemini/xAI/ZAI/Minimax/OpenRouter等)、中转站(AIXN/Provider-A等)、订阅服务(Brave/Tavily/Serper)。触发词：查额度、查余额、API用量、供应商额度、quota、balance、usage、billing。

Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive present...

Plan and report statistical rigor for ML experiment results. Use when significance testing, effect size reporting, confidence intervals, seed variance analysis, or multiple-comparison corrections are needed before including results in a paper or rebuttal.

Build paper-facing tables and figures from CSV experiment outputs. Use to inventory evidence, aggregate seeds, select result slices, generate LaTeX assets, and record provenance.

Mine existing results for paper evidence gaps before new compute. Use when claims lack support, CSVs may already contain evidence, or tables/figures can be derived.

Use when training has engineering failures — NaN/gradient issues, GPU OOM, slow data loading, wrong metrics, reproducibility failures. Not for checking job queue/status (use run-status-monitor). Not for valid-but-surprising scientific results (use result-diagnosis). Not for confound or claim audit before writing (use research-results-auditor).

Plan and write appendix or supplementary material for ML papers. Use when the appendix needs to be structured, main-paper claim boundaries need to be enforced, NeurIPS/ICLR reproducibility checklists need sections, or cross-references between paper and supplement need to be aligned.

日本語または英語の意図から、短い英語名の候補を作り、kebab-case、snake_case、camelCase、PascalCase、dot.case、path/case、CONSTANT_CASE など change-case 由来の形式へ整形する。ファイル、スラッグ、メモ、スクリプト、文書、短い技術成果物の命名に使う。ブランド名、商品名、長いタイトル、一般的な翻訳、命名形式の制約が関係しない用途には使わない。

Expert in automating Excel workflows using Node.js (ExcelJS, SheetJS) and Python (pandas, openpyxl).

Expert in observing, benchmarking, and optimizing AI agents. Specializes in token usage tracking, latency analysis, and quality evaluation metrics. Use when optimizing agent costs, measuring performance, or implementing evals. Triggers include "agent performance", "token usage", "latency optimization", "eval", "agent metrics", "cost optimization", "agent benchmarking".

Expert in business intelligence, SQL, data visualization, and translating data into actionable business insights.

Expert in high-performance CSV processing, parsing, and data cleaning using Python, DuckDB, and command-line tools. Use when working with CSV files, cleaning data, transforming datasets, or processing large tabular data files.

对问卷原始数据进行全流程自动化分析，包括基础统计（频率分布 + 人口学概览）、 交叉分析（不同人群差异对比）和文本分析（开放题主题归纳）。 支持两种数据来源：用户提供本地 CSV/Excel 文件，或通过问卷 ID/名称从问卷系统直接下载（支持清洗）后分析。 输出 Markdown 摘要报告 + Word 分析报告（默认），支持转换为 Excel/TXT 格式。 当用户要求分析问卷数据、生成问卷调研报告、对比不同人群差异、 分析开放题文本内容时触发。即使用户没有明确说"问卷"，只要涉及 调研数据分析、用户反馈分析、满意度分析、NPS 分析等场景也应触发此 skill。 当用户说"下载并分析问卷"、"清洗问卷然后出报告"、"帮我下载问卷90450"、 "下载国内问卷数据"、"从问卷系统拉数据"等涉及下载+分析的场景时，也应触发。 确保在用户说"帮我分析这份问卷"、"分析一下不同性别的差异"、 "请结合文本题分析"、"下载问卷90450然后分析"、"清洗并导出问卷"等类似表达时使用。

Analyze CSV files, generate summary statistics, and create visualizations using Python and pandas. Use when the user uploads, attaches, or references a CSV file, asks to summarize or analyze tabular data, requests insights from CSV data, or wants to understand data structure and quality.

Press release writing in AP style with inverted pyramid structure. Covers formatting, datelines, quotes, boilerplates, and fact-checking. Use for: product launches, funding announcements, partnerships, company news, events. Triggers: press release, pr writing, media release, news release, announcement, product launch announcement, funding announcement, company news, media advisory, ap style, press statement, news wire

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D mo...

Press release writing in AP style with inverted pyramid structure. Covers formatting, datelines, quotes, boilerplates, and fact-checking. Use for: product launches, funding announcements, partnerships, company news, events. Triggers: press release, pr writing, media release, news release, announcement, product launch announcement, funding announcement, company news, media advisory, ap style, press statement, news wire