Data Analysis AI Skills

GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering,…

Builds and audits LLM pretraining corpora: extraction, filtering, dedup, decontamination, data mixing, synthetic data. Use when curating or ablating a pretraining data pipeline.

Use when: 需要与技术团队对接技术方案、评估技术可行性、制定技术架构、评估第三方服务 Do NOT use when: 技术方案已由技术团队确定、仅需功能描述无需技术评估

Run full computational-pathology workflows with PathML — whole-slide-image (WSI) analysis across 160+ slide formats, multiplexed immunofluorescence (CODEX, Vectra, MERFISH), nucleus…

Audit the sales side of a HubSpot portal: pipeline configuration, deal data quality, stale and past-due deals, ownership and handoff gaps, and overdue follow-up. Read-only. Use when the forecast is…

Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture…

Implement ESG (Environmental, Social, Governance) framework and multi-stakeholder balance for modern enterprises. Use when managing a modern enterprise, seeking investment, developing sustainable…

Cold email outreach via Instantly.ai API. Upload leads from business_leads table to campaigns, manage templates, track opens/replies/bounces, sync replies back to DB. Trigger when asked to send cold…

Drupal migration API — D7-to-D11 upgrades, CSV imports, JSON API imports, and custom source/process/destination plugins.

Complete toolkit for programmatic video creation with Remotion + React. Covers animations, timing, rendering (CLI/Node.js/Lambda/Cloud Run), captions, 3D, charts, text effects, transitions, and media…

Guides agents through publishing data products for internal or external consumers. Use when sharing tables, files, extracts, APIs, or reverse-ETL-ready outputs that require stable contracts,…

Decide what must be true of a dataset and where that assertion belongs — freshness against event time, volume floors and bands, distribution and referential checks, source reconciliation, and whether…

将宏观经济数据解读为结构清晰、可直接复用的研究周报式分析，支持CPI、PPI、PMI、GDP、社融等指标解读。Invoke when user asks about macroeconomic data interpretation, economic trends, or data analysis.

Autonomously optimize an existing skill's output quality by running it repeatedly, scoring against binary evals, mutating the prompt, and keeping improvements. Started only by the user, because it…

已有 successful S-Learner 或 T-Learner modeling_result_path 后，用于生成、确认并执行有边界的 LightGBM learner 调参 study。不要用于首次训练、多模型比较、最终报告或模型采用决策。

Power Platform observability, telemetry, and monitoring. Use when: Application Insights, App Insights, monitoring, telemetry, observability, alerting, diagnostics, Monitor tool, tracing, plugin…

Audit the visual quality of a UI against established visual-design principles — hierarchy, emphasis, contrast, spacing, alignment, grouping, consistency, and depth. Produces a severity-rated issue…

Experimental DryUI compact evidence fixture skill for image-to-app layout tests. Use when testing stage 1 page classification, stage 2 concise DryUI implementation, and stage 3 build/visual repair.

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

Builds and audits reproducible NeuroKit2 research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Use when code…

当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要：打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件（例如添加列、计算公式、格式化、制图、清理混乱数据）；从头创建新的电子表格或从其他数据源创建；或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及（如"我下载目录里的…

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited…

Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or…

Use when testing the empty rss golden build

Search Inbox Zero mail, read threads, create mailbox drafts, and manage automation rules through a remote MCP server. Use when the user wants ChatGPT, Claude, or Cursor to work with their Gmail or…

Use when working with Lightdash YAML files, dbt models with Lightdash metadata, the lightdash CLI (deploy, upload, download, preview, lint, warehouse-catalog, sql, set-warehouse, apps…

Update SenseNova Skills (the sn-* bundle) inside an OpenClaw or hermes-agent install. ALWAYS use this skill when the user says any of: "update SenseNova skills", "update SN skills", "更新 sensenova…

End-to-end R data analysis workflow from exploration through regression to publication-ready tables and figures

Use when an app already runs Prisma and needs TanStack AI chat persistence — writes a chat-persistence.ts into the app against its existing PrismaClient and schema.prisma. Covers the four models,…

Quality control for pooled CRISPR screens. Covers library representation, read distribution, replicate correlation, and essential gene recovery. Use when assessing screen quality before hit calling or…

Unified risk engine with VaR, stress testing, volatility regimes, and automated controls

Strategic context reconnaissance — read existing roadmaps, OKRs, competitive docs, and briefs to establish context before planning. Use when asked to "understand our strategy", "what's the current…

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

小红书账号整体诊断与竞品对标。对一个或多个小红书账号做量化体检——定位清晰度、内容垂直度、封面统一性、标题钩子率、更新节奏、互动率、爆款率、粉丝转化效率八个维度打分，定位卡点并给出可执行改动。当用户说"账号诊断""帮我看看我的号""我的号没起色/不涨粉/流量下滑""主页体检""账号定位有问题吗""竞品账号分析""对标账号拆解""这个博主为什么能起来""帮我和竞品比一比"，或直接贴出小红书主页链接/…

Capture a Genie Sim RT Engine episode while a scene runs — record the canonical ROS 2 topics (`/joint_states`, `/joint_command`, `/tf`, `/clock`, cameras) with `ros2 bag`, or pair the recording with…

16S/18S rRNA amplicon preprocessing — from raw paired-end FASTQ files through N removal and primer trimming, producing outputs ready for DADA2 quality filtering and denoising. Deliberately stops…

Plan which skills are needed to fulfill user requirements. Use when the user wants to design an agent workflow, plan skill composition, or determine what skills are needed for a task. Input includes…

Summarize modeling experiment evidence, compare the approved main method with a usable baseline, surface fallback triggers, and produce a decision-point or final report without creating routine…

Generic PowerPoint authoring skill for A-share investment analysis and pitch decks. Creates professional 路演PPT / 投资分析PPT for any A-share company using live data from iFind MCP (Tier-1) and AkShare MCP…

This tool uses the label-tree function from HyPhy to annotate a phylogenetic tree. It allows users to select a subset of leaves using either a regular expression or a list of sequence names, and then…

Install and configure OpenTelemetry for Codex-oriented workflows, including OTLP exporter setup, collector endpoint wiring, and validation that traces/logs/metrics are emitted and stored under…

AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance. Use when checking AWS alarms, analyzing VPC flow logs, investigating network latency, or…

OPS on-demand: This skill should be used when the user asks to "fleet dashboard", "CLIProxy sessions"…

Estimate and communicate business impact of insights. Use when sizing opportunities discovered in analysis, calculating ROI of recommended actions, or prioritizing initiatives by potential impact.

Use when a business or operational metric needs definition and source provenance checked, freshness and comparability validated, or an anomaly reviewed against a baseline and target.

PHP Web 路由到 Sink 的多层数据流追踪工具。根据用户指定路由，追踪从 handler 到最终敏感操作点，输出层级证据、参数变量追踪、可控性分析（不做漏洞结论）。

Train ML models on Databricks. Use for: classification/regression/deep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod/@challenger aliases, batch scoring (spark_udf for plain…

Optimize crew composition using CWICR labor norms. Balance productivity, cost, and skill requirements for construction crews.

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

Generates a comprehensive client health overview across all accounts. Reads CRM data, support tickets, usage metrics, billing, and engagement logs. Calculates health scores, trend direction, and RAG…