Data & Analytics

Data analysis, BI, visualization, datasets, statistics, and ML workflows

skills in category: 13,012
pages available: 543

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse data & analytics skills

Showing 2,017–2,040 of 13,012 skills

FinetuneAFine-tune an oh-my-mlip model on your own dataset from a foundation checkpoint. Triggers on requests to fine-tune, continue training, or adapt a model to custom data — "fine-tune MACE on my data", "continue training SevenNet", "train DeePMD with my extxyz frames" — even when "oh-my-mlip" or "finetune" is not named.dataVotes: 0GitHub stars: 3
DistillADistill any oh-my-mlip teacher MLIP into a CPU-deployable LAMMPS NN-MTP student via the onthefly-distill (GPL-2.0, orchestrated sibling repo) active-learning loop. Triggers on requests to distill, compress, or convert a foundation MLIP into a fast LAMMPS potential — "distill MACE into a LAMMPS student", "onthefly-distill", "NN-MTP student", "AL loop for a student potential", "shrink this teacher into something CPU-deployable" — even when "oh-my-mlip" or "distill" is not named.databashVotes: 0GitHub stars: 3
CatbenchARun the full-roster catbench adsorption benchmarking pipeline across oh-my-mlip models. Triggers on requests to benchmark, compare, or evaluate MLIPs on catalysis/adsorption tasks — including generic phrasing like "benchmark several machine-learning potentials on my adsorption dataset" — even when "oh-my-mlip" or "catbench" is not named. Do NOT trigger on literature-only comparison questions with no dataset/compute intent.dataVotes: 0GitHub stars: 3
Bdd AnswerAAnswer a "how do I …" question about the platform with a Gherkin scenario on @datagrok-libraries/bdd that is filmed into a how-to video (grok-bdd guide), so the answer is demonstrated, sent as a video plus numbered steps, and kept as a regression testdatagoshellVotes: 0GitHub stars: 74
Xinke Laile Analytics EnterpriseAAnalyze tenant-scoped lead trends, source performance, and push delivery through the Xinke Laile MCP service.datasqlperformanceVotes: 0GitHub stars: 45
Ae CliAUse ae-cli to query and manage data, analytics, metadata, tracking, knowledge bases, Agent resources, Engage, DataOps, Community, teams, and system administration in the configured ThinkingAI AE environment.datagoVotes: 0GitHub stars: 45
Skills DirectorySkills Directory 3 slots · $399/mo · one ad per page · sponsors can never buy grades.See placements
Tdengine RcaAUse when diagnosing industrial equipment faults, performance anomalies, alert events, or unexplained metric changes with TDengine data and public MCP tools.datapythonjavaVotes: 0GitHub stars: 45
Shopee Market IntelligenceA使用 Shopee MCP 分析站点、类目、商品、店铺、品牌、趋势和热搜词。适用于市场规模评估、类目选品、竞品研究、榜单分析、店铺/品牌诊断以及关键词趋势分析。datagoapiVotes: 0GitHub stars: 45
Jumper Kpi AnalysisA使用 Jumper MCP 只读查询和分析医院经营与门店人员的 KPI 数据。门店维度：有效金额、退款、成交、线索/客资/商机漏斗、企微客户数（CRM客户数）、渠道来源、趋势、同比环比、医院与渠道排名，也用于识别收入/利润/成本/净额等当前不支持的口径。支持通过人名、地区/城市匹配医院简称。人员维度：个人 KPI 目标、完成金额、完成率、缺口、达标情况、职级与 KPI 档级、按医院汇总的人员达标率，以及逐日进度（截至某日的月累计、当日新增业绩、每天的走势）。用于回答「某家门店上月业绩多少」「各门店渠道来源对比」「某院这个月新增多少企微客户」「本月环比上月」「某个顾问某月完成得怎么样」「某人某天做了多少」「某门店谁业绩最差」这类问题。不用于数据写入，也不用于非医院经营的问题。dataapiperformanceVotes: 0GitHub stars: 45
Twilio Lookup Phone IntelligenceBLook up phone number intelligence via Twilio Lookup v2 API. Covers number validation, line type detection (mobile/landline/VoIP), SIM swap detection, caller name, identity match, and SMS pumping risk scoring. Use this skill to validate numbers or assess fraud risk before sending messages or calls.datapythonnodeVotes: 0GitHub stars: 9
PolarsAHigh-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.datapythonrustVotes: 0GitHub stars: 9
HubspotAUse when working with HubSpot CRM records to search, summarize, create, update, associate, or analyze objects and properties.dataVotes: 0GitHub stars: 9
Eqtl Catalogue Region FetchAFetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP. Use when an agent needs eQTL beta / SE / p-value for every variant in a window around a gene's TSS for one specific dataset (study × tissue × quantification method). Input: dataset_id, chromosome, start, end, optional molecular_trait_id. Output: harmonised TSV slice.datapythongoVotes: 0GitHub stars: 9
Dashboard ExpertAFull CRUD and analysis for Mixpanel dashboards. Use when the user asks to build, create, analyze, read, understand, explain, modify, update, enhance, or manage dashboards, or asks about dashboard layout, text cards, or report arrangement. Covers dashboard analysis (read + understand existing), creation (new builds), modification (update existing), and explanation (data-driven annotation).datapythongoVotes: 0GitHub stars: 9
Msmodelslim Model AdaptA为 msModelSlim 创建基础 Transformers 模型适配器（Model Adapter）。datapythonrustVotes: 0GitHub stars: 31
Msagent Profiler BreakdownADB格式Profiling数据场景化性能拆解：自动完成场景确认（框架/任务类型判定）、阶段拆解与单次执行边界拆解，并给出报告。Use when 需要对昇腾 Profiling DB 做阶段拆解、step 归因或生成性能报告, or when the user says "帮我按任务阶段拆解这个Profiling数据", "多层次性能耗时拆解", "分析这个 vllm/sglang/verl 数据，主要耗时都花费在哪里了"。datapythongoVotes: 0GitHub stars: 31
Memory AnalysisA对 msMemScope 显存数据做全链路处理：根据用户的显存问题诉求（OOM、显存泄漏、显存占比拆解、Step 间对比等），指导并帮助用户以最合适的 msMemScope 采集配置完成显存数据采集（支持命令行、Python 接口、mstx 打点三种采集方式，覆盖训练、推理 vLLM-Ascend、FSDP、强化学习 verl 等场景）；对已采集的 memscope_dump_*.csv/db 数据做系统性解读与问题诊断（整体显存曲线趋势分析、显存使用大头按模块/组件拆解分析、显存峰值点各模块与流程占比分析，以及对显存泄漏、OOM 等典型问题的根因定位与原因分析）。datapythonbashVotes: 0GitHub stars: 31
Ascend Profiler Data ValidationA当用户提供 MindStudio profiler 采集的性能数据（框架 profiler、msprof 命令行）时，对数据完整性、采集状态及关键配置进行校验，确保后续分析工具能正常运行。dataapiVotes: 0GitHub stars: 31
Ascend Prof CompareACompares two Prof datasets (GPU vs NPU / NPU vs NPU) by auto-installing and calling msprof-analyze compare, then parses the result xlsx into HTML report and Chinese xlsx. Invoke when user provides two prof dirs to compare, or has a compare result xlsx to analyze/translate.datapythonbashVotes: 0GitHub stars: 31
Ascend Msprof Analyze CliAMindStudio Profiler Analyze（msprof-analyze）是面向 AI 训练与推理场景的性能分析工具，基于采集得到的 profiling 数据进行统计、比对和诊断，帮助定位计算、通信、调度及集群场景下的性能瓶颈。databashapiVotes: 0GitHub stars: 31
Ascend Communication AnalysisAAnalyze Ascend NPU collective communication profiling data with a DB-first workflow. Use when the user provides `cluster_analysis_output/cluster_analysis.db`, rank-level `analysis.db`, rank-level `ascend_pytorch_profiler_{rank_id}.db`, together with `profiler_info.json`, and asks about HCCL or hcom communication cost, collective communication TOP ops, wait time, slow rank/straggler, Notify Wait, bandwidth, retry, relay, SDMA/RDMA/HCCS links, communication matrix, or Ascend communication fault...datapythongoVotes: 0GitHub stars: 31
Ascend Cluster Fast Slow Rank DetectorA专门用于 Ascend 集群 Profiling 性能数据的“快慢卡”诊断专家技能。当用户提供【集群性能数据目录/路径】并要求分析【快慢卡】、【慢节点】、【负载不均衡】或【集群瓶颈】时，必须触发此技能。该技能会自动接收集群路径，调度相关工具输出快慢卡的宏观定性与微观根因（如 Host 下发瓶颈、算子计算劣化）。datapythonbashVotes: 0GitHub stars: 31
Ascend Cluster CompareAAscend cluster comparison tool. Invoke when user asks to compare two cluster datasets (DB or TEXT), or to generate cluster_analysis_output from raw profiling data via msprof-analyze and then compare.datapythongoVotes: 0GitHub stars: 31
Ops Performance TuningACompile, profile, diagnose, optimize, and compare Ascend NPU operators across CANN versions and A2/A3/A5 for Ascend C, CATLASS, Triton-Ascend, TileLang-Ascend, PyPTO, and SHMEM/MC2. Use when an operator already has a runnable implementation and the user asks for msOpProf collection, bottleneck analysis, source-level tuning, or a reproducible before/after performance report. Do not use as the primary workflow for operator creation, migration, or unresolved correctness failures.datapythongoVotes: 0GitHub stars: 31