Data & Analytics
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
-
georgeqle Skill Session Triage 11Investigate one immediate session, correction, repo incident, or skill failure and recommend a verified fix
1 -
georgeqle Skill Session Triage 12Investigate one immediate session, correction, repo incident, or skill failure and recommend a verified fix
1 -
georgeqle Skill Session Triage 13Investigate one immediate session, correction, repo incident, or skill failure and recommend a verified fix
1 -
georgeqle Skill Session Triage 14Investigate one immediate session, correction, repo incident, or skill failure and recommend a verified fix
1 -
georgeqle Skill Analyze Sessions 2Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 3Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 4Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 5Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 6Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 7Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 8Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 9Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 10Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
georgeqle Skill Analyze Sessions 11Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
1 -
timlai666 Bundle Benchling IntegrationBenchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
1 -
ahang1598 Skill Skill 44产品设计套件深挖工具。当用户是设计师拿到一堆客服工单 / 应用商店评论 / 社群反馈 / 内嵌反馈表单数据,想从海量散乱反馈里提炼出"高频体验问题 + 受影响的页面 / 流程"时启动的 Skill。与 Probe(用户访谈)形成互补——Probe 是主动深挖少量样本,Signal 是被动整理海量样本。 与 product-management(产品管理)套件互补,服务不同角色: - 用户是设计师要从工单 / 评论里找体验卡点、流程断点、关联页面→ 用本 Skill ✅ - 用户是产品经理要做 NPS 计算、产品决策、改进建议优先级 → 请用 product-management 套件的 `/用户反馈分析` - 用户是设计师要主动做用户访谈 / 用研整理 → 请用本套件 `/用户研究` 本 Skill 从原始反馈数据(工单 CSV / 评论文本 / 截图描述)提炼结构化体验问题清单——6 类反馈分类 + 3 级情感分级 + 双聚类法(亲和图法 + 主题编码) + 痛点优先级排序(频次 × 体验严重度 × 可信度),核心差异化输出是 `affected_pages[]`(每个痛点关联到具体页面 / 流程),下游 /启发评估 走查时直接对齐、/用户旅程 标断点时直接消费。设计师视角 ≠ 产品经理视角:本 Skill 不计算 NPS、不做趋势预测、不提改进建议——只对齐"哪些页面 / 哪些流程被反馈最多、卡点在哪、需要走查或重设计"。 触发关键词(前提:用户身份是设计师 / 设计师语境): - 设计师 + [工单 / 客诉 / 客服记录 / 评论 / 反馈 / 用户声音] [分析 / 整理 / 挖掘 / 归类] - 应用商店评论 / App Store 差评 / 小红书评论分析 / 知乎反馈 - 帮我从这堆反馈里找体验问题 / 看看用户在哪里卡住 - VoC 分析(设计师视角)/ 客诉里的体验痛点 - 找产品的体验断点 / 流程卡点 / 高频痛点定位 - signal / feedback mining / VoC for designer 排除(反向): - 用户是 PM 要做 NPS / 产品决策 / 改进优先级 → 用 product-management 套件 `/用户反馈分析` - 主动用户访谈 / 5-8 人深访整理 → 用 `/用户研究`(本套件 Probe) - 现有产品 UI 走查 → 用 `/启发评估
9 -
ahang1598 Skill Skill 78上传用户反馈数据(Excel/CSV/文本),自动分类统计并提取高频模式,输出包含情感分析、痛点排序和改进建议的洞察报告。 支持主题聚类、趋势分析和三角验证,从反馈中提炼用户画像。 连接~~Notion后报告直接写入知识库。 当用户说"用户反馈"、"反馈分析"、"用户声音"、"VOC分析"、"NPS分析"、"用户评价分析"、 "应用商店评论"、"客诉分析"、"用户调研"、"满意度分析"、"差评分析"、"好评分析"、 "反馈聚类"、"反馈趋势"、"用户画像提炼"时触发。
9 -
ahang1598 Skill Data Model Creation 2Optional advanced tool for complex data modeling. For simple table creation, use relational-database-tool directly with SQL statements.
9 -
ahang1598 Bundle Tchouse C SQL 2TCHouse-C(ClickHouse)慢 SQL 诊断与自动调优 Skill。AI 自动检索指定集群的慢查询日志,对 Top N 慢 SQL 逐一执行 EXPLAIN 获取执行计划,分析性能瓶颈(全表扫描/JOIN 顺序不优/索引缺失/数据倾斜),生成 SQL 改写方案。 触发词:慢查询、慢SQL、slow query、SQL优化、查询优化、执行计划、EXPLAIN、查询耗时、查询超时、SQL调优、索引优化、全表扫描、数据倾斜、JOIN优化、查询性能、SQL性能、query performance、查询变慢、报表变慢、ClickHouse优化、TCHouse-C优化、cdwch、查询诊断、SQL诊断。 本 Skill 包含 3 个子能力:①慢查询 Top N 检索与趋势分析 ②执行计划分析与瓶颈定位 ③SQL 改写与索引优化方案生成。 何时不触发:集群选型与架构推荐、智能建表与数据建模、NL2SQL、集群健康诊断与故障排查(监控指标/告警/节点故障)、集群扩缩容、权限管理、数据导入导出等非查询性能相关问题不走本 Skill。
9 -
ahang1598 Bundle Tchouse C 2TCHouse-C(ClickHouse)集群健康诊断与故障排查 Skill。AI 拉取集群监控指标(CPU/内存/磁盘/IOPS/连接数/副本延迟)、告警历史及节点状态,输出集群健康评分,定位异常根因,并给出修复建议(参数调整/分区清理/节点重启等)。 触发词:集群健康、健康检查、巡检、节点故障、磁盘告警、CPU告警、内存告警、OOM、磁盘满、磁盘空间不足、节点异常、副本延迟、查询堆积、连接数满、集群状态、cluster health、node failure、disk alert、replica lag、集群诊断、故障排查、监控异常、告警处理、节点状态、资源告警、性能瓶颈、IO高、网络异常、ZooKeeper异常、parts过多、merge压力、cdwch、TCHouse-C、ClickHouse集群。 本 Skill 包含 3 个子能力:①集群全面健康巡检 ②告警事件排查与根因定位 ③节点故障诊断与修复建议。 何时不触发:慢 SQL 诊断与自动调优(单条 SQL 性能分析)、集群选型与架构推荐、智能建表与数据建模、NL2SQL、AI Function 智能编排、集群扩缩容操作、权限管理、数据导入导出等非集群健康/故障相关问题不走本 Skill。
9 -
ahang1598 Bundle Skill 204根据交易场景生成尽调材料索取清单(Excel格式),按M&A/PE/IPO/资产收购/跨境投资5种场景路由,覆盖12大模块,含风险驱动+交叉验证+动态迭代方法论。触发:尽调启动需向目标公司发函索取材料。不触发:尽调报告(→07)、合同审查(→06)、法律意见、陷阱对抗(→adversarial)、创始人责任(→founder-liability)、股权核验(→cap-table-verify)、权利设计(→special-rights-design)、多轮一致性(→multi-round)。
9 -
ahang1598 Skill Relational Database MCP Cloudbase 2[Deprecated] This is the required documentation for agents operating on the CloudBase Relational Database through MCP. It defines the canonical SQL management flow with `queryMysqlDatabase`, `manageMysqlDatabase`, `queryPermissions`, and `managePermissions`, including MySQL provisioning, destroy flow, async status checks, safe query execution, schema initialization, and permission updates. New environments should use PostgreSQL — see postgresql-development skill instead.
9 -
ahang1598 Bundle Tchouse C 3TCHouse-C(ClickHouse)集群选型与架构推荐 Skill。面向首次开通或新增 ClickHouse 集群的用户,AI 根据用户提供的业务画像(数据规模、增长速率、查询模式、并发要求、延迟要求、预算约束),推荐适合的集群规格(节点数/CPU/内存/存储类型/副本数)、可用区与网络方案,并输出多方案费用对比。 触发词:集群选型、集群推荐、新建集群、新购集群、购买集群、创建集群、集群规格、节点选型、机型推荐、架构推荐、容量规划、sizing、cluster recommendation、cluster sizing、TCHouse-C 新购、cdwch 新建、ClickHouse 选型、选什么规格、买多大的集群、集群配置推荐、存储选型、磁盘选型、高可用方案、跨AZ部署、费用估算、成本对比、包年包月还是按量。 本 Skill 包含 3 个子能力:①业务画像采集与需求分析 ②集群规格与架构方案推荐 ③多方案费用对比与最终建议。 何时不触发:已有集群的慢查询诊断、SQL 优化、集群扩缩容操作、集群健康诊断与故障排查、NL2SQL、权限管理、数据导入导出等非新购选型相关问题不走本 Skill。
9 -
johnalbertini14-glitch Bundle RosterCreates weekly shift rosters (KW-JSON) from CSV availability data and pushes them to GitHub.
1 -
johnalbertini14-glitch Bundle DocstrangeDocument extraction API by Nanonets. Convert PDFs and images to markdown, JSON, or CSV with confidence scoring. Use when you need to OCR documents, extract invoice fields, parse receipts, or convert tables to structured data.
1 -
johnalbertini14-glitch Bundle Linkedin DmSend personalized LinkedIn direct messages to a list of existing 1st-degree connections via browser automation. Use when the user wants to message LinkedIn connections with AI-personalized outreach — e.g. nurturing leads, following up after events, reconnecting with contacts, or announcing something. Takes a data file (CSV/TSV) or plain list with connection names and companies, asks for outreach context/goal, generates a tailored message per person, and sends each one via browser automation. Handles message compose flow, character limits, and incremental status tracking.
1 -
johnalbertini14-glitch Bundle InstantlyInstantly API integration with managed OAuth. Cold email outreach platform for managing campaigns, leads, accounts, and analytics. Use this skill when users want to create campaigns, manage leads, send emails, or view analytics. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
1 -
johnalbertini14-glitch Bundle PandasAnalyze, transform, and clean DataFrames with efficient patterns for filtering, grouping, merging, and pivoting.
1 -
johnalbertini14-glitch Bundle Outlit MCPUse when querying Outlit customer data via MCP tools (outlit_*). Triggers on customer analytics, revenue metrics, activity timelines, cohort analysis, churn risk assessment, SQL queries against analytics data, or any Outlit data exploration task.
1 -
johnalbertini14-glitch Bundle AgentcanaryMarket intelligence API for AI agents. Macro regime detection, risk scoring, trading signals (IGNITION/ACCUMULATION/DISTRIBUTION/CAPITULATION), whale alerts, funding arbitrage, orderbook analytics, 29 technical indicators, RSI screening (606 coins), breaking news with FinBERT sentiment, economic calendar, treasury tracking, and Polymarket odds. 33 endpoints, 1181 assets, 250+ sources. Use when an agent needs macro regime context, risk assessment, position sizing guidance, market structure data, whale activity monitoring, or news sentiment. API-only — no local execution, no filesystem access, no secrets in prompt.
1 -
johnalbertini14-glitch Bundle TokportalAutomate social media at scale — create TikTok/Instagram accounts, distribute videos, upload content, and track analytics with 30 AI-native MCP tools via the TokPortal API.
1 -
johnalbertini14-glitch Bundle Heurist Mesh SkillReal-time crypto token data, DeFi analytics, blockchain data, Twitter/X social intelligence, enhanced web search, crypto project search all in one Skill. For in-depths topics, "Ask Heurist" agent can handle market trends, trading strategies, macro news, and deep research.
1 -
johnalbertini14-glitch Bundle Appraisal AIDrafts real estate appraisal reports from your project workfile. Produces Word narratives with tracked changes and Excel adjustment grids from your own master templates. You review and accept every change.
1 -
johnalbertini14-glitch Bundle FoxreachManage FoxReach cold email outreach — leads, campaigns, sequences, templates, email accounts, inbox, and analytics. Use when the user asks to create leads, manage campaigns, check analytics, send outreach, manage email sequences, or anything related to the FoxReach API.
1 -
johnalbertini14-glitch Bundle AnalystExtract insights from data with SQL, visualization, and clear communication of findings.
1 -
johnalbertini14-glitch Bundle Inclawnch AnalyticsReal-time INCLAWNCH token analytics on Base. Price, volume, liquidity, staking TVL, UBI APY, distribution rates, and platform metrics in a single API call. No API key needed. Use when: (1) user asks about INCLAWNCH price or market data, (2) checking UBI staking yields, (3) monitoring ecosystem health, (4) building dashboards or alerts.
1
Frequently asked questions
What are Data & Analytics agent skills?
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
Which Data & Analytics skills are most installed?
Popular Data & Analytics skills on SkillMD right now include 工单分析, 用户反馈分析, data-model-creation. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Data & Analytics skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.