Data & Analytics

kiwissenorg-skills Bundle

Datenschutz-Skill mit zwei Modi: **Verblenden** (Anonymisieren) und **Entblenden** (Re-Identifizieren). Verblenden ersetzt alle personenbezogenen und datenschutzrelevanten Daten in einem Dokument durch neutrale Platzhalter-IDs (z.B. PERSON_01, FIRMA_01), speichert ein Mapping als CSV und legt das anonymisierte Dokument ab. Entblenden liest das Mapping und stellt das Original wieder her. Nutze diesen Skill IMMER wenn Harald oder ein User fragt: „verblende das Dokument", „anonymisiere den Text", „entblende die Datei", „mach die Daten unkenntlich", „ersetze Namen und Adressen", „re-identifiziere", „stell das Original wieder her", „datenschutzkonform anonymisieren". Auch triggern bei Begriffen wie Pseudonymisierung, Anonymisierung, DSGVO-Anonymisierung, Datenschutz- Schwärzung, Testdaten anonymisieren, PII entfernen, Namen ersetzen, sensible Daten ersetzen. Verwende diesen Skill bei jedem Workflow der Originaldaten anonymisiert an KI-Systeme weitergibt und danach die Ergebnisse re-identifiziert.

shipiit Skill

Turn a messy CSV, spreadsheet or export into something analysable, without silently changing what it says. Use when data has inconsistent formats, missing values, duplicates or bad headers.

snowflake-labs Bundle

Interactive tutorial teaching Snowflake Cortex Search for building semantic search and RAG applications. Guide users through creating search services and querying them using SQL and Python. Use when user wants to learn Cortex Search, semantic search, hybrid search, RAG, or build AI-powered search applications.

snowflake-labs Bundle

Interactive tutorial teaching Snowflake Cortex CLASSIFY_TEXT for categorizing unstructured text. Guide users through classifying customer reviews using Python and SQL. Use when user wants to learn text classification, Cortex LLM functions, or analyze unstructured feedback data.

accoil Bundle

Generate real instrumentation code from the tracking plan and instrumentation guide. Produces typed SDK wrapper functions, identity management, and integration guidance. Outputs files in a tracking/ directory. Use when the user wants to generate or regenerate tracking code, implement the delta plan, turn the instrumentation guide into working code, 'implement tracking,' 'generate code,' 'create tracking module,' or 'build analytics SDK wrapper.'

accoil Bundle

Design an opinionated target tracking plan and produce an explicit delta from current state to target. Combines the product model, current-state audit, and telemetry best practices to decide what events, properties, entities, and group hierarchies should exist. Outputs .telemetry/tracking-plan.yaml and .telemetry/delta.md. Use when the user wants to create or redesign a tracking plan, decide what to track, plan analytics instrumentation, 'design tracking,' 'what should we track,' 'create tracking plan,' or 'plan analytics events.'

accoil Bundle

Reverse-engineer the current state of analytics tracking from a codebase. Scans for SDK calls, identity management, and instrumentation patterns to produce a factual inventory — not recommendations. Outputs .telemetry/current-state.yaml and a timestamped audit report. Use when the user wants to know what's currently tracked, audit existing analytics, capture tracking reality before designing a new plan, 'what analytics do we have,' 'what events are tracked,' 'scan for tracking,' or 'tracking inventory.'

accoil Bundle

Translate a tracking plan into an SDK-specific instrumentation guide. Shows how to make identify, group, and track calls using the target analytics SDK with real template code, architecture guidance, and constraint documentation. Outputs .telemetry/instrument.md. Covers 24 analytics destinations across product analytics, CDPs, web analytics, error monitoring, feature flags, and session tools. Use when the user has a tracking plan and needs to know how to implement it with a specific SDK like Segment, Amplitude, Mixpanel, PostHog, Accoil, Google Analytics, Sentry, LaunchDarkly, or via generic HTTP POST. Also use when user asks 'create instrumentation guide,' 'how to implement tracking,' 'SDK guide,' or 'generate implementation guide.'

agenthouse-org Bundle

Interview a user to define an organizational role, clarify its purpose, domains, responsibilities, authority, obligations, boundaries, requirements, holder, and approval, then create a professional role profile as DOCX or Excel. Use when designing roles, clarifying accountability, separating roles from job positions, preparing organizational changes, improving handoffs, hiring, onboarding, governance, or documenting decision rights.

nansen-ai Skill

Token God Mode analytics via Nansen CLI. Screen tokens, analyze holders, track flows, see who's buying/selling, PnL leaderboards, and flow intelligence by label.

nansen-ai Skill

Entry point for all Nansen queries. Routes user requests to the correct Nansen skill based on intent. Load this skill first — it decides which domain skill to activate for any blockchain analytics question.

nansen-ai Skill

Hyperliquid perpetual trading analytics via Nansen CLI. Track smart money perp trades, open positions, PnL leaderboards, and trader analysis on Hyperliquid.

nanzhipro Bundle

针对指定 PDF 或 Office 文档（.pdf/.docx/.xlsx/.pptx）进行全文解析、检索与深度理解，识别并汇总隐私/敏感信息（PII、金融、健康、账号凭据等），输出审计报告与风险提示。用于合规审查、数据脱敏准备、外发前检查或隐私扫描。

nicknisi Skill

Show usage metrics and analytics for AI coding sessions. Use when the user asks "how much have I been coding", "session stats", "show me metrics", "tool usage", "which tool do I use most", "active hours", or wants analytics about their AI coding tool usage.

nirholas Skill

Use this skill any time MEV exposure is a consideration in PumpKit — designing or auditing a trading flow, deciding slippage / RPC privacy / wallet rotation, hardening a launch, or post-mortem investigating a sandwich. Triggers on "MEV", "sandwich", "frontrun", "sniper", "copy-trader", "private RPC", "wallet rotation", "slippage", "contested launch". Skip for read-only flows (analytics, decoders) where no value is at risk.

theaayushstha1 Bundle

Construction industry lead generation for Gaudon Silicone. Triggers on: "find leads", "lead gen", "construction leads", "find contractors", "find distributors", "prospect list", "sales leads", "find glazing companies". Uses Gemini API with Google Search grounding to find real companies with contact info, outputs professional Excel spreadsheets for sales outreach.

timeplus-io Bundle

Timeplus streaming SQL covering stream types, EMIT policies, window functions, JOINs, materialized views, external streams, and UDFs. Make sure to use this skill for any SQL-related question including writing queries, debugging SQL errors, understanding streaming behavior, or designing stream processing pipelines, even if the user doesn't explicitly mention streaming SQL.

timeplus-io Bundle

Build, compile, run server/client/cluster, execute unit/stateless/SQL tests, verify results, and troubleshoot build/test failures. Make sure to use this skill whenever the user mentions building, compiling, ninja, cmake, running tests, test failures, starting the server, or pre-commit checks, even if they just say 'it doesn't build' or 'the test broke'.

varunk130 Skill

Generates eval test cases for AI agents from an eval suite plan (output of /eval-suite-planner) or a plain-English agent description. Supports both single-response and conversation (multi-turn) evaluation modes. Outputs a test set table, a CSV file in the Copilot Studio import format (single-response only - used here as the primary worked example; trivially adaptable to any harness that accepts tabular test cases), and a docx report for human review.

varunk130 Skill

Analyzes AI agent evaluation results - primarily from Copilot Studio (the worked example here, via its CSV export) but also from custom harnesses or any evaluator that produces per-case pass/fail rows - using Microsoft's Triage & Improvement Playbook. Returns a SHIP / ITERATE / BLOCK verdict with root cause classification, diagnostic triage, prioritized remediation, and pattern analysis.

vh992098059 Skill

指导何时及如何调用 read_file、write_file、execute 工具。适用于用户说「读文件」「打开 CSV」「执行脚本」「保存到文件」「运行代码」等文件操作场景。

spitoglou Bundle

Convert content between formats, summarize at different levels, and repurpose for various platforms. Use when asked to convert to markdown, create summaries of varying lengths, make tweets, create flashcards, or process video content. Triggers include "convert to markdown", "summarize in one sentence", "make this a tweet", "create flashcards", "TL;DR", "summarize this video", "export as CSV".

ssheleg Bundle

Use when setting up or modifying ad pixel integration, conversion tracking, consent management, purchase event tracking, retargeting audiences, or auditing an existing advertising analytics stack. Covers Google Analytics 4, Google Ads, Meta (Facebook) Pixel and LinkedIn Insight Tag in web applications: Consent Mode v2, standard events, e-commerce tracking, advanced matching, Enhanced Conversions, CSP configuration, user identification, cross-device tracking, and GDPR/DMA compliance. Triggers - "ad tracking", "conversion tracking", "meta pixel", "fbq", "google ads", "GA4", "gtag", "consent mode", "cookie consent", "enhanced conversions", "retargeting", "purchase event", "CAPI", "gclid", "UTM", "attribution", "отслеживание конверсий", "пиксель Meta", "согласие на куки", "ретаргетинг", "аналитика рекламы". Not for running the ad campaigns themselves.

sungjunlee Bundle

Drive an immutable cohort of already-planned relay leaves through fan-out and derived status.

techstay Bundle

Create and manage reactive Python notebooks in Marimo. Use when creating notebooks, adding UI input components, writing SQL queries, deploying as apps, or learning about Marimo's reactive execution model. Keywords: marimo notebook, reactive notebook, Python notebook, UI components, SQL cell, app deployment.

tencent Bundle

Minimal text2sql skill. Gives you tools and knowledge to generate SQL — no required workflow.

the-vibe-company Bundle

Use this skill when the user or workflow needs to share by public link, send a URL, attach as a public URL, upload to Vanish, publish, hand off by URL, or create a public URL for one or more files or documents, including PDFs, DOCX, PPTX, XLSX, Markdown, images, screenshots, reports, archives, generated deliverables, or review artifacts. Prefer it automatically when a final artifact should be externally accessible by URL. Do not use for local-only reading, summarizing, editing, native email/chat attachments, connector-specific sends, or inspection. Ask before uploading suspected secrets, credentials, customer/private data, contracts, invoices, medical/legal/financial records, unreleased proprietary content, or personal data.

yugabyte Bundle

Use when writing or reviewing SQL, schema definitions, or application code that targets YugabyteDB's PostgreSQL-compatible YSQL API (port 5433). Triggers on CREATE TABLE, indexes, connections, transactions, sharding, migrations from PostgreSQL, or any mention of YugabyteDB with SQL.

yulianggan Bundle

Ozon FBO 按 timeslot 日期生成对照表 + 合并箱唛 PDF (build_by_date.py). 当用户说 "按日期整理对照表"、"按发运日期分对照表"、"准备交货 tab 的对照表"、"按预约时间合并箱唛"、"按日期合并 PDF"、"打印发货清单"、"司机交货前出对照表" 时触发. 默认只取 READY_TO_SUPPLY 状态 (Ozon 后台 "准备交货" tab), 输出 by_date/YYYY-MM-DD/{对照表.xlsx, 箱唛合并.pdf}.

yulianggan Bundle

Ozon FBO 端到端发货编排. 当用户说"丝绸生活账号补 N 天 FBO"、"按安全天数发货"、"清空海外仓"、"补海外仓没货的 SKU"、"Q_X 发 N 箱你帮分集群"、"全自动发货"、"FBO 一键发"时触发. 自动 4 mode 决策 + 跑 create_fbo_plan + cron-style 自动 retry 直到全发完, 终态出对照表 Excel. wrapper 调用老 fbo-* 子 skill 的脚本, 不重复实现.

zavora-ai Skill

Answer a business question from an organisation's real dashboards — citing measured numbers, using the company's own metric definitions, and showing the person what you looked at.

zenml-io Bundle

Guide users from their own agent code or recorded traces through Kitaru setup, session import or recording, human review, an accepted behavior, a versioned cohort, and evaluator selection, then hand one bounded change to the replay-experiment skill. Use when a user wants to connect or inspect an existing agent, import real traces, investigate a known bad or surprising session, discover recurring failure modes, learn the evidence-led review flow, resume an investigation, create a cohort from reviewed evidence, or author an evaluator for an accepted behavior. When a first-time user has no agent or evidence and wants a fast demonstration with the PydanticAI returns agent example, use the `kitaru-guided-tour` skill instead.

zenml-io Bundle

Run and interpret one safe, bounded Kitaru replay comparison against an accepted cohort and exact evaluators. Use when a user wants to replay a cohort, test or compare a model, prompt, system prompt, parameter, agent version, or tool policy, supervise an experiment run, determine whether one candidate helped, or ask for one bounded change worth testing.

zerx-lab Skill

gettopic 后端开发规约(Go + connectRPC + GORM)。当新增/修改 RPC、实现 service handler、写数据访问、用 GORM 泛型 API、自定义 querier SQL、跑 codegen 时使用。Keywords: connectRPC, handler, service, GORM, gorm.G, 泛型, Count, FirstOrCreate, nilaway, getter, querier, 自定义 SQL, deleted_at, 软删, convert, proto, task gen, buf, 代码生成, JS 保留字, 后端, backend, Go

zerx-lab Skill

gettopic 认证与安全机制(JWT/会话/刷新/验证码/防爆破/审计日志/文件上传/对象存储)。当处理登录注册、token 刷新、会话管理、登录限流、操作日志、上传、存储 driver 时使用。Keywords: JWT, access token, refresh token, 会话, session, jti, 单点登录, AUTH_SINGLE_SESSION, 验证码, captcha, 防爆破, ratelimit, 锁定, 审计, 操作日志, OperationLog, login_logs, 上传, upload, 对象存储, storage, local, s3, minio, password policy, password reset, SMTP, mailer, TOTP, 2FA, MFA, export, import, xlsx, OpenAPI, docs, cron, job, scheduler, readyz, 安全, security, 认证, auth

promptingcompany Bundle

Build, debug, or plan work with The Prompting Company through its API, MCP Server, CLI, or SDK entrypoints. Use when the user needs public routes, OpenAPI schema guidance, TypeScript SDK integration, CLI workflows, MCP setup, content APIs, app publishing APIs, public markdown access, simulations, visibility analytics, authentication, or API key scopes.