Data & Analytics

Execute KQL queries and analyze data in Azure Data Explorer for log analytics, telemetry, and time series insights. Execute KQL queries against massive datasets with sub-second performance, including filtering, aggregation, time series analysis, and cross-table joins Discover and explore cluster resources, databases, and table schemas to understand your data model before querying Supports five core query patterns: basic retrieval, aggregation analysis, time series analytics, join-based correlation, and schema discovery Built-in fallback to Azure CLI commands when MCP tools timeout or encounter connection errors

Comprehensive Lark Base operations via CLI with table, field, record, view, formula, lookup, workflow, dashboard, and form management. Supports full CRUD operations on Base workspaces, tables, fields, and records; includes formula and lookup field creation for derived metrics and cross-table calculations Handles data analysis workflows: filtering, sorting, grouping, aggregation via data-query ; record search, list, and history tracking; view configuration and temporary projections Manages workflows, dashboards with block components, forms with question management, and role-based access control with advanced permissions Requires reading command-specific reference documentation before execution; enforces strict field structure validation, token parsing (Wiki to Base resolution), and serial execution for list operations

Create, manage, and manipulate Lark spreadsheets with full cell and sheet control. Supports spreadsheet creation, sheet operations (create/copy/delete/update), and cell data management (read/write/append/find/replace) Handles rich cell types including formulas, links with text, @mentions, @documents, and dropdown lists via object-format syntax Provides row/column management, cell styling, merging, image insertion, filter views, and floating image support Includes async export functionality and cross-sheet formula references (IMPORTRANGE) with up to 5 nesting levels Requires lark-cli binary and proper authentication via shared Lark credentials; wiki links require node type resolution before use

Daily schedule and task summary combining calendar events and pending to-dos for a specified date. Fetches calendar events and incomplete tasks for today, tomorrow, or a custom date range using ISO 8601 timestamps Requires explicit --complete=false flag when querying tasks to exclude completed items from the summary Outputs a structured report with time-converted events, task deadlines, conflict detection, and free time slots Supports filtering by due date ( --due-end ) and pagination ( --page-all ) for large task lists; requires prior Lark CLI authentication with calendar and task scopes

Query historical Azure costs, forecast future spending, and identify optimization opportunities across subscriptions and resource groups. Supports three primary workflows: cost queries with breakdown by service/resource/tag, spending forecasts with configurable time periods, and cost optimization analysis including orphaned resources and VM rightsizing Integrates with Azure Cost Management API (query and forecast endpoints) and Azure Monitor for utilization metrics; includes MCP tools for documentation lookup, CLI command generation, and Azure Quick Review compliance scanning Handles subscription, resource group, management group, and billing account scopes; enforces Cost Management Reader role requirement and includes rate-limit handling (4 requests/minute per scope) Requires actual cost data validation before recommendations; always presents total bill alongside optimization suggestions and includes Azure Portal links for all resources

Identify cost savings across Azure subscriptions through resource analysis, utilization metrics, and actionable optimization recommendations. Discovers orphaned resources (unattached disks, unused NICs, idle gateways) and over-provisioned services using Azure Quick Review Queries actual costs from Azure Cost Management API and utilization data from Azure Monitor to support rightsizing recommendations Generates prioritized optimization reports with estimated savings, implementation commands, and Azure Portal links for each resource Includes specialized Redis cost optimization analysis with subscription filtering and pre-built report templates Requires Cost Management Reader, Monitoring Reader, and Reader roles; validates prerequisites before analysis begins

Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms. Four observability tiers: Cloud Trace (always enabled, distributed tracing), Prompt-Response Logging (GenAI interactions to GCS/BigQuery), BigQuery Agent Analytics (structured agent events), and third-party integrations (AgentOps, Phoenix, MLflow, Weave, Freeplay, and others) For Agent Runtime deployments, run agents-cli infra single-project before first deploy to provision Terraform-managed infrastructure (service account, GCS bucket, BigQuery dataset); post-deployment setup requires manual IAM and env var configuration Cloud Trace works out of the box with OpenTelemetry spans tracking invocation flow, LLM calls, and tool execution; accessible via Cloud Console Trace explorer Prompt-response logging is privacy-preserving by default (metadata only via OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=NO_CONTENT ); disabled locally unless LOGS_BUCKET_NAME is set Includes troubleshooting guide covering missing traces, privacy misconfiguration, BigQuery setup, and cost optimization strategies

Reduce voluntary and involuntary churn through cancel flows, dynamic save offers, and payment recovery. Design exit surveys and targeted save offers (discounts, pauses, downgrades) matched to cancellation reasons, typically recovering 25-35% of at-risk customers Implement proactive retention by tracking health signals (login frequency, feature usage, support sentiment) and intervening before customers reach the cancel page Set up dunning sequences with smart payment retries, escalating emails, and grace periods to recover 50-60% of failed payments Integrates with Stripe, Chargebee, Paddle, and retention platforms like Churnkey and ProsperStack for end-to-end churn prevention

Query metrics, logs, and traces across Azure Monitor, Application Insights, and Log Analytics. Access metrics, KQL log queries, and distributed tracing through MCP tools or Azure CLI commands Supports Application Insights for APM and performance analysis, Log Analytics for custom KQL queries, and Azure Monitor for infrastructure metrics Includes common KQL query patterns for errors, request performance, and resource usage monitoring Workbooks integration for building interactive observability dashboards and reports

Design and optimize systems connecting marketing, sales, and customer success into a unified revenue engine. Covers lead lifecycle stages (Subscriber → Lead → MQL → SQL → Opportunity → Customer), stage definitions with entry/exit criteria, and ownership accountability across teams Includes lead scoring frameworks combining fit (ICP attributes) and engagement (behavioral signals) with negative scoring to filter unqualified leads Provides lead routing methods (round-robin, territory, account-based, skill-based) with speed-to-lead optimization and SLA enforcement for handoffs Details pipeline stage hygiene, required fields per stage, stale deal detection, and key metrics (conversion rates, velocity, coverage ratio, win rate by source) Covers CRM automation workflows, deal desk approval tiers, data dedup and enrichment strategies, and quarterly audit checklists

Create database-like views of Obsidian notes using .base files with filters, formulas, and multiple display modes. Supports four view types: table, cards, list, and map, each configurable with custom property ordering and grouping Define computed properties using formulas with conditional logic, date arithmetic, string formatting, and 15+ built-in functions Apply global or view-specific filters using tag, folder, property, date, and link conditions with AND/OR/NOT logic Includes summaries for numeric, date, and boolean properties (Average, Sum, Min, Max, Median, Earliest, Latest, Checked, Unique, etc.) Embed bases in markdown files and validate YAML syntax; common issues include unquoted special characters, mismatched quotes in formulas, and missing null checks for optional properties

Install the lark-okr skill for your AI agent. Published on open.feishu.cn.

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google…

Set up, audit, and improve analytics tracking to measure marketing and product decisions. Provides a tracking plan framework with event naming conventions, essential event libraries by business type, and property standards to ensure consistent, decision-driven measurement Covers GA4 implementation, Google Tag Manager setup with data layer patterns, and UTM parameter strategy for campaign attribution Includes debugging and validation tools, common issue troubleshooting, and privacy/compliance considerations for consent and PII protection Integrates with GA4, Mixpanel, Amplitude, PostHog, and Segment; works with product marketing context if available to inform tracking decisions

Expert analysis and actionable recommendations to improve marketing page conversion rates. Analyzes pages across seven dimensions: value proposition clarity, headline effectiveness, CTA placement, visual hierarchy, trust signals, objection handling, and friction points Provides structured output with quick wins, high-impact changes, test ideas, and copy alternatives for headlines and CTAs Includes page-type-specific frameworks for homepages, landing pages, pricing pages, feature pages, and blog posts Reads product marketing context from .agents/product-marketing-context.md if available to inform recommendations without redundant questions

Strategy, optimization, and execution for paid advertising campaigns across Google Ads, Meta, LinkedIn, and other platforms. Covers campaign structure, audience targeting, bidding strategies, and creative best practices across five major ad platforms with platform-specific strengths and use cases Includes funnel-based retargeting strategies, segmentation by stage, and exclusion rules to prevent wasted spend on existing customers Provides optimization frameworks for high CPA, low CTR, and high CPM scenarios, plus weekly reporting metrics and attribution considerations Offers naming conventions, budget allocation guidance for testing vs. scaling phases, and pre-launch checklists to ensure proper conversion tracking and setup

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B…

Optimize post-signup user activation and time-to-value through structured onboarding flows. Defines activation metrics and "aha moments" specific to your product type, then maps the fastest path from signup to first value Provides templates for onboarding checklists, empty states, and guided tours designed to reduce friction and guide users to core features Includes trigger-based email coordination strategies to reinforce in-app actions and re-engage stalled users across days 1, 3, 7, and beyond Offers funnel analysis frameworks to identify drop-off points and prioritize fixes by impact, plus experiment ideas for flow simplification and progress mechanics