16,488 tagged Analytics and metrics, measured the same way as everything else here.
Browse within: LLM 162agent 151agents 134agentic-ai 84skills 83javascript 75seo 69data-analysis 68ab-testing 66ai-assistant 60cli 60claude-code-skills 59dashboard 54Evaluation 53
Skill Claude CodeCodex
Triage a broken or degraded data asset in DataHub. Traces the downstream blast radius across all lineage hops, resolves owners, ranks by criticality, writes a structured incident report, and records the incident back into the catalog (tag + runbook document + native incident). Use when a table, view, dashboard, or…
Skill Claude CodeCodex
Use when the user asks a data question in plain English that needs SQL across one or more configured databases (ClickHouse, Teradata, PostgreSQL/GaussDB, MySQL, SQL Server, DB2, Oracle, Mongo). Governed NL→SQL via the chat-sql MCP server — results are PII-masked and writes are limited to scratch tables the assistant…
Skill Claude CodeCodex
A process for reviewing Chinese pre-sales customer-service chats in a logged-in browser system and producing a traceable PowerPoint report.
Skill Claude CodeCodex
Render Apache ECharts charts server-side as SVG, PNG, or interactive HTML using the echarts-mcp MCP server. Use when the user asks to visualize data as a chart, graph, plot, or dashboard widget, wants a statically renderable vector graphic for a document, a PNG image for a chat platform, or a self-contained HTML page.…
Big-Tea-Rice/tradingview-mcp-jackson
Skill Claude CodeCodex
Analyze a chart — set up symbol/timeframe, add indicators, scroll to key dates, annotate, and screenshot. Use when the user wants technical analysis or chart review.
Skill Claude CodeCodex
Expert analysis of Rapid7 InsightVM data exported via Bulk Export API with strict MCP requirements.
Skill Claude CodeCodex
Converts CSV exports to Parquet and validates them against a declared schema, reporting type mismatches per column. Use when the user asks to convert, compact, or validate tabular data files before loading them into a warehouse.
Skill Claude Code
Turn a folder of call transcripts into a prospect intelligence report. Filters noise, separates prospect calls from customer calls, fans out parallel subagents to read transcripts, and consolidates personas, pain points, objections, competitive mentions, feature requests and verbatim quotes. Trigger on…
Skill Claude CodeCodex
Run the eval harness over 50+ synthetic COD orders and produce batch metrics with honest assumptions. Use when validating gate decisions or preparing evidence for the buildathon submission.
Skill Claude CodeCodex
A skill for commercial data research and report creation using the ShuLan AI data platform. It covers tasks such as industry research, creator lists, tenders, company insights, hiring signals, and public-opinion trends.
unchartered-starlet3516/App-data-IOS-GP-
Skill Claude CodeCodex needs its repo
An automation guide for collecting app-store data from FoxData and turning it into posts for several social and developer platforms. FoxData provides data about apps in Apple’s App Store and Google Play.
Skill Claude CodeCodex
A research tool for retrieving and analyzing trending products on Product Hunt, a website where new technology products are launched and discussed.
tetracoralla/context-surface-analyzer
Skill Codex
Use Context Surface Analyzer when the user supplies one explicit Agent tool-catalog snapshot to measure or two ordered snapshots to compare, especially for exact catalog bytes, tool and schema counts, name collisions, exact duplicate schemas, declared budget checks, or fully labeled caller-supplied token measurements.…
Skill Claude CodeCodex
Diagnose and speed up slow or expensive Apache Spark jobs using the Spark History Server MCP tools — finds the real bottleneck (skew, spill, shuffle, small files, GC, bad join strategy, under-parallelism) from task-level metrics and returns ranked, quantified fixes. Use this whenever someone asks why a Spark job is…
Skill Claude CodeCodex
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…
Skill Claude CodeCodex
End-to-end Simba MMM workflow over MCP — upload a dataset, create and poll a Bayesian model, and read results correctly (section semantics, channel naming, attribution/Overlap rules, context-size controls). Use when building or analyzing an MMM through the Simba MCP tools.
nano-step/embrace-readonly-mcp
Skill Claude CodeCodex
Use the local read-only Embrace MCP proxy when investigating Embrace app health, logs, crashes, network spans, or full structured tool results.
Skill Claude CodeCodex
Launch or reuse the loopback Memex Workspace UI when the user asks to browse conversations, manage facts, inspect taxonomy or pipeline health, or explore the knowledge map.
Skill Claude CodeCodex
Use when querying or analyzing Xiaomi Mi Fitness data through MCP.
petrycz/ecommerce-mcp-automation
Skill Claude CodeCodex
Generate the daily Shopify + Meta Ads P&L and ad-performance report as a formatted .xlsx spreadsheet. Use when asked to run, generate, or refresh today's numbers, P&L, revenue/COGS/gross-profit, ad spend, or ROAS report.
Skill Claude CodeCodex
Measure signal-level behavior in existing waveform files (VCD and FST) through the waver-mcp MCP server (waveropen, waversearch, wavervalues, wavervalueat, waveranalyze, waverlatency, waverfind, waverplot). Use when the user asks what a signal was doing at a time, a clock's period/duty/frequency, when a signal became…
Skill Codex
Safely inspect, preview, apply, and verify typed Google Ads changes through the policy-gated Google Ads MCP. Use for audits, diagnostics, performance analysis, evidence-backed recommendations, and explicitly authorized operations.
Skill Claude CodeCodex
Use the memoryengine tools for long-term memory recall, deterministic analytics, transcript logging, and sync operations.
Skill Claude CodeCodex
Operate a Reweave self-healing web-data fleet — run pipelines, triage structural-drift incidents, review repair proposals, and manage the human approval workflow. Use whenever a monitored source is broken, a heal is pending, or the operator asks about pipeline health or impact.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: