Analytics and metrics skills

17,752 tagged Analytics and metrics, measured the same way as everything else here.

Browse within: skills 93javascript 84ab-testing 79ai-assistant 58claude-code-skills 57claude-code-plugin 56data-analysis 51geo 49seo 49ai-scientist 44coding-agents 44marketing 44open-source 44dashboard 43

rag-evaluate-quality

193

lyonzin/knowledge-rag

Skill Claude CodeCodex

Periodically measure the retrieval quality of the knowledge base using evaluateretrieval (MRR@5, Recall@5, Precision@5) plus getindexstats for health metrics. Run weekly, after significant reindex activity, or when the user reports declining answer quality. Prevents silent index rot and grounds "should we tune X"…

not rated 269 +7 yesterday A 78 tokens original MIT

frontend

194

speakeasy-api/gram

Skill Claude CodeCodex

Rules and best practices when working on the dashboard React frontend codebase (including the inlined Gram Elements code).

not rated 266 +1 today A 24 tokens AGPL-3.0

layerlens

195

LayerLens/stratix-python

Skill Claude CodeCodex

Evaluate AI outputs with LayerLens. Upload traces, create judges, run evaluations, and retrieve quality scores -- all from within OpenClaw.

not rated 260 8d ago A 31 tokens original Apache-2.0

evalyn

196

shihongDev/evalyn

Skill Claude CodeCodex

Use to evaluate an LLM agent with evalyn. Orchestrates the full pipeline: install, instrument, trace, build dataset, suggest metrics, run eval, analyze, calibrate.

not rated 257 3mo ago A 41 tokens original MIT

maxanatsko/mcp-engine-public

Skill Claude CodeCodex

Use when a DAX query, measure, or visual is slow, when interpreting analyze timings, Storage Engine / Formula Engine splits, or query plans, when VertiPaq storage size or cardinality drives cost, or when the user wants a tuning pass or before/after benchmark. For wrong values, use mcp-engine-dax-debugging; for writing…

not rated 256 +1 8d ago A 101 tokens

recursive-improve

198

kayba-ai/recursive-improve

Skill Claude CodeCodex

End-to-end agent improvement pipeline. Analyzes raw execution traces, extracts insights, manages a skillbook, gathers domain context, defines metrics, builds a rubric, creates a prioritized action plan, presents it for review, and implements approved fixes. Trigger when the user says "improve my agent", "run the…

not rated 253 +3 5mo ago A 89 tokens original Apache-2.0

graphsignal-profiler

199

graphsignal/graphsignal-profiler

Skill Claude CodeCodex

Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.

not rated 244 1mo ago A 74 tokens original Apache-2.0

command-center

200

jontsai/openclaw-command-center

Skill Claude CodeCodex

Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in one place.

not rated 244 4d ago A 38 tokens original MIT

ghealth

201

Google-Health-API/google-health-cli

Skill Claude CodeCodex

Query Google Health API v4 — steps, heart rate, exercise, sleep, weight, SpO2, HRV, ECG, blood glucose, nutrition, and 40 total data types.

not rated 238 +4 1mo ago A 41 tokens original Apache-2.0

prism-skill

202

destiny520537work-lab/fate-skill

Skill Claude CodeCodex

An educational framework for analysing US stocks through three fictional viewpoints: supply chains, the wider economy and chart-based trade execution.

not rated 236 +1 2mo ago A 59 tokens original MIT

stock-daily-analysis

203

chjm-ai/stock-daily-analysis-skill

Skill Claude CodeCodex

A stock-analysis tool for A-shares, Hong Kong stocks, and United States stocks. It calculates technical indicators and uses a configured language model to provide analysis and trading advice.

not rated 235 7mo ago A 102 tokens original MIT

aliyun/alibabacloud-aiops-skills

Skill Claude CodeCodex

A manager for Dataphin data-quality rules on tables and fields. These rules check conditions such as required values, uniqueness, allowed values, or enumerations, and can run on a schedule.

not rated 234 +8 yesterday A 276 tokens

a-share-data

205

shouldnotappearcalm/a-share-skill

Skill Claude CodeCodex

A data lookup skill for mainland Chinese A-shares, meaning stocks traded on China's Shanghai and Shenzhen exchanges. It covers prices, history, indicators, company events, sectors, concepts, market news, and macroeconomic data.

not rated 233 +2 2mo ago A 97 tokens original MIT

google-ads

206

TheMattBerman/google-ads-copilot

Skill Claude CodeCodex

Google Ads operator system for search-term analysis, intent mapping, wasted spend control, account structure decisions, tracking diagnostics, RSA generation, budget review, account planning, and full-account audits. Supports live API data (connected mode via google-ads-mcp) or manual exports (export mode). Produces…

not rated 231 2mo ago A 70 tokens original MIT

d3-viz

207

chrisvoncsefalvay/claude-d3js-skill

Skill Claude CodeCodex

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke…

not rated 228 +2 10mo ago A 87 tokens

mviz

208

matsonj/mviz

Skill Claude CodeCodex

A chart & report builder for AI. Use when the user asks to show, display, render, or visualize data as a chart (bar, line, pie, scatter, area, bubble, histogram, etc.), a table, KPI, big number, dashboard, report, sparkline, heatmap, sankey, funnel, calendar, waterfall, or any composed data visualization. Generates…

not rated 226 3mo ago A 106 tokens

mcp-metric-surface

209

jimmykane/quantified-self

Skill Claude CodeCodex

Keep the read-only Quantified Self MCP surface aligned when Sports Lib metrics, activity details, routes, Training-derived kinds, sleep sessions, or their persisted contracts change.

not rated 225 +2 today A 40 tokens

torchscan

210

frgfm/torch-scan

Skill Claude CodeCodex

Inspect and compare PyTorch models with TorchScan reports, operator FLOPs, and peak-memory workloads. Use when an agent must analyze model structure, parameters, compute, memory, regressions, unsupported operations, or an owner-provided model budget without inventing completeness.

not rated 222 5d ago A 56 tokens original Apache-2.0

origin-pro-mcp-skill

211

leima-max/origin-pro-mcp-skill

Skill Claude CodeCodex

Use this skill when the user wants to create, edit, style, fit, or export Origin Pro worksheets and figures through the origin-pro MCP server.

not rated 220 +39 3mo ago A 0 tokens original MIT

mcp

212

Piebald-AI/splitrail

Skill Claude CodeCodex

Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.

not rated 218 today A 26 tokens original MIT

ncu-report-skill

213

mit-han-lab/ncu-report-skill

Skill Claude CodeCodex

A guide for profiling CUDA kernels with NVIDIA Nsight Compute on B200 GPUs. A CUDA kernel is a GPU function whose execution can be measured for performance problems.

not rated 218 +10 9d ago A 72 tokens original MIT

opik-instrument

214

comet-ml/opik-mcp

Skill Claude CodeCodex

Add Opik tracing to an existing app and verify a real trace lands. Installs the Opik package, detects the language and LLM framework, adds the minimum tracing, runs a safe representative path, confirms a trace in Opik, and returns the trace link. Use for "instrument my code", "add opik tracing", "add observability"…

not rated 217 today A 101 tokens original Apache-2.0

kis-backtester

215

koreainvestment/kis-ai-extensions

Skill Claude CodeCodex

A tool for testing trading strategies against past market data. Backtesting means simulating how a strategy would have performed before using it in live trading.

not rated 212 +1 2mo ago A 187 tokens

tufte-data-viz

216

caylent/tufte-data-viz

Skill Claude CodeCodex

Use when creating, reviewing, or styling charts, graphs, dashboards, sparklines, or any data visualization. Applies to Recharts, ECharts, Chart.js, matplotlib, Plotly, seaborn, D3.js, and SVG. Enforces Tufte principles (data-ink ratio, direct labeling, range-frame axes) plus modern screen-first standards…

not rated 212 +3 6mo ago A 89 tokens original MIT

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: