Analytics and metrics

23,477 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

weekly-protocol

1994

lucas-antunes/growth-ops-blueprint

Skill Claude CodeCodex

Use quando o usuário pedir uma análise completa de performance, check semanal, check diário, ou "como está {{COMPANYNAME}}". Cobre todas as seções do negócio em modo diário ou semanal.

not rated 2 3mo ago A 45 tokens

codesurf-insights

1995

jasonkneen/codesurf-insights

Plugin Claude Code

Bundles 1 skill, 3 commands · 24 tokens together

Learn from conversation history to improve Claude Code performance. Analyzes logs for communication patterns, model understanding, assumptions, efficiency, and extracts actionable lessons.

not rated 2 8mo ago A tokens not measured

launchproof-web-audit

1996

raptorxde/LaunchProof-Web-Audit

Skill Claude CodeCodex

Audit an entire website or web app project for launch readiness, SEO completeness, compliance pages, analytics, robots/sitemap setup, responsive behavior, content gaps, competitor-informed positioning, and production polish. Use when asked to review, improve, QA, prepare, or checklist a site before launch or…

not rated 2 2mo ago A 105 tokens original MIT

finskills

1997

finskills/finskills

Skill Claude CodeCodex

Real-time financial data API for systematic stock analysis and quantitative investment research. Access stock quotes, historical OHLCV, batch screening, company fundamentals (income statement, balance sheet, cash flow), earnings estimates, analyst recommendations, options chains, institutional holders, macroeconomic…

not rated 2 4mo ago A 113 tokens original Apache-2.0

Kamrul5242/entrepreneur-business-intelligence-cfo

Skill Claude CodeCodex

Acts as a practical CFO, growth strategist, and operations analyst for founders and small businesses. Use whenever a user shares business numbers, revenue, expenses, ad spend, or a P&L; asks whether a business is profitable, sustainable, or running out of cash; asks about cash in vs cash out, burn, runway, margins…

not rated 2 changed 9d ago A 178 tokens

Saddss/cursor-skills

Skill Claude CodeCodex

Find the maximum sustainable QPS of an LLM inference service that meets a p50 e2e latency SLO using onlinereplay.py and a binary search. Use for maximum-QPS benchmarks, SLO-based performance tests, and optional serving configuration or feature tuning on local OpenAI-compatible servers.

not rated 2 15d ago A 67 tokens

data-max

2001

insanetic/data-max

Plugin Claude Code

Bundles 3 skills · 528 tokens together

Work with data end to end: review raw exports for warehouse readiness and cleanse them, transform them into clean warehouse-ready tables, and author versioned, DSL-compatible metric (data cube) and dimension definitions.

not rated 2 3mo ago A tokens not measured original MIT

ddggkkcc/industry-intelligence-researcher

Skill Claude CodeCodex

This skill should be used when conducting evidence-led industry, market, competitive, value-chain, business-model, or investment research across any sector. It converts broad questions into a decision-oriented research brief; combines official statistics, company filings, trade data, expert/participant evidence, and…

not rated 2 26d ago A 111 tokens original MIT

growth-percentile

2003

smallinaUCSD/growth-percentile-skill

Plugin Claude Code

Bundles 1 skill · 170 tokens together

Computes pediatric growth percentiles and z-scores (weight-for-age, length/height-for-age, weight-for-length/stature, BMI-for-age, head-circumference-for-age) against CDC and WHO growth standards, using a frozen deterministic engine instead of model arithmetic.

not rated 2 2mo ago A tokens not measured original MIT

t00-perf-check

2004

maysunAI/T00-zh

Command Claude Code

A command that checks a Claude Code setup, including automatically loaded instructions, token use, skills, and hooks. It is described in Chinese and produces a configuration report with optimization suggestions.

not rated 2 1mo ago A 29 tokens original MIT

stock-screener

2005

quantskills/skill-stock-screener

Skill Claude CodeCodex

A natural-language screener for shares listed in mainland China’s A-share market. It turns written investment filters into verified Pandadata API queries and returns matching stocks with supporting evidence.

not rated 2 1mo ago A 115 tokens GPL-3.0

jg-benchmarker

2006

JahnelGroup/multi-agents

Agent Claude Code

Utility agent for pulling benchmark data, evaluating cost vs performance, and recommending which models to use for which agents. Use on-demand for model assignment reviews.

not rated 2 2mo ago A 35 tokens

autoresearch

2007

misbahsy/autoresearch-skill

Skill Claude CodeCodex

Universal autonomous experimentation loop inspired by Karpathy's autoresearch. Give it any project with a measurable metric and tunable variables, and it runs experiments autonomously: modify, measure, keep or discard, repeat. Works for landing pages, ad campaigns, prompt engineering, RAG pipelines, checkout flows…

not rated 2 6mo ago A 111 tokens original MIT

grafana

2008

Bhoopesh123/MCP_Servers

MCP server Claude CodeCodexCursor +2

One of 2 in claude_desktop_config.json

MCP server "grafana" as configured in Bhoopesh123/MCPServers. Runs in Docker (mcp/grafana). Needs 2 environment variables to run.

not rated 2 8mo ago A tokens not measured

NICKNAME

2009

israel-salgado/dt-mcp-server

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "NICKNAME" as configured in israel-salgado/dt-mcp-server. Runs locally from the @dynatrace-oss/dynatrace-mcp-server npm package. Needs 1 environment variable to run.

not rated 2 4mo ago A tokens not measured original MIT

monitor-query

2010

Tobewont/monitor-mcp-server

Skill Claude CodeCodex

A query guide for reading monitoring data from Prometheus-compatible systems such as Prometheus, Thanos, Mimir, and VictoriaMetrics. Prometheus-compatible systems store time-based measurements about services, computers, containers, and Kubernetes.

not rated 2 2mo ago A 112 tokens original MIT

rescuetime

2011

sapientsai/rescuetime-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server "rescuetime" as configured in sapientsai/rescuetime-mcp-server. Runs ./dist/bin.js with node. Needs 1 environment variable to run.

not rated 2 3mo ago A tokens not measured original MIT

pudding-data-story

2012

tseng71/skills

Skill Codex

Build or revise reader-first interactive data stories and visual essays in the spirit of The Pudding. Use for Pudding-style websites, scrollytelling, scroll-driven graphics, interactive data journalism, data-backed longform features, animated visual explanations, storyboards, or audits of work that feels like a…

not rated 2 13d ago A 161 tokens original MIT

agentkaizen

2014

TheIllusionOfLife/AgentKaizen

Skill Claude CodeCodex

Use agentkaizen to measure and prove whether your AI coding agent actually follows instructions. Works natively — no installation required. Use this skill when: you want to score a recent Codex or Claude Code session and check rule compliance (did it branch before work? stay within tool limits?); you changed AGENTS.md…

not rated 2 6mo ago A 114 tokens original Apache-2.0

nonce

2015

noncehq/agent-skills

Skill Codex

Use this skill when the user needs to query, analyze, automate, or operate Nonce mining resources: workspaces, farms, miners, agents, task batches, miner tasks, metrics, history, or operational actions. It provides code-first access to the complete Nonce MCP tool set so the agent can filter and aggregate data before…

not rated 2 changed 4d ago A 88 tokens

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: