16,285 tagged Analytics and metrics, measured the same way as everything else here.
Browse within: LLM 164agent 151agents 136javascript 97ab-testing 88skills 87agentic-ai 84seo 70ai-assistant 60cli 60claude-code-skills 59claude-code-plugin 57Evaluation 53dashboard 52
Skill Claude Code
Homer L6 — Sleep-time routing weight tuner. Mines Brain's decisions.jsonl + advisorcalls.jsonl, computes tier / model / guardrail distributions, and proposes routingmanifest.toml weight adjustments based on observed data. Aurora PROPOSES; the user decides. No auto-apply. Sacred Rule.
jleonceo/skill-adherencia-reglas
Skill Claude Code
Mide qué fracción de las reglas propias del proyecto se cumple de verdad, contándolo sobre el historial de sesiones que Claude Code ya guarda en disco. Se activa al preguntar si una norma, protocolo o convención se está aplicando, al revisar si un CLAUDE.md sirve de algo, al decidir si una regla debe pasar a ser hook…
Skill Claude Code
Use when running data pipeline workflows for data-pipeline-demo.
Not-Dev-Tech/codex-insights-local
Skill Claude CodeCodex
Gere um relatório local e somente leitura sobre sessões, tokens, modelos, reasoning effort, profiles, MCPs, ferramentas, skills, prompts repetidos, finalidades e objetivos do Codex CLI. Use para auditoria de consumo e recomendações de configuração.
agentic-control-plane/codex-acp-plugin
Skill Claude Code
Generate a cost X-ray report for your agent from ACP's metering — cache economics, context composition, tool bloat, loop share — before you ship it (or whenever spend surprises you).
Skill Claude CodeCodex
Analyze AI coding-agent runs and generate user-facing replay reports. Use when Codex needs to review Codex, Claude Code, OpenCode, Gemini CLI, or other coding-agent transcripts/logs; debug agent behavior; summarize file changes, commands, failures, interruptions, verification, and risks; or create Markdown/HTML…
yuri-semenenko/ai-engineering-workspace
Skill Claude Code
Web performance checklist — Core Web Vitals (LCP/INP/CLS), TTFB diagnosis, and frontend levers (JS/CSS/fonts/images/network/rendering) plus backend (DB N+1, API latency, caching, infra). Use when optimizing performance, diagnosing a slow page or unresponsive interaction, setting a performance budget, or reviewing a…
nielsvbrecht/victoriametrics-logs-mcp
Skill Claude CodeCodex
Specialized in system-wide troubleshooting using metrics and logs.
Skill Claude CodeCodex
You are running the Performance category of a Ship Score production readiness audit. Follow every instruction below precisely. Do not add checks beyond the 7 defined here. Do not skip checks. Report exactly what you find.
Skill Claude CodeCodex
Aggregate aestheticfindings, automatedfindings, and alignmentmeasurements into a single 1.0-10.0 beautyscore plus 7 weighted sub-scores and a 0.0-1.0 consistencyScore. Pure calculation step — never fails. Use during ui-specialist Phase 7 (Aggregation) AFTER all other ui- skills have completed and BEFORE writing the…
Jignesh-Gond/Power-BI-Master-Skill
Skill Claude CodeCodex
POWER BI MASTER SKILL by JG — The ultimate Power BI Automation and DAX Engineering standard. Master PBIX surgery, Lakh/Crore formatting, and high-performance DAX patterns. Compatible with Gemini CLI, OpenCode, and Agy CLI.
cherryjain-msft/awesome-fabric
Skill Claude CodeCodex
Comprehensive Power BI data model design review prompt for evaluating model architecture, relationships, and optimization opportunities.
Skill Claude CodeCodex needs its repo
A Japanese-language stock analysis skill for single companies listed on US stock exchanges such as the NYSE or NASDAQ. It uses Haruspex data to provide scores, outlooks, signals, trends, and related news.
Skill Claude CodeCodex
Use this server as the control plane for the unified fleet PLG stack (Grafana 12000, Prometheus 12001, Loki 12002).
Skill Claude CodeCodex
Queries U.S. Bureau of Labor Statistics data using the BLS MCP server. Use when user asks about CPI, inflation, unemployment, employment, wages, jobs, labor statistics, producer prices, or any economic indicator tracked by BLS. Maps natural language to correct series IDs and tools.
Skill Claude CodeCodex
Protocol-wide on-chain analytics for Limitless prediction markets on Base — trader P&L, top traders, market and daily volume history, liquidity events, and raw GraphQL, from the Limitless subgraphs on The Graph's decentralized network.
Skill Claude CodeCodex
You have access to a Whoop MCP server with 15 tools for reading biometrics and writing activities/journal entries. This skill teaches you how to use them like a coach, not a dashboard.
Skill Claude CodeCodex
Bộ não phân tích dành cho Claude, kết hợp với các Smart Tools của BOS MCP Server để giúp AI phân tích dữ liệu eCommerce một cách hiệu quả, tiết kiệm token và đưa ra insight chuyên sâu.
Skill Claude CodeCodex
Carbon-aware scheduling of AI tasks. Use this skill when the user asks to defer, schedule, or queue an AI task ("run this overnight", "do it when the grid is clean", "wait until off-peak"). Also use when the user explicitly asks about grid carbon intensity, AI energy cost, or wants a CO₂ receipt for a task they're…
Skill Claude CodeCodex
A Japanese-language assistant for managing GitHub Projects V2, GitHub's system for organizing issues and project work. It covers setup, daily project operations, reporting, sprint tracking, and migration from other tools.
Skill Claude CodeCodex
A command-line skill for querying data from the Korea Exchange (KRX), South Korea’s stock-market operator. It covers stocks, indices, funds, bonds, derivatives, commodities and ESG data.
Skill Claude CodeCodex
SpeechPulse is a voice emotion understanding MCP Server that analyzes speech audio to detect emotions, assess urgency, and detect sarcasm.
Skill Claude CodeCodex
Show Python visualizations live in the browser with the dataviz-mcp MCP tools (show, screenshot). Use when those tools are available and the user asks to display, plot, chart, or visualize anything. Do not use for apps the user serves themselves with panel serve.
Skill Claude CodeCodex
UniverCity MCP is a business consulting engine by CIA (Consultoría de Inteligencia Aplicada). It diagnoses any company across 11 dimensions and returns a Revenue Leak Score with actionable recommendations.
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: