23,484 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.
Operating instructions for charting with this pack — profile before you plot, aggregate in the session kernel before a spec, and look at the render (it comes back attached to the call) plus its diagnostics before calling a chart done. Use when plotting data, building charts or dashboards, exploring a CSV or parquet…
Reviews how a Claude Code session was conducted rather than what it shipped — classifies its shape, scores the run, flags where the context window went, and turns recurring cost into wire-ins for the skills it used or a named lever on the environment that caused it.
★not rated 0
changed 10d agoA
tokens not measured
originalMIT
Google Lighthouse CLI reference for auditing web performance, accessibility, SEO, and best practices. Use this skill when users need to analyze website performance, run audits, generate reports, or integrate Lighthouse into their workflow.
MCP server for Google's TimesFM 2.5 foundation model — give any AI agent zero-config time-series forecasting. Runs locally from the timesfm-mcp Python package.
★not rated 0 3mo agoA
tokens not measured
originalApache-2.0
MCP server "marketing-agent-eval-harness" as configured in Praharsh-Projects/marketing-agent-eval-harness. Runs locally from the marketing-agent-eval-harness Python package.
A locally running tool for collecting and analysing trending news. Its description does not specify which news sources or analysis functions it supports.
MCP server for managing Apache Superset — dashboards, charts, datasets, SQL Lab, access control, and more. Runs locally from the mcp-superset Python package. Needs 3 environment variables to run.
AI-Powered MCP server for KQL query execution with Natural Language to KQL (NL2KQL) conversion, intelligent schema memory, RAG-enhanced context assistance, and semantic search capabilities. Runs locally from the mcp-kql-server Python package.
Model Context Protocol server for Skore (experiment tracking and model evaluation). Runs locally from the skore-mcp Python package.
★not rated 0 5mo agoA
tokens not measured
originalMIT
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: