53 boosters for "monitoring" — open source, verified from GitHub, ready to install
Weibo Strategist is an AI agent that helps brands navigate Sina Weibo's ecosystem—from trending topics and community management to sentiment monitoring and fan economy strategies—enabling viral reach and sustained growth on China's leading social platform.
Model QA Specialist is an independent auditing agent that performs comprehensive ML/statistical model validation—from documentation review and data reconstruction through calibration testing, interpretability analysis, and audit-grade reporting. It's ideal for data scientists, ML engineers, and compliance teams who need rigorous, end-to-end model validation.
An AI agent that automatically monitors and extracts key sales metrics (MTD, YTD, Year End) from Excel files for real-time internal reporting. Ideal for sales teams and business analysts who need automated data pipeline extraction without manual spreadsheet parsing.
A Claude Code plugin that shows what's happening — context usage, active tools, running agents, and todo progress. Always visible below your input.  
Provides complete specifications and role prompt templates for 37 specialized agent types in a dynamic multi-agent system, enabling developers to configure and monitor Claude-based agents across projects of varying complexity.
Train language models using TRL (Transformer Reinforcement Learning) on fully managed Hugging Face infrastructure. No local GPU setup required—models train on cloud GPUs and results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Use Unsloth () instead of standard
Train object detection, image classification, and SAM/SAM2 segmentation models on managed cloud GPUs. No local GPU setup required—results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Helper scripts use PEP 723 inline dependencies. Run them with :
A skill for fine-tuning and training language models on Hugging Face's cloud GPU infrastructure using TRL, supporting SFT, DPO, GRPO methods and GGUF conversion for local deployment. Developers and ML engineers working with cloud-based model training benefit from this comprehensive guidance.
"name": "claude-seo", "description": "Comprehensive SEO analysis skill for Claude Code. 20 core sub-skills covering technical SEO, content quality (E-E-A-T), schema markup, image optimization, sitemap architecture, AI search optimization (GEO), local SEO, maps intelligence, semantic topic clustering
"name": "spec-workflow-mcp", "description": "MCP server for structured spec-driven development with real-time web dashboard and VSCode extension.", "homepage": "https://github.com/Pimzino/spec-workflow-mcp",
You weed the Allium garden. You compare specifications against implementation code, find where they have diverged, and help resolve the divergences. 1. Read for the Allium syntax and validation rules. 2. Read the relevant files (use to find them if not specified).
The Crisis Management Platform skill provides crisis response platform integration and real-time monitoring capabilities. This skill enables rapid crisis detection, coordinated response, and comprehensive documentation throughout crisis situations. This skill integrates with the following PR process
This module focuses on learning the language transition from JavaScript to Python, helping developers quickly master Python programming through comparative teaching. console.log("Hello World"); print("Hello World")
"version": "0.25.0", "description": "Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.", "email": "support@datadoghq.com"
Control tmux windows programmatically: create windows, send commands, capture output, and manage processes. Each window gets full screen space for easier output tracking. Window names are visible in the tmux status bar for easy identification. For commands that write to a file (cleaner than capturin
Monitor Agent Mail messages for coordination across agents. For active threads with multiple messages: Read for the display template and example session.
1. Incorrect values (must be , , or ) 2. Missing on energy sensors 3. Wrong for utility_meter entities (must be )
"name": "claude-dashboard", "version": "1.29.0", "description": "Unified status line for Claude Code with multi-CLI (Claude, Codex, Gemini, z.ai) usage monitoring, context, rate limits, and cost tracking",
This booster enables developers to manage Alibaba Cloud CDN operations—including domain onboarding, cache management, and certificate updates—directly through an AI coding assistant with OpenAPI/SDK integration. It's valuable for teams building or maintaining CDN infrastructure on Alibaba Cloud.
This skill provides comprehensive guidance for all aspects of Playwright test development, from writing new tests to debugging and maintaining existing test suites. Consult these references based on what you're doing:
Graphsignal observes inference workloads from a sidecar process — the profiler. It never shares a process with CUDA: the profiler watches the workload externally via CUPTI, OTLP/gRPC, Prometheus scraping, and NVML. Auto-instrumentation covers vLLM, SGLang, and PyTorch out of the box. Two install pat
"description": "Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage",
This MCP server integrates Dynatrace monitoring and observability capabilities into Claude and Copilot, enabling developers to query application performance data, logs, and metrics directly within AI assistants. It benefits DevOps engineers, SREs, and developers who need real-time access to Dynatrace insights during troubleshooting and development workflows.
