MCP App StoreMCP App StoreThis skill produces polished narrative summaries and timestamped event lists from recorded video clips. It prefers a local LVS summarization microservice (with a human-in-the-loop step to collect scenario/events) and falls back to a VLM-based summarizer when the service is unreachable. The skill includes routing logic, readiness probes, and curl examples to call the appropriate backend.
Use this skill when you need a concise, actionable summary of a recorded video (e.g., activity monitoring, incident review, warehouse/industrial monitoring). It is intended for post-hoc summarization of stored clips — not for live RTSP captioning or full-archive semantic search.
references/ folder with API and deployment docs for summarization, debugging, and HITL prompts./v1/ready), mandatory HITL collection for LVS path, fallback VLM prompt, and examples for calling /v1/summarize or VLM chat completions.Best used by agent runtimes that can run shell curl commands and call internal services (Claude Code / Copilot-style agents or automation runbooks). The skill expects access to network endpoints and jq/curl on the host.
This skill has not been reviewed by our automated audit pipeline yet.
MoE Expert-Parallel Overlap (Megatron-Bridge)
Guidance and configs to enable expert-parallel communication overlap in Megatron-Bridge for MoE models — use to hide dispatch/combine latency and improve throug
Megatron CI/CD Guide
Reference guide to Megatron-LM CI/CD: pipeline structure, PR scope labels, triggering internal CI, and steps for investigating CI failures.
Video Analytics (VA-MCP)
Query incidents, alerts, sensor counts and metrics from a VA-MCP Elasticsearch backend (port 9901) to answer questions about violations, occupancy, speeds, and
AWP (Agent Work Protocol)
Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail
Monitoring Stack Deployer
Deploy and configure production-ready monitoring stacks (Prometheus, Grafana, Datadog) with collectors, dashboards, and alerting rules for Kubernetes, Docker, o
Azure External Attack Surface Management
Provides expert guidance for Azure External Attack Surface Management (EASM): quotas, configuration, integrations, and exporting inventory to analytics platform
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Algolia Cost Tuning
Practical guide to reduce Algolia billing by auditing records/requests, switching to virtual replicas, multi-query usage, caching, and cleanup strategies.