nemo-mbridge-perf-hierarchical-context-parallel
Provides operational guidance for hierarchical context parallelism. Covers configuration controls, relevant code locations, pitfalls, and verification.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides operational guidance for hierarchical context parallelism. Covers configuration controls, relevant code locations, pitfalls, and verification.
Examines commit metadata, code search, patches, repository history, and forks using tools such as trufflehog and gitleaks. Finds exposed secrets and organizational links for credential response, supply-chain reviews, and insider-threat investigations.
Provides an agent harness performance system for Claude Code and other AI coding agents. It includes skills, instincts, memory, hooks, commands, and security scanning.
Identifies Stockbee-style exhaustion setups using prior momentum, pullback depth, undercut and reclaim behavior, lower-wick geometry, and closing position. Applies volume confirmation, quality and liquidity gates, and risk-distance scoring.
Calls VIOS endpoints to list sensors, access timelines, extract clips, and retrieve snapshots. Also adds or deletes sensors and streams, excluding VLM inference and search.
Sets up vss-video-analytics-api with a configuration source, data-log bind, and Elasticsearch. Supports optional Kafka integration and excludes full warehouse deployment.
Examines specific k6 cloud tests and runs to explain failures or unusual behavior. Retrieves scripts, execution history, metrics, and logs, and can update the test script when requested.
Covers fault tolerance, straggler detection, and in-process restart in Megatron Bridge. Includes preemption handling and the re-run state machine.
Uses the Korea Heritage Service Open API to search official national heritage records. Retrieves heritage details, locations, and monthly heritage events.
Provides patterns for geographic data visualization, including choropleths, heat maps, 3D views, and animated data. Covers layer selection, color scales, data-driven styling, and performance optimization.
Provides fine-grained control over plot elements for novel visualizations and scientific workflows. Supports publication exports in PNG, PDF, and SVG formats.
Generates calibration using AutoMagicCalib with local MP4 files, RTSP streams, or the bundled sample dataset. Supports deploying vss-auto-calibration and excludes other calibration methods and runtime analytics.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name