MCP App StoreMCP App Store
from megatron-lm16,208
Reference guide for Megatron-LM CI: pipeline structure, PR scope labels, triggering internal CI, and investigating CI failures.
Provides a concise, actionable CI/CD reference for contributors and maintainers of Megatron-LM. It documents the main workflow files, how pipeline scope is determined by PR labels, where images are published, how to trigger internal GitLab CI, and pragmatic steps to investigate failing CI runs. Concrete commands and decision rules are included so maintainers can reproduce triggers and read logs.
Use this skill when you need to: diagnose failing CI jobs, decide which PR labels to attach to get the correct test scope, trigger internal CI without using the web UI, or understand how CI maps to pipeline stages (linting, container build, unit and integration tests). Trigger phrases: 'CI is red', 'how do I trigger CI', 'PR labels', 'where are the logs', 'pull-request branch'.
Best used by agents with GitHub CLI and repo inspection capabilities (e.g., GitHub-capable agents, Copilot/Code assistants that can run gh commands).
Reference-only CI/CD guide for Megatron-LM contributors covering pipeline structure, PR scope labels, internal GitLab CI triggering, and failure investigation. No bundled scripts — purely informational with well-structured bash snippets and decision tables. Clean security profile with no executable code, just documentation and example commands.
Pure documentation skill — no scripts to test. Well-written reference guide targeting a narrow audience (Megatron-LM contributors). Force-push in trigger_internal_ci.py could benefit from a stronger warning. Decision tables for PR labels are very clear and practical.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Scikit-learn (Classical ML reference)
Comprehensive scikit-learn guidance for classification, regression, clustering, preprocessing, model evaluation, and production-ready ML pipelines.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
Spring Boot Migration
Guided, phased migration for existing Spring Boot apps to Boot 4 / Java 25 (including Modulith 2 and Testcontainers 2), with scanners and reference guides.
ArcKit Architecture Conformance
Run a systematic architecture conformance assessment that compares ADRs and principles against HLD/DLD artifacts to surface drift, violations, and technical deb
Speak Security Basics
Security best practices for integrating Speak: API key management, audio data privacy, student data protection, and COPPA/FERPA compliance for production deploy
Replit — Advanced Troubleshooting
Step-by-step diagnostics and debugging techniques for deep Replit issues: Nix build failures, container crash loops, memory leaks, and platform vs app isolation