AI & LLM Engineering · For developers

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

NVIDIA/skills

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.

NVIDIA/skills

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

NVIDIA/skills

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM…

NVIDIA/skills

MoE expert-parallel communication overlap in Megatron Bridge.

NVIDIA/skills

Representative, point-in-time MoE training playbooks by hardware and model family.

NVIDIA/skills

Long-context MoE training guidance for Megatron Bridge. An agent skill from NVIDIA/skills.

NVIDIA/skills

Practical guidance for training MoE VLMs in Megatron Bridge.

NVIDIA/skills

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

NVIDIA/skills

The FLUX craft skill (Black Forest Labs) — generate and edit on-brand images with the right variant and license.

social-media-skills/skills

A skill your agent uses when explicit manual re-discovery of team context modules is wanted beyond the injected CDR index (/team-discover) — produces a structured match table with relevance…

tikalk/adlc-team-skills

A skill your agent uses when coordinating continuous improvement loops (team-levelup + change + evals feedback + cleanup) targeting team-ai-directives — includes build-to-delete pruning and…

tikalk/adlc-team-skills

Shallow, text-only triage of a GitHub issue on pytorch or torch-xpu-ops.

intel/torch-xpu-ops

Guide an OpenART agent or contributor through planning, running, extending, and debugging the framework.

AI45Lab/OpenART

Multi-agent orchestration patterns for production deployments.

LeoYeAI/openclaw-master-skills

Meta-skill for building and publishing agent skills on ClawHub.

LeoYeAI/openclaw-master-skills

Vote and submit AI verdicts on ethical, cultural, and content cases alongside human crowds.

LeoYeAI/openclaw-master-skills

Version tracking for Agent Skills bundles and their associated files across sessions, surfaces, and platforms.

LeoYeAI/openclaw-master-skills

Integrate OpenAI Agents SDK with You.com MCP server - Hosted and Streamable HTTP support for Python and TypeScript.

LeoYeAI/openclaw-master-skills

A skill your agent uses when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress…

Asymmetric-al/core

A skill your agent uses when analyzing an existing TypeScript or JavaScript codebase to decide where and how to introduce Inngest.

Asymmetric-al/core

Route ambiguous or mixed Phoenix/LiveView/Ecto requests; Use when user is unsure where to start/how to approach work…

oliver-kriska/claude-elixir-phoenix

Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

Implement small Phoenix changes without planning — add validations; Use for single-file edits under 50 lines.

oliver-kriska/claude-elixir-phoenix

Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations.

oliver-kriska/claude-elixir-phoenix

Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10 types), context trust labels against…

AnastasiyaW/codex-claude-code-config

Machine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment tracking, and model explainability.

AnastasiyaW/codex-claude-code-config

Search relevance and ranking on OpenSearch/Elasticsearch for a two-sided marketplace — candidate retrieval (hybrid BM25 + kNN, RRF, two-tower EBR), base relevance (BM25F, multimatch, LambdaMART)…

pproenca/dot-skills

Builds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained .skill bundle (BM25 index + bundled searcher + query protocol).

oaustegard/claude-skills

Optimize transformer attention with Flash Attention — 2-4x speedup, 10-20x memory reduction for long sequences on CUDA GPUs.

AlexAI-MCP/hermes-CCC

HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API.

AlexAI-MCP/hermes-CCC

Run quantized LLMs locally with llama.cpp — CPU+GPU inference, GGUF format, OpenAI-compatible server, and Python bindings.

AlexAI-MCP/hermes-CCC

High-performance vector search engine for production RAG — Rust-powered, horizontal scaling, hybrid dense+sparse search, metadata filtering.

AlexAI-MCP/hermes-CCC

Deploy and serve LLMs with vLLM — OpenAI-compatible inference server with PagedAttention, continuous batching, and quantization support.

AlexAI-MCP/hermes-CCC

OpenAI Whisper for speech recognition and transcription — local inference, multiple model sizes, language detection, and subtitle generation.

AlexAI-MCP/hermes-CCC

Create a minimal working Langfuse trace example. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Install and configure Langfuse SDK authentication for LLM observability.

jeremylongshore/tons-of-skills-marketplace

Debug complex Claude API issues including context window overflow, tool use failures, streaming corruption, and response quality problems.

jeremylongshore/tons-of-skills-marketplace

Configure CI/CD pipelines for Anthropic Claude API integrations.

jeremylongshore/tons-of-skills-marketplace

Create a minimal working Anthropic Claude Messages API example.

jeremylongshore/tons-of-skills-marketplace

Install and configure Anthropic Claude SDK authentication for Python and TypeScript.

jeremylongshore/tons-of-skills-marketplace

Identify and avoid common Claude API anti-patterns and integration mistakes.

jeremylongshore/tons-of-skills-marketplace

Implement load testing, auto-scaling, and capacity planning for Claude API.

jeremylongshore/tons-of-skills-marketplace

Migrate to Claude API from OpenAI, Gemini, or other LLM providers.

jeremylongshore/tons-of-skills-marketplace

Execute production deployment checklist for Claude API integrations.

jeremylongshore/tons-of-skills-marketplace

Implement reliability patterns for Claude API: circuit breakers, graceful degradation, idempotency, and fallback strategies.

jeremylongshore/tons-of-skills-marketplace

Apply production-ready Anthropic SDK patterns for TypeScript and Python.

jeremylongshore/tons-of-skills-marketplace

Upgrade Anthropic SDK versions and migrate between Claude API versions.

jeremylongshore/tons-of-skills-marketplace