Explore

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

in the skill textJetson LLM Benchmark Reproducible Jetson benchmarks with **structured JSON output** so an agent can compare runs. Encodes the workflow from the Jetson AI Lab GenAI Benchmarking

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Creates, edits and benchmarks Agent Skills, with evals and description tuning for better triggering.

Official·Skill·Apache-2.0·No key

Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, compar

in the skill textuse `scripts/training/run_recipe.py`. 2. **Benchmark recipes** under `src/megatron/bridge/perf_recipes/` are for upper-bound throughput benchmarks. They own their canonical benchmark data and settings and should not be presented

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, Mean-Variance/SOCP variance caps, efficient frontiers, scenario generation, or NVIDIA cuOpt.

in the skill textProduce a weights-by-risk-aversion table. - Backtest an optimized portfolio against benchmarks. - Rebalance a portfolio on a schedule or drift trigger. - Run workflows

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

A lightweight, lightning-fast, in-process vector database

in the skill textEnglish | 中文 🚀 Quickstart | 🏠 Home | 📚 Docs | 📊 Benchmarks | 🔎 DeepWiki | 🎮 Discord | 🐦 X (Twitter) **Zvec** is an open-source, in-process vector database — lightweight, lightning-fast, and designed to embed

Skill·Apache-2.0·★ 16k·No key

Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignm

in the skill textcuration, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Selects a base model for the user's use case by querying SageMaker Hub. Use when the user asks which model to use, wants to select or change their base model, mentions a model name or family (e.g., "L

in the skill textthe exact Hub model ID must be resolved. Queries available models, presents benchmarks and licenses, and confirms selection. # Model Selection Guides the user through selecting

Official·Skill·Apache-2.0·★ 918 in collection·No key

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

in the skill textretains its upstream license. The public 1,000-skill demo, three agent benchmarks, and live SkillHub show the result. ## 🔥 Latest Updates - **2026-09-17 · v0.4.0

Skill·Apache-2.0·★ 685·No key

Dex is the agent-native analytics engineering toolkit. Point it at your warehouse and your dbt project. It learns the landscape, authors your transformations, and tells you exactly what to fix when th

in the skill textStack for Your Data Stack.     Run this

Skill·Apache-2.0·★ 78·No key

Physical AI Studio is an end-to-end framework for training robots to perform tasks through imitation learning from human demonstrations.

in the skill textbenchmark, and export policies programmatically. The library also supports LIBERO and RoboCasa benchmarks; see the benchmarking guide for suite-specific setup and checkpoint requirements. Copy the

Skill·Apache-2.0·★ 139·No key

Agent Skill for writing Golang code

in the skill textaround package design, constructors and config, interfaces, errors, logging, documentation, layout, and benchmarks. ## What this is The `go-style-guide` skill is a practical Go engineering

Skill·Apache-2.0·★ 38·No key

in the skill textTest ](  ** Quickstart ** · ** Guides ** · ** Manual workflows ** · ** Workbench docs ** · ** Shared access ** · ** Benchmarks ** · ** Operator tools ** · ** CLI reference ** · ** Python & API ** · ** Cookbooks ** · ** Contributing ** For a shared Workbench endpoint

Skill·Apache-2.0·★ 35·No key

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

in the skill textmethod in `references/15-decision-model-judge.md`. TypeSafe's own guidance, put zero weight on public benchmarks and earn trust on your own workload, is the same discipline Eval Genius

Skill·Apache-2.0·★ 17·No key

Raw documents (Markdown, HTML, plain text) → structured bridge format <D>?<H><B> — with adaptive compression that keeps you under token budget.

in the skill texttables | | 🌊 | **Streaming output** | Tokio stream delivers the first chunk immediately, minimizing TTFT | ### Benchmarks 48 documents, 3 formats, 15 languages — Apple M-series, `--release` build. Numbers below

Skill·Apache-2.0·★ 6·No key

Structured outline output for LLM prose — nested lecture-note format instead of paragraphs

in the skill textexplanation nodes. ## Contents 1. Motivation 2. Installation 3. Usage 4. Method 5. Benchmarks 6. Limitations 7. Future work 8. Documentation 9. Contributing 10. Reuse and training

Skill·Apache-2.0·★ 2·Few stars·No key

Lightweight prompt versioning, evals, benchmarks, and delivery

Skill·Apache-2.0·★ 3·Few stars·No key

Commercial real estate AI agent skills for CRE underwriting, due diligence, financing, brokerage, legal and closing workflows - standalone prompts for Claude Code, ChatGPT, Cursor, and other LLMs.

in the skill textfinancing fit, and IC memo writing - **4 office knowledge bases** covering office benchmarks, lease structures, TI/LC economics, and lender criteria - **12 office companion research notes** under

Skill·Apache-2.0·★ 117·No key