Agent Skill
Tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualizati…
Data Analysis & ML
Spreadsheets, statistics, dashboards, data science and machine learning.
156 prompts
Agent Skill
Weights and Biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative ML…
Agent Skill
Implementing LLMs Litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, e…
Agent Skill
Distributed LLM Pretraining Torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom mode…
Agent Skill
Evaluating LLMs Harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic…
Agent Skill
Peft Fine Tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <…
Agent Skill
Pytorch Fsdp
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
Agent Skill
Long Context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), exten…
Agent Skill
Ray Data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales f…
Agent Skill
Llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engine…
Text
Test Quality Analyzer
Analyze test suite quality with comprehensive metrics and improvement recommendations
Text
Estimate Assistant
Generate accurate task estimates using historical data, complexity analysis, and team velocity metrics
Text
Retrospective Analyzer
Analyze team retrospectives with quantitative metrics and actionable insights generation
Text
Team Velocity Tracker
Track and analyze team velocity with predictive forecasting and performance optimization recommendations
Text
Add Performance Monitoring
Setup comprehensive application performance monitoring with metrics, alerting, and observability
Text
Sync Contacts To Sheet
Export Google Contacts directory to a Google Sheets spreadsheet.
Text
Compare Sheet Tabs
Read data from two tabs in a Google Sheet to compare and identify differences.
Text
Create Events From Sheet
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
Text
Backup Sheet As Csv
Export a Google Sheets spreadsheet as a CSV file for local backup or processing.
Text
Game Analytics & Player Intelligence System
Use PROACTIVELY to implement game analytics systems with player behavior tracking, performance monitoring, and business intelligence integration
Custom Agent
Computer Vision Engineer
Use this agent for image/video analysis systems requiring classical or trainable CV models: object detection, face recognition, OCR/document analysis, real-time video an…
Custom Agent
LLMs Maintainer
LLMs.txt roadmap file generator and maintainer for AI Engine Optimization (AEO). Use PROACTIVELY after build completion, content/routing changes, or when setting up AI c…
Text
充当 Solr 搜索引擎
我希望您充当以独立模式运行的 Solr 搜索引擎。您将能够在任意字段中添加内联 JSON 文档，数据类型可以是整数、字符串、浮点数或数组。插入文档后，您将更新索引，以便我们可以通过在花括号之间用逗号分隔的 SOLR 特定查询来检索文档，如 {q='title:Solr', sort='score asc'}。您将在编号列表中提供三个命令…
Text
作为专业DBA
贡献者：[墨娘](https://github.com/moniang) 我要你扮演一个专业DBA。我将提供给你数据表结构以及我的需求，你的目标是告知我性能最优的可执行的SQL语句，并尽可能的向我解释这段SQL语句，如果有更好的优化建议也可以提出来。 我的数据表结构为: CREATE TABLE user ( id int NOT NU…