Browse agent skills
Free SKILL.md packages for Claude Code, Codex, Cursor, Antigravity, Cowork and more. Filter by what you need — every listing links to the original source.
97 skills
Skill Creation Guide
davila7
Efficiently create and update Claude skills.
TypeScript Expert
davila7
Your go-to resource for TypeScript and JavaScript challenges.
Excel File Management
davila7
Efficiently create, edit, and analyze Excel files.
XLSX File Management
davila7
Efficiently create, edit, and analyze spreadsheet files.
Fine-Tuning with TRL
davila7
Align language models with human preferences using reinforcement learning.
Implementing LLMs with LitGPT
davila7
Train and implement LLMs efficiently using Lightning AI.
Gemini API Agent Platform
davila7
Integrate Google's Gemini API for enterprise AI applications.
NotebookLM Research Assistant
davila7
Query Google NotebookLM for precise, citation-backed answers.
PPTX Skill
davila7
Effortlessly manage .pptx presentations and content.
PPTX Skill
davila7
Easily create and manipulate PowerPoint presentations.
High-Performance LLM Serving
davila7
Optimize LLM API deployment with high throughput and low latency.
PDF Processing Pro
davila7
Efficiently manage complex PDF workflows with ease.
Senior ML/AI Engineer
davila7
Expertly productionize AI and ML models with advanced MLOps.
Regulatory Affairs Manager
davila7
Expert guidance for HealthTech and MedTech compliance.
CC Plugin Forge
davila7
Effortlessly create and manage Claude Code plugins.
BLIP-2 Vision-Language
davila7
Bridge vision and language with zero-shot capabilities.
MLflow
davila7
Manage the entire ML lifecycle with ease.
Long Context
davila7
Extend transformer context windows for long documents.
TensorBoard
davila7
Visualize and debug machine learning models effectively.
MoE Training
davila7
Efficiently train Mixture of Experts models with DeepSpeed.
LlamaIndex
davila7
Connect LLMs to your data with ease.
Causal Interventions with pyvene
davila7
Perform causal interventions on PyTorch models effortlessly.
Model Pruning
davila7
Compress LLMs and speed up inference with pruning techniques.
Knowledge Distillation
davila7
Compress large language models while retaining performance.