Skip to content

Agent skills

Agent skills are folders of instructions and scripts that teach Claude Code, Codex, Cursor and other agents a task. Each one lists what it can run and how to install it.
  1. Fine-tune open models or Gemini on Google Agent Platform, from dataset to endpoint

    • Open source
    • 24.4K GitHub stars
    • AI models and LLM tooling
  2. Administer AlloyDB for PostgreSQL clusters, instances and backups with secure defaults

    • Open source
    • 24.4K GitHub stars
    • Databases
  3. Turn a REST API on Google Cloud API Gateway into a remote MCP server

    • Open source
    • 24.4K GitHub stars
    • AI models and LLM tooling
  4. Run a cloud-trial acceptance test on a GPU cluster and write a dated report

    • Open source
    • 19.7K GitHub stars
    • Cloud and infrastructure
  5. Practitioner runbook for training and serving large models, from GPUs to NaN loss spikes

    • Open source
    • 19.7K GitHub stars
    • Developer tools
  6. Search the Hugging Face Hub and run GPU jobs through the HF MCP server tools

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  7. Drive the Hugging Face Hub from the hf CLI: repos, buckets, jobs, endpoints and papers

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  8. Read the local AWS profile, region and caller identity before touching an AWS account

    • Open source
    • 11.4K GitHub stars
    • Cloud and infrastructure
  9. Create an isolated Python 3.12 virtual environment with current boto3 for SageMaker work

    • Open source
    • 11.4K GitHub stars
    • Developer tools
  10. Estimate GPU memory for a Hugging Face model's weights and KV cache without downloading it

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  11. Recommend top Hugging Face models for a task from official leaderboards and device limits

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  12. Run local evals on Hugging Face models with inspect-ai or lighteval and pick a backend

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  13. Explore Hugging Face datasets through the read-only Dataset Viewer API

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  14. Build Gradio web UIs, chatbots and ML demos in Python, and call Spaces from the CLI

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  15. Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  16. Find GGUF models on Hugging Face, pick a quant and serve them locally with llama.cpp

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  17. Guides an agent through press outreach, pitches, press pages and crisis statements

    • Open source
    • 60.9K GitHub stars
    • Marketing and SEO
  18. Guides design of referral, affiliate and partner programs and review campaigns

    • Open source
    • 60.9K GitHub stars
    • Marketing and SEO
  19. Builds a dated history of how a competitor grew and turns the gaps into marketing plays

    • Open source
    • 60.9K GitHub stars
    • Marketing and SEO
  20. Designs lead lifecycle, scoring, routing and pipeline rules that align marketing and sales

    • Open source
    • 60.9K GitHub stars
    • Sales and CRM
  21. Creates sales decks, one-pagers, objection docs, battle cards and demo scripts for reps

    • Open source
    • 60.9K GitHub stars
    • Sales and CRM
  22. Adds, fixes and validates schema.org JSON-LD markup for search engine rich results

    • Open source
    • 60.9K GitHub stars
    • Marketing and SEO
  23. Audits a site's crawlability, indexing, Core Web Vitals and on-page SEO for an agent

    • Open source
    • 60.9K GitHub stars
    • Marketing and SEO
  24. Guides agents through reviewing and improving signup, registration and trial-start flows

    • Open source
    • 60.9K GitHub stars
    • Marketing and SEO