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. Guides an agent through migrating Airflow DAGs to Airflow 2.11.1 or Airflow 3 on Managed

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  2. Guides tuning and best practices for Google Cloud Managed Airflow environments using

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  3. Diagnoses failing, crashing or hung Pathways on Cloud JAX workloads running on GKE TPUs

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  4. Lets an agent list, inspect, update, comment on and close Google SecOps SOAR cases

    • Open source
    • 24.4K GitHub stars
    • Security
  5. Lets your agent write, validate, test and deploy YARA-L 2.0 rules in Google SecOps

    • Open source
    • 24.4K GitHub stars
    • Security
  6. Guides an agent through proactive threat hunting in Google SecOps using UDM queries

    • Open source
    • 24.4K GitHub stars
    • Security
  7. Guides an agent through deep Google SecOps incident and entity investigations

    • Open source
    • 24.4K GitHub stars
    • Security
  8. Guides an agent through triaging Google SecOps alerts and cases to close or escalate them

    • Open source
    • 24.4K GitHub stars
    • Security
  9. Guides an agent through Cloud Spanner provisioning, schema design, SQL and performance

    • Open source
    • 24.4K GitHub stars
    • Databases
  10. Lets an agent run Google Cloud Workload Manager evaluations and review their results

    • Open source
    • 24.4K GitHub stars
    • Databases
  11. Lets your agent read and manage Gerrit code reviews through its REST API

    • Open source
    • 24.4K GitHub stars
    • Developer tools
  12. Guides an agent through porting legacy C, C++, Fortran, Java or Python code to Safe Rust

    • Open source
    • 24.4K GitHub stars
    • Developer tools
  13. Guides agents through binding Google OAuth refresh tokens to a P-256 key with DPoP

    • Open source
    • 24.4K GitHub stars
    • Security
  14. Guides an agent through implementing and securing Google Sign-In on web apps

    • Open source
    • 24.4K GitHub stars
    • Developer tools
  15. Compiles, benchmarks and packages LiteRT models for Google Tensor Pixel TPUs

    • Open source
    • 24.4K GitHub stars
    • AI models and LLM tooling
  16. Builds and publishes a private Gradio Space that runs inference with a LoRA

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  17. Publish, index, link and claim research papers on the Hugging Face Hub

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  18. Reads Hugging Face and arXiv paper pages and metadata so the agent can analyze AI papers

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  19. Guides an agent to build, deploy and debug apps on Hugging Face Spaces

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  20. Builds reusable shell and Python scripts that fetch and process Hugging Face API data

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  21. Lets an agent log, alert on and query ML training experiment metrics with Trackio

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  22. Fine-tunes object detection, image classification and SAM segmentation models on Hugging

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  23. Guides agents writing Gradio code for ZeroGPU Spaces, covering @spaces.GPU limits

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  24. Guides an agent through training sentence-transformers embedding, reranker and sparse

    • Open source
    • 11.4K GitHub stars
    • Knowledge and memory
  25. Run Hugging Face machine learning models directly in JavaScript and TypeScript apps

    • Open source
    • 11.4K GitHub stars
    • Design and media
  26. Guides an agent through post-training LLMs with TRL: SFT, DPO, GRPO, KTO and reward models

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  27. Generates crypto test vectors that target mutants surviving existing test suites

    • Open source
    • 8.2K GitHub stars
    • Knowledge and memory
  28. Guides an agent to write, review and structure Lean 4 proofs in Mathlib style

    • Open source
    • 8.2K GitHub stars
    • Developer tools