Skip to content

Agent skills for Claude Code

3,385 agent skills for Claude Code, out of 3,419 agent skills listed. Popular ones include Skill creator, Rea analysis optimization and Rea changelog update. Claude Code reads the SKILL.md folder format, so each skill here can be copied into ~/.claude/skills. Each one lists what it can run and the steps to install it.
  1. Architect enterprise Gemini agent platforms on Google Cloud: network, identity, policy

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  2. Deploy Model Garden models to Agent Platform endpoints with cost checks and cleanup

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  3. Evaluate and iteratively improve AI agents on Google Cloud with an eval flywheel

    • Open source
    • 24.4K GitHub stars
    • AI models and LLM tooling
  4. Call Gemini, open models and custom endpoints on Google Cloud; debug 429 and 404 errors

    • Open source
    • 24.4K GitHub stars
    • AI models and LLM tooling
  5. Upload, list, update and delete models in the Agent Platform Model Registry

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  6. Create, list, version and delete managed prompts in Google Agent Platform via Python

    • Open source
    • 24.4K GitHub stars
    • AI models and LLM tooling
  7. Search, upload and manage skills in the Gemini Enterprise Agent Platform Skill Registry

    • Open source
    • 24.4K GitHub stars
    • AI models and LLM tooling
  8. Diagnose Agent Gateway, IAP, Model Armor and DNS failures on Google's agent platform

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  9. 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
  10. Administer AlloyDB for PostgreSQL clusters, instances and backups with secure defaults

    • Open source
    • 24.4K GitHub stars
    • Databases
  11. 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
  12. Run a cloud-trial acceptance test on a GPU cluster and write a dated report

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

    • Open source
    • 19.7K GitHub stars
    • Developer tools
  14. 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
  15. 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
  16. Read the local AWS profile, region and caller identity before touching an AWS account

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

    • Open source
    • 11.4K GitHub stars
    • Developer tools
  18. 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
  19. 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
  20. 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