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. Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

    • Open source
    • 11.4K GitHub stars
  2. Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  3. Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, do

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  4. Build Gradio web UIs and demos in Python

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  5. Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  6. Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  7. Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/dataset

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  8. Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loadi

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  9. Track and visualize ML training experiments with Trackio

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  10. AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  11. Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript

    • Open source
    • 11.4K GitHub stars
    • Design and media
  12. Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training

    • Open source
    • 11.4K GitHub stars
  13. Runs a Trailmark summary analysis on a codebase

    • Open source
    • 8.2K GitHub stars
  14. Expands one confirmed or suspected vulnerability into a Trailmark graph neighborhood of variant candidates by finding sibling functions, sha

    • Open source
    • 8.2K GitHub stars
  15. Mutation-driven test vector generation

    • Open source
    • 8.2K GitHub stars
    • Knowledge and memory
  16. Hunts for the other instances of a bug already found — the variants of one root cause across a codebase

    • Open source
    • 8.2K GitHub stars
  17. This skill should be used when the user asks to "triage a vulnerability report", "assess a CVE", "evaluate a bug bounty submission", "decide

    • Open source
    • 8.2K GitHub stars
    • Security
  18. Writes and reviews structured Lean 4 proofs and designs Lean libraries following Mathlib conventions

    • Open source
    • 8.2K GitHub stars
  19. Builds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests

    • Open source
    • 8.2K GitHub stars
  20. Sets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-clang-fast or afl-gcc-fast

    • Open source
    • 8.2K GitHub stars
  21. Sets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer

    • Open source
    • 8.2K GitHub stars
  22. Sets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust projects

    • Open source
    • 8.2K GitHub stars
  23. Measures and interprets what a fuzzing campaign actually reaches, using llvm-cov, lcov, or a fuzzer's own coverage output

    • Open source
    • 8.2K GitHub stars
  24. Builds and applies fuzzing dictionaries so a fuzzer can produce the keywords, magic bytes, and tokens a target expects

    • Open source
    • 8.2K GitHub stars
  25. Patches past the barriers that stop a fuzzer making progress — checksum and hash verification, magic-value validation, time-based seeds, and

    • Open source
    • 8.2K GitHub stars
  26. Designs and improves fuzzing harnesses for C/C++ and Rust

    • Open source
    • 8.2K GitHub stars
  27. Builds custom fuzzers with LibAFL, the modular Rust fuzzing library

    • Open source
    • 8.2K GitHub stars
  28. Sets up and runs libFuzzer, the coverage-guided fuzzer built into LLVM, on C/C++ code that compiles with Clang

    • Open source
    • 8.2K GitHub stars
  29. Enrolls a project in OSS-Fuzz, Google's free continuous fuzzing service for open source, and drives it locally

    • Open source
    • 8.2K GitHub stars
  30. Sets up and runs Ruzzy, Trail of Bits' coverage-guided Ruby fuzzer and the only production-ready one for the language

    • Open source
    • 8.2K GitHub stars