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.

Showing 1,501–1,530 of 3,419

  1. Plan and conduct target-specific GDB, SWD/JTAG and OpenOCD or vendor-probe debugging

    • Open source
    • 32 GitHub stars
  2. Auto-generates professional README.md files for Arduino/ESP32/RP2040 projects following open-source best practices

    • Open source
    • 32 GitHub stars
    • Files and documents
  3. Design task ownership, control deadlines and overload behavior for an embedded controller running alongside sensors, networking or flash wri

    • Open source
    • 32 GitHub stars
    • Design and media
  4. Use when makers need calibration workflows for sensors such as CO2 sensors, load cells, magnetometers, color sensors, or analog sensors, inc

    • Open source
    • 32 GitHub stars
  5. Use when the main problem is a noisy or aliased analog/ADC signal and the task needs signal-chain diagnosis or filter-path selection across

    • Open source
    • 32 GitHub stars
    • Communication
  6. Build and diagnose STM32Cube HAL/LL projects using their existing CMake, Make, CubeIDE or PlatformIO toolchain

    • Open source
    • 32 GitHub stars
  7. Diagnose embedded USB enumeration, descriptors, CDC/REPL ports and intermittent disconnects

    • Open source
    • 32 GitHub stars
  8. Design and diagnose embedded telemetry, packet freshness and wireless coexistence using UDP, ESP-NOW or a serial bridge

    • Open source
    • 32 GitHub stars
  9. Use when wiring an Arduino, ESP32, ESP32-S3, Pico, or Pico W to sensors, LEDs, motors, relays, buses, or external supplies, especially when

    • Open source
    • 32 GitHub stars
  10. Build and debug Zephyr applications with west, devicetree, Kconfig and versioned workspaces

    • Open source
    • 32 GitHub stars
  11. Check planned AI coding actions and patches against explicit project constraints through SpecLock MCP tools

    • Open source
    • 26 GitHub stars
  12. Check planned AI coding actions and patches against explicit project constraints with SpecLock

    • Open source
    • 26 GitHub stars
  13. Two-layer AI-tell audit of any text — deterministic scanner (lexicon, constructions, stylometry with line numbers) plus a blind semantic jud

    • Open source
    • 25 GitHub stars
  14. One brief, N posts, N genuinely different people — voice-isolated writers, cross-post overlap detection, per-post verification receipts

    • Open source
    • 25 GitHub stars
    • Marketing and SEO
  15. Rewrite existing text so it reads human — either scrubbed-and-souled in its own register, or fully re-voiced as one of the roster's people

    • Open source
    • 25 GitHub stars
  16. Front door and router for the idiolect voice engine

    • Open source
    • 25 GitHub stars
  17. Build and maintain the user's OWN voice profile from continuously captured writing plus explicit samples — status, build/refresh, add sample

    • Open source
    • 25 GitHub stars
  18. Create a new voice profile — from a writing corpus (measured, not vibed), or invented to fill a gap in the roster

    • Open source
    • 25 GitHub stars
  19. Write a social post in one of the roster's voices (or the user's own `self` voice) — platform-native, craft-floored, scanner-verified

    • Open source
    • 25 GitHub stars
  20. Detect, activate, or deactivate bundled knowledge patches.

    • Open source
    • 25 GitHub stars
  21. Report bundled patch versions, activation state, age, and missing artifacts.

    • Open source
    • 25 GitHub stars
  22. Route technology work to matching bundled knowledge patches.

    • Open source
    • 25 GitHub stars
  23. Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons

    • Open source
    • 74.4K GitHub stars
    • Security
  24. Rewrite AI-sounding text so it reads like the writer without changing what it says

    • Open source
    • 70.1K GitHub stars
  25. When the user wants to write or judge ad creative, or asks which ad, hook, or angle to run or kill: headlines, primary text, and variations

    • Open source
    • 60.9K GitHub stars
  26. When the user wants to plan, run, or fix paid ads on Google, Meta, and LinkedIn, or asks a judgement call on them: are ads worth it, which c

    • Open source
    • 60.9K GitHub stars
  27. When the user wants to get cited and recommended in AI answers (ChatGPT, Perplexity, AI Overviews), or asks why AI cites a competitor, which

    • Open source
    • 60.9K GitHub stars
    • Marketing and SEO
  28. When the user wants to set up or audit analytics, or asks whether a metric or number is calculated right, what to track, or how to name even

    • Open source
    • 60.9K GitHub stars
    • Analytics and data