intellectronica

Nano Banana Pro SKILL

Use this skill to create or edit images using Nano Banana Pro.

Installation

Unzip nano-banana-pro.zip into ~/.claude/skills or ~/.skillz/ or wherever you keep skills locally. Or upload it to the Claude app.

intellectronica

GitHub Copilot CLI SKILL

Use models like Gemini 3 Pro, GPT-5.1, and GPT-5.1-Codex from within Claude by invoking GitHub Coplit CLI.

Installation

1. Create ~/.claude/skills/github-copilot
2. Save SKILL.md to ~/.claude/skills/github-copilot/SKILL.md

intellectronica

ericflo

# opd_teacher_prefix.py
# -----------------------------------------------------------------------------
# On-Policy Distillation with:
#   - Student:  Qwen/Qwen3-4B-Base (trainable, LoRA, chat template with user-only)
#   - Teacher:  Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 (frozen, chat template with [big system + user])
#
# Enhancements:
#   * Deep W&B tracking (Accelerate tracker): losses, token stats, throughput, memory, histograms, samples
#   * FlashAttention-2 gating (attn_implementation="flash_attention_2" iff flash_attn is installed)
#   * Liger kernels (RMSNorm/RoPE/SwiGLU/etc.) if available; safe fallback

intellectronica

allowed-tools	Bash(/opt/homebrew/bin/codex *)
description	Run codex with GPT-5-high
argument-hint	your prompt text
model	haiku

Run the following command exactly. Don't modify it in any way.

tkafka

Electron Apps Causing System-Wide Lag on Tahoe

This script detects apps with not yet updated versions of Electron.

Repo: https://github.com/tkafka/detect-electron-apps-on-mac

See:

• electron/electron#48311 (comment)
• Michael Tsai: Electron Apps Causing System-Wide Lag on Tahoe

intellectronica

Promptify

Turn messy dictated instructions to AI into neat prompts that are easy to read and modify.

I do most of my prompting by dictation, usually in very confused and messy form. To be able to review these prompts and amend them before submitting them to the AI, I use this meta-prompt.

I use a Raycast AI Command which reads my clipboard and runs the prompt using Gemini 2.5 Pro. But this can work just as well with any recent LLM and driver.

---

marksweb

from django.apps import apps


def create_model_fixture(model):
    """
    This injects the model names as fixtures.
    eg def test_something(MyModel):
    will make the `MyModel` available in a test.
    """

judy2k

#!/bin/sh

# This script prints out the packages that have been installed by homebrew,
# along with a description of each package.
#
# This doesn't include packages that were installed as dependencies,
# only packages requested explicitly by the user.
#
# This script requires the following packages: jq, qsv

andreagrandi

...
"hooks": {
    "Notification": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "terminal-notifier -title \"🔔 Claude Code\" -message \"Claude needs your input\""
          }