Skip to content

Instantly share code, notes, and snippets.

View evrenesat's full-sized avatar
🤹‍♂️
🎱

Evren Özkan evrenesat

🤹‍♂️
🎱
View GitHub Profile
@evrenesat
evrenesat / summarize_anything_prompt.txt
Last active February 27, 2025 19:36
Summarize anything prompt
First determine if given text is an article or series of comments:
A) If you're sure content is an article, follow these steps:
1.) Start with a tl;dr about to subject.
2.) Analyze the input text and generate 5 essential questions that, when answered, capture the main points and core meaning of the text.
3.) When formulating your questions: a. Address the central theme or argument b. Identify key supporting ideas c. Highlight important facts or evidence d. Reveal the author's purpose or perspective e. Explore any significant implications or conclusions.
4.) Answer all of your generated questions one-by-one in detail. Finish each answer with a SHORT, single sentence summary of the answer.
Take into account length of article, so total length of your answers should not exceed 50% of article.
@evrenesat
evrenesat / contemplative-llms.txt
Created January 9, 2025 16:26 — forked from Maharshi-Pandya/contemplative-llms.txt
"Contemplative reasoning" response style for LLMs like Claude and GPT-4o
You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.
## Core Principles
1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference
/*
==UserScript==
@name Solarize
@match https://3.basecamp.com/3788301/*
@match https://github.com/solarmonkey/*
@version 1.0
==/UserScript==
*/
@evrenesat
evrenesat / kanbanize_userstyle.css
Last active November 22, 2019 14:42
Solarized theme for Kanbanize
/*
==UserCSS==
@name Kanbanize
@match https://solarmonkey.kanbanize.com/*
@version 1.0
@run-at document-start
==/UserCSS==
*/
@evrenesat
evrenesat / hosts
Created February 14, 2019 12:40 — forked from abelhadigital/hosts
# Blocklist for Android devices
# Blocking ad providers + analytics providers + phone home instances + resource wasters
#
# First release: 2017-09-16
# Last update: 2018-10-28
#
# License:
# CC Attribution 4.0 International (http://creativecommons.org/licenses/by/4.0/)
127.0.0.1 localhost
"use strict";
var amqplib = require("amqplib");
var format = require("string-format");
var DEVICE_SETTINGS = {
MODEL: "6‐diesel_generator_schema",
INSTANCE_NAME: "test_dg",
DEVICE_ID: "56090580e7e466125aa1c0a5",
INSTRUMENT: "generator",
WRITER: "power",
@evrenesat
evrenesat / init.lua
Last active July 14, 2016 08:29 — forked from rock3m/lm35-to-thingspeak.lua
-- Detects temperature using LM35. -- Periodically sends recordings to ThingSpeak. -- If current temp exeeds 25C, trigger an email via PushingBox
-- Original code taken from https://medium.com/grace-learns-iot/day-7-monitoring-home-temperature-on-the-internet-26c175ee7200
-- Detects temperature using LM35.
-- Periodically sends recordings to ThingSpeak.
-- If current temp exeeds 25C, trigger an email via PushingBox
--- Config
SSID = ""
PASSWORD = ""
THINGSPEAK_API_KEY = ""
@evrenesat
evrenesat / virtualenvwrapper_with_auto_activation.sh
Last active August 29, 2015 14:24
VirtualenvWrapper bash integration with auto activation on project directory
# Append this to end of ~/.bashrc
WORKON_HOME=~/.virtualenvs
. /usr/local/bin/virtualenvwrapper.sh
_virtualenv_auto_activate() {
if [ -e ".venv" ]; then
# Check to see if already activated to avoid redundant activating
_VENV_NAME=`cat .venv`
if [ "$VIRTUAL_ENV" != "$WORKON_HOME/$_VENV_NAME" ]; then
echo Activating virtualenv \"$_VENV_NAME\"...
VIRTUAL_ENV_DISABLE_PROMPT=1
#!/bin/env python
#This script scans for readable home dirs based on running process list (ps -ef)
#Can be used to test and warn the ignorant shared hosting users (Webfaction, I'm looking to you!)
import subprocess, os, re
psef=subprocess.Popen(['ps','-ef'], stdout=subprocess.PIPE).communicate()[0]
print filter(lambda h:os.access(h, os.R_OK), set(re.findall("(/home.?/\w*)", psef)))