Skip to content

Instantly share code, notes, and snippets.

@VictorTaelin
VictorTaelin / mini_termination_checker_via_fold_generation.hs
Last active June 3, 2026 02:40
Mini Termination Checker Via Fold Generation
-- ============================================================================
-- MINI TERMINATION CHECKER VIA FOLD GENERATION
-- finding the legal recursive calls of a clause, without comparing sizes
-- ============================================================================
--
-- Everything here is written in the term language and nothing else:
--
-- x a variable
-- λx. e a lambda
-- (f x) application (n-ary: (f x y))
@aparente
aparente / SKILL.md
Last active June 21, 2026 11:30
tufte-viz Claude Code skill — Edward Tufte data visualization principles

name: tufte-viz description: | Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4) Deciding between visualization approaches (5) Reducing chartjunk or improving data-ink ratio (6) Planning small multiples or high-density displays

@evelynmitchell
evelynmitchell / ensure-fresh-branch.sh
Created February 23, 2026 02:38
Claude hook to make new branch before starting to plan
#!/usr/bin/env bash
# Hook: ensure-fresh-branch.sh
# Fires on SubagentStart(Plan).
# Ensures we're on a fresh branch before starting any new task planning.
# save as .claude/hooks/ensure-fresh-branch.sh
#
# Behavior:
# - Non-Plan subagent: no-op (exit 0 immediately)
# - On master/main: fetches latest, creates claude/task-<slug> branch
# - On a branch with a merged PR: switches to master, creates new branch
@robzolkos
robzolkos / interview.md
Created December 28, 2025 20:39
Claude Code Interview command by Thariq
description Interview me about the plan
argument-hint
plan
model opus

Read this plan file $1 and interview me in detail using the AskUserQuestionTool about literally anything: technical implementation, UI & UX, concerns, tradeoffs, etc. but make sure the questions are not obvious.

how is the morph warp search tool working for you so far? Is it reliable and effective at finding relevant code? Use ultrathink

● Honestly, I haven't actually used the mcp__morph-mcp__warp_grep tool in this session at all. Let me reflect on why and give you a candid assessment:

My Actual Tool Usage This Session

I defaulted to the standard tools:

  • Grep for pattern searches (e.g., screenshot in deployment-monitor.sh)
  • Read for reading specific files I already knew about
# /// script
# dependencies = [ "transformers", "accelerate" ]
# ///
# run on 2xH200 rented from primeintellect.ai
import gc
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
@VictorTaelin
VictorTaelin / hard_ai_debugging_prompt.txt
Last active March 1, 2025 23:03
Hard AI Debugging Prompt / SupTT Codebase
This is a debugging challenge.
Read the document below, and identify the bug.
---
# The Interaction Calculus
The Interaction Calculus (IC) is term rewriting system inspired by the Lambda
Calculus (λC), but with some major differences:
1. Vars are affine: they can only occur up to one time.
@zackradisic
zackradisic / index.ts
Created February 14, 2025 20:42
Visitor pattern vs sum types and pattern matching
// First, let's look at the traditional visitor pattern
// This is how we might implement a simple expression evaluator
// Traditional Visitor Pattern
namespace Traditional {
// Abstract base class for expressions
abstract class Expr {
abstract accept<T>(visitor: ExprVisitor<T>): T;
}
@ngxson
ngxson / FAQ.md
Last active August 5, 2025 17:29
convert ARM NEON to WASM SIMD prompt

Why did you do this?

Relax, I only have one Sunday to work on idea, literally my weekend project. So I tried Deepseek to see if it can help. Surprisingly, it works and it saves me another weekend...

What is your setup?

Just chat.deepseek.com (cost = free) with prompts adapted from this gist.

Does it work in one-shot or I have to prompt it multiple times?

@Maharshi-Pandya
Maharshi-Pandya / contemplative-llms.txt
Last active May 29, 2026 06:22
"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