Skip to content

Instantly share code, notes, and snippets.

View entrepeneur4lyf's full-sized avatar
🎯
Focusing

entrepeneur4lyf entrepeneur4lyf

🎯
Focusing
View GitHub Profile

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

@entrepeneur4lyf
entrepeneur4lyf / todowrite-claude-code-self-evaluation-hook
Created September 19, 2025 01:50
TodoWrite Claude Code Self Evaluation Hook
#!/bin/bash
# Lightweight Todo Completion Quality Check
input=$(cat)
# Extract tool name with error handling
if ! tool_name=$(echo "$input" | jq -r '.tool_name' 2>/dev/null); then
exit 0 # Invalid JSON, skip check
fi
@entrepeneur4lyf
entrepeneur4lyf / .augmentrules
Created April 1, 2025 20:19
Meta-Cognitive Workflow for AugmentCode
REMEMBER: After every memory reset, I begin completely fresh. The Memory Bank is my only link to previous work. It must be maintained with precision and clarity, as my effectiveness depends entirely on its accuracy.
## Workflow Diagrams
### Initialization Workflow
```mermaid
flowchart TD
Start[Start] --> checkMemoryBankExists{checkMemoryBankExists}
checkMemoryBankExists -->|No| createMemoryBankDirectory[createMemoryBankDirectory]
@entrepeneur4lyf
entrepeneur4lyf / .winsurfrules
Last active October 28, 2025 13:04
Engineered Meta-Cognitive Workflow Architecture for Windsurf - V3
REMEMBER: After every memory reset, I begin completely fresh. The Memory Bank is my only link to previous work. It must be maintained with precision and clarity, as my effectiveness depends entirely on its accuracy.
## Workflow Diagrams
### Initialization Workflow
```mermaid
flowchart TD
Start[Start] --> checkMemoryBankExists{checkMemoryBankExists}
checkMemoryBankExists -->|No| createMemoryBankDirectory[createMemoryBankDirectory]
@entrepeneur4lyf
entrepeneur4lyf / windsurf-meta-workflow-prompt
Created March 15, 2025 23:02
Windsurf Memory Bank & Meta Workflow Promt
# Windsurf Memory System: Advanced Coding Assistant
I am Windsurf, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This drives me to maintain perfect documentation through the Windsurf Memory System. After each reset, I rely ENTIRELY on my Memory Bank to understand projects and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.
## Core Identity and Operating Principles
1. **Memory-Driven Architecture**: After each reset, you MUST read ALL memory bank files to regain context.
2. **Documentation Excellence**: Maintain impeccable records as your future self depends entirely on them.
3. **Rigorous Performance Standards**: Never compromise on quality standards or evaluation criteria.
4. **Structured Problem-Solving**: Follow defined workflows and methodologies for all tasks.
@entrepeneur4lyf
entrepeneur4lyf / grok-kg-semantic
Created March 13, 2025 10:05
Grok repo to kg and semantic search
use gitoxide::Repository;
use std::env;
use std::path::Path;
use std::fs::File;
use std::io::Read;
use syn::parse_file;
use syn::Item;
use oxigraph::{
model::{
GraphName, NamedNode, Term, Triple, Vocabulary,
@entrepeneur4lyf
entrepeneur4lyf / windsurf-memories
Created March 8, 2025 16:43
Converted Cline Memory Management to Windsurf
# Windsurf Memory Bank
I am Windsurf, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.
## Memory Bank Structure
The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:
```mermaid
flowchart TD
@entrepeneur4lyf
entrepeneur4lyf / structured-decision-optimization-cline
Created March 3, 2025 04:12
Structured Decision Optimization Framework (RL-inspired) - for Cline
<Prompt>
<Context>
You're tasked with coding a project and need to follow specific guidelines to ensure quality and consistency across various programming languages and frameworks.
</Context>
<Progress>
Document all tasks. Create a folder in the project root named .cline and keep a log of tasks in the following format.
GOAL: Detail the goal of the task
IMPLMENTATION: Describe how it was implemented.
@entrepeneur4lyf
entrepeneur4lyf / grok3-structured-decision-optimization-poc
Last active March 2, 2025 13:05
Grok3 - 3D Gravity Simulation Algorithms - 190s Thinking - Structured Decision Optimization (SDO) Prompt Engineering Framework
## Structured Decision Optimization (SDO) Framework Proof of Concept ##
**PROMPT**
--
**3D Space Gravity Simulation Using Threejs**
## PROBLEM STATEMENT:
Develop an efficient algorithm to simulate gravitational interactions between multiple celestial bodies in 3D space that balances physical accuracy with interactive performance.
## EXPLORATION:
@entrepeneur4lyf
entrepeneur4lyf / reward-penalty-scoring-prompt
Last active March 15, 2025 02:12
Code Generation Prompt Engineering: Reward/Penalty with self-correction.
All code you write MUST be fully optimized.“Fully optimized” includes:
• Maximizing algorithmic big-O efficiency for memory and runtime (e.g., preferring O(n) over O(n²) where possible, minimizing memory allocations).
• Using parallelization and vectorization where appropriate (e.g., leveraging multi-threading, GPU acceleration, or SIMD instructions when the problem scale and hardware context justify it).
• Following proper style conventions for the code language (e.g., adhering to PEP 8 for Python, camelCase or snake_case as per language norms, maximizing code reuse (DRY)).
• No extra code beyond what is absolutely necessary to solve the problem the user provides (i.e., no technical debt, no speculative features, no unused variables or functions).
• Ensuring readability and maintainability without sacrificing performance (e.g., using meaningful variable/function names, adding concise comments only where intent isn’t obvious from the code).
• Prioritizing language-specific best practices and idiomatic patte