Skip to content

Instantly share code, notes, and snippets.

@a-c-m
a-c-m / reflection.md
Last active July 11, 2025 05:15
reflection.md - a way to have claude-code self improve its context.

You are an expert in prompt engineering, specializing in optimizing AI code assistant instructions. Your task is to analyze and improve the instructions for Claude Code. Follow these steps carefully:

  1. Analysis Phase: Review the chat history in your context window.

Then, examine the current Claude instructions, commands and config <claude_instructions> /CLAUDE.md /.claude/commands/*

@sotayamashita
sotayamashita / claude_desktop_config.json
Created May 22, 2025 09:00
How to Run DeepWiki MCP Server on Claude Desktop for Volta Users
{
"mcpServers": {
"deepwiki": {
"command": "<TODO: Replace with output from `which -a npx` (use the Volta path)>",
"args": [
"-y",
"mcp-remote",
"https://mcp.deepwiki.com/sse"
]
}

Coding Rules and Instructions

  1. Test-Driven Development (TDD) with pytest: Always write a failing test before writing implementation code (Red-Green-Refactor). Use pytest and pytest-fixtures for test setup, execution, and teardown.
  2. KISS (Keep It Simple, Stupid): Favor the simplest solution that meets the requirements.
  3. DRY (Don't Repeat Yourself): Avoid code duplication. Extract reusable logic into functions or classes.
  4. Standard Libraries and Tools: Utilize standard Python libraries (like datetime for date/time, requests for HTTP requests, and logging) and external libraries, including BeautifulSoup4 for HTML parsing, to avoid reinventing the wheel. Favor well-maintained and widely-used libraries.
  5. YAGNI (You Ain't Gonna Need It): Don't implement features or functionality unless they are currently required.
  6. SOLID Principles & Extensibility: Adhere to SOLID principles, promoting maintainability, testability, and future extension. Consider potential future requi
@iamhenry
iamhenry / custom_modes.yaml
Last active July 10, 2025 09:36
My Roocode Custom Modes Config
customModes:
- slug: security-auditor
name: 🛡️ Security Auditor
roleDefinition: Act as an expert security researcher conducting a thorough
security audit of my codebase. Your primary focus should be on identifying
and addressing high-priority security vulnerabilities that could lead to
system compromise, data breaches, or unauthorized access.
customInstructions: >-
Follow this structured approach:
@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.
@kleneway
kleneway / gist:c50903b277b159c313400d29b30f6298
Created January 21, 2025 22:10
Template to give to o1-pro to generate instructions for cursor composer agent mode (use sonnet 3.5 new)
<TEMPLATE>
<INSTRUCTIONS>
Use the <CODEBASE> code as reference, and convert the high-level <TASK> into a set of very detailed step-by-step instructions that an AI coding agent can complete.
Only includes steps an AI coding agent can take. Do not include testing or any other work a human would do to confirm the task has been completed.
ALWAYS have the agent run a build when it is complete. Be specific and decisive about what the agent should do.
Do not include any additional meta instructions to the user. Use markdown formatting.
</INSTRUCTIONS>
<TASK>
#Resume Phrase Matcher code
#importing all required libraries
import PyPDF2
import os
from os import listdir
from os.path import isfile, join
from io import StringIO
@thomwolf
thomwolf / gradient_accumulation.py
Last active November 23, 2024 20:53
PyTorch gradient accumulation training loop
model.zero_grad() # Reset gradients tensors
for i, (inputs, labels) in enumerate(training_set):
predictions = model(inputs) # Forward pass
loss = loss_function(predictions, labels) # Compute loss function
loss = loss / accumulation_steps # Normalize our loss (if averaged)
loss.backward() # Backward pass
if (i+1) % accumulation_steps == 0: # Wait for several backward steps
optimizer.step() # Now we can do an optimizer step
model.zero_grad() # Reset gradients tensors
if (i+1) % evaluation_steps == 0: # Evaluate the model when we...
http://www.oreilly.com/data/free/files/2014-data-science-salary-survey.pdf
http://www.oreilly.com/data/free/files/2015-data-science-salary-survey.pdf
http://www.oreilly.com/data/free/files/Data_Analytics_in_Sports.pdf
http://www.oreilly.com/data/free/files/advancing-procurement-analytics.pdf
http://www.oreilly.com/data/free/files/ai-and-medicine.pdf
http://www.oreilly.com/data/free/files/analyzing-data-in-the-internet-of-things.pdf
http://www.oreilly.com/data/free/files/analyzing-the-analyzers.pdf
http://www.oreilly.com/data/free/files/architecting-data-lakes.pdf
http://www.oreilly.com/data/free/files/being-a-data-skeptic.pdf
http://www.oreilly.com/data/free/files/big-data-analytics-emerging-architecture.pdf
@ashokpant
ashokpant / cuda_9.0_cudnn_7.0.sh
Last active October 15, 2024 08:56
Install CUDA Toolkit v9.0 and cuDNN v7.0 on Ubuntu 16.04
#!/bin/bash
# install CUDA Toolkit v9.0
# instructions from https://developer.nvidia.com/cuda-downloads (linux -> x86_64 -> Ubuntu -> 16.04 -> deb)
CUDA_REPO_PKG="cuda-repo-ubuntu1604-9-0-local_9.0.176-1_amd64-deb"
wget https://developer.nvidia.com/compute/cuda/9.0/Prod/local_installers/${CUDA_REPO_PKG}
sudo dpkg -i ${CUDA_REPO_PKG}
sudo apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/7fa2af80.pub
sudo apt-get update
sudo apt-get -y install cuda-9-0