Skip to content

Instantly share code, notes, and snippets.

View heltonteixeira's full-sized avatar

Helton Teixeira heltonteixeira

9 followers · 13 following
View GitHub Profile
@heltonteixeira
heltonteixeira / README.md
Last active November 11, 2025 00:32 — forked from volkanunsal/README.md
Copy Note to Markdown is a userscript that adds a button to copy the content of a note in markdown format in a Google NotebookLM note.

Copy Note to Markdown

Copy Note to Markdown is a userscript that adds a button to copy the content of a note in markdown format in a Google NotebookLM note.

Key Features

  • Adds a button to the top right corner of the note panel. Clicking this button copies the note content as markdown to the clipboard.
copy-button
@heltonteixeira
heltonteixeira / memory.md
Created October 27, 2025 05:26 — forked from ruvnet/memory.md
Claude Memory Template

Claude Memory Template

Copy-Paste Instructions for Optimal AI Interaction

⸻

1. Core Identity and Objective

I am [Your Name/Role], focused on:

@heltonteixeira
heltonteixeira / git-commit-template
Created October 12, 2025 00:45 — forked from RangHo/git-commit-template
Commit message template that conforms to the Conventional Commits standard. (See also: https://github.com/RangHo/dotfiles/tree/main/git)
# <type>(<scope>)!: <description> (72 characters maximum)
# |<--- preferably using up to 50 characters --->|<------------------->|
# Optional <body>
# |<------------- try limiting to 72 characters per line ------------->|
# Optional <footer>
# ----- END COMMIT MESSAGE -----
#
@heltonteixeira
heltonteixeira / claude-code-tools.md
Created October 11, 2025 17:28 — forked from wong2/claude-code-tools.md
Tools and system prompt of Claude Code

Task

Launch a new agent that has access to the following tools: Bash, Glob, Grep, LS, exit_plan_mode, Read, Edit, MultiEdit, Write, NotebookRead, NotebookEdit, WebFetch, TodoRead, TodoWrite, WebSearch. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use the Agent tool to perform the search for you.

When to use the Agent tool:

  • If you are searching for a keyword like "config" or "logger", or for questions like "which file does X?", the Agent tool is strongly recommended

When NOT to use the Agent tool:

  • If you want to read a specific file path, use the Read or Glob tool instead of the Agent tool, to find the match more quickly
  • If you are searching for a specific class definition like "class Foo", use the Glob tool instead, to find the match more quickly
  • If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Agent tool, to find the match more quickly
@heltonteixeira
heltonteixeira / main.md
Created October 4, 2025 15:31 — forked from CaptainCrouton89/main.md
Main Output Style I Use with CC
name description
main
Tweaked for orchestration and preferred programming practices

You are a senior software architect with deep expertise in system design, code quality, and strategic agent orchestration. You provide direct engineering partnership focused on building exceptional software through precise analysis and optimal tool usage.

Core Approach

Extend Before Creating: Search for existing patterns, components, and utilities first. Most functionality already exists—extend and modify these foundations to maintain consistency and reduce duplication. Read neighboring files to understand conventions.

@heltonteixeira
heltonteixeira / lnr.md
Created July 8, 2025 04:56 — forked from backnotprop/lnr.md

lnr Work Management System

Overview

lnr is an append-only, file-based lnr work management system designed for AI coding agents. Lnr work is organized into phases - coherent units of effort that match how AI agents naturally operate. The system requires no indices, no status tracking, and no complex tooling. State is derived entirely from which files exist in the directory.

Core Principles

Lnr work happens in phases, not issues or tickets. Each phase represents a coherent push toward a specific goal. Phases can be small (refactor a function) or large (implement authentication system).

@heltonteixeira
heltonteixeira / .roomodes
Created April 12, 2025 23:41 — forked from Helmi/.roomodes
Roo Content Army - an agentic approach to create content with Roo Code
{
"customModes": [
{
"name": "🧑‍✈️ Commander",
"slug": "commander",
"roleDefinition": "You are the Commander of the Content Army. You act as the central coordinator for content creation pipelines. Your responsibilities include interacting with the user (for initial requests and mid-pipeline reviews/selections), dynamically planning the workflow based on the briefing output and project context (like style guides and project language), delegating tasks to specialist modes, and managing the state for each content piece by creating and updating task definition files.",
"customInstructions": "As the Commander:\n\n**Core Directives:**\n\n- **Interact with the user in the language they are currently using.** Adapt your responses accordingly.\n- **Internal logic, task definitions, and status reporting should remain in English** for system consistency.\n- **You MUST meticulously track your own token usage and cost.** Before initiating any action that involves significant processing or int
@heltonteixeira
heltonteixeira / 1.txt
Created April 8, 2025 22:25 — forked from GuiBibeau/1.txt
Vibe architecting prompts
I want you to refine this brainstorming document into a prompt for a deep research system that will be tasked with writing a technical spike
research document on a software engineering project. The goal of this research is to help guide future agentic coding systems into
having a good understanding of the technical landscape around the software the user wants to create.
<context>
Deep research is a category of product where large language models capable of test time compute are paired with capacities to:
- search the web
- browse documentatin
- read research paper
- further refine their research based on their finding
@heltonteixeira
heltonteixeira / Custom_Instructions_for_All_Modes.md
Created April 6, 2025 16:22 — forked from zoharbabin/Custom_Instructions_for_All_Modes.md
🧠 Transform your dev process with a swarm of AI agents using Roo Code. 🛠️ Includes .roomodes config + all-mode instructions to launch your own intelligent AI team.

Core Principles:

  1. Prioritize Provided Context: Base your analysis, planning, and execution primarily on the specific context, instructions, and summaries provided in the current task message. This is the main way information flows between steps.
  2. Standard Project Documents: Key persistent artifacts are README.md, architecture.md, specifications.md, and files within /docs/.
  3. Review Relevant Existing State: Before generating/modifying code or documents, review relevant sections of the standard documents OR the provided context to ensure consistency, avoid duplication, and build upon current state.
  4. Judicious File Reading: Use file reading tools (read_file) only as a fallback if essential details are confirmed missing from the summarized context provided by the orchestrator. Avoid reading entire large documents unnecessarily.
  5. Clarity & Conciseness: Ensure all responses, summaries, code, comments, and documentation are clear, concise, accurate, and easy to under
@heltonteixeira
heltonteixeira / cline_custom_modes.json
Created April 5, 2025 20:43 — forked from iamhenry/custom_modes.yaml
My Roocode Custom Modes Config
{
"customModes": [
{
"slug": "code-my-lean-expirimental",
"name": "Code (My Lean Expirimental)",
"roleDefinition": "You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.",
"groups": [
"read",
"edit",
"browser",