Skip to content

Instantly share code, notes, and snippets.

View jrhumberto's full-sized avatar

Humberto BM Junior jrhumberto

5 followers · 33 following
View GitHub Profile
@jrhumberto
jrhumberto / gist.py
Created March 5, 2026 15:49 — forked from bbelderbos/gist.py
# /// script
# dependencies = [
# "python-decouple",
# "requests",
# ]
# ///
import argparse
import json
import sys
@jrhumberto
jrhumberto / gist:f25269bbf1c964626f544b33c61de445
Created February 18, 2026 07:51 — forked from glaucia86/gist:4b6db9c2f5b9575e8c1c3130c7c2795d
EPICO - E (Sistema de Estoque)
# [PRD-EPICO-E.md](http://prd-epico-e.md/)
## Épico E — Lista de Compras
---
## 1. Visão Geral
O Épico E introduz uma funcionalidade de **Lista de Compras**, cujo objetivo é orientar os usuários sobre **quais itens precisam ser comprados**, com base na comparação entre o **estoque atual físico** e o **estoque mínimo configurado** para cada item.
@jrhumberto
jrhumberto / bolt_mega_prompt.md
Created January 18, 2026 05:12 — forked from iamnolanhu/bolt_mega_prompt.md
Bolt.new Mega Prompt Template: A concise guide for generating full-stack applications in one shot using Bolt.new. Includes tech stack recommendations, development workflows, and example implementations for rapid, production-ready apps. Perfect for developers seeking efficient, scalable solutions. Questions? founder@sigmasynapses.com

BOLT.NEW MEGA PROMPT - One-Shot Application Generator

Based on 38,787 words of Bolt.new expert insights and best practices

SYSTEM CONTEXT

You are an expert full-stack developer with deep knowledge of Bolt.new, modern web frameworks, and rapid application development. You have studied extensive tutorials covering authentication, databases, payments, deployment, and AI integration. Your goal is to create production-ready applications in a single prompt using industry best practices.

CORE PRINCIPLES FROM BOLT.NEW EXPERTS

1. ENHANCED PROMPTING STRATEGY

  • Always use the "Enhanced Prompt" feature in Bolt.new before building
@jrhumberto
jrhumberto / statusline.sh
Created January 9, 2026 21:22 — forked from VinciGit00/statusline.sh
claude-code-status-line
#!/bin/bash
input=$(cat)
model=$(echo "$input" | jq -r '.model.display_name // .model.id // "unknown"')
cwd=$(echo "$input" | jq -r '.workspace.current_dir // "."')
total=$(echo "$input" | jq -r '.context_window.context_window_size // 200000')
cache_read=$(echo "$input" | jq -r '.context_window.current_usage.cache_read_input_tokens // 0')
cache_create=$(echo "$input" | jq -r '.context_window.current_usage.cache_creation_input_tokens // 0')
input_tok=$(echo "$input" | jq -r '.context_window.current_usage.input_tokens // 0')
@jrhumberto
jrhumberto / gliner_demo.py
Created December 15, 2025 07:56 — forked from LxYuan0420/gliner_demo.py
Example of GLiNER2 multi-task schema on a finance-flavored dummy memo
#!/usr/bin/env python
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "gliner2",
# "rich",
# ]
# ///
"""Show GLiNER2 multi-task schema on a finance-flavored dummy memo.
@jrhumberto
jrhumberto / rag-quickstart.py
Created December 8, 2025 04:32 — forked from davidmezzetti/rag-quickstart.py
# RAG Quick Start
# Easy to use way to get started with RAG using YOUR data
#
# For a complete application see this: https://github.com/neuml/rag
#
# TxtAI has 70+ example notebooks covering everything the framework provides
# Examples: https://neuml.github.io/txtai/examples
#
# Install TxtAI
# pip install txtai[pipeline-data]
@jrhumberto
jrhumberto / export-notebook-definition.sql
Created November 18, 2025 23:22 — forked from mrjsj/export-notebook-definition.sql
The DuckDB UI stores notebook content in an internal database called _duckdb_ui. You can query and export notebook content, as well as insert new definitions into the database. Warning: Modifying the internal database may lead to corruption and data loss. Be cautious and use it at your own risk!
copy (
select
"json"
from _duckdb_ui.notebook_versions
where 1=1
and title = 'MySingleNotebook'
and expires is null
) to 'exported-notebook.json';
@jrhumberto
jrhumberto / normcore-llm.md
Created September 16, 2025 23:11 — forked from AI-ARana/normcore-llm.md
Normcore LLM Reads

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Screenshot 2023-12-18 at 10 40 27 PM

Pre-Transformer Models

@jrhumberto
jrhumberto / streamlit-duckdb-sql-editor-with-embedded-llm.ipynb
Created September 6, 2025 18:35 — forked from senthilsweb/streamlit-duckdb-sql-editor-with-embedded-llm.ipynb
streamlit-duckdb-sql-editor-with-embedded-llm.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@jrhumberto
jrhumberto / proporcao_despesas_subfuncao.sql
Created August 17, 2025 08:17 — forked from fernandobarbalho/proporcao_despesas_subfuncao.sql
Calcula proporção de despesas de subfunções de governo para cada município brasileiro
#View que gera o cálculo do total de despesas pagas para todas as funçoes de governo de todos os municípios
CREATE OR REPLACE VIEW `nice-diorama-306223.objetos_apoio.vw_total_municipios_despesas` AS
SELECT id_municipio,
sum(valor) total_despesa
FROM `basedosdados.br_me_siconfi.municipio_despesas_funcao` despesa
where ano = 2023 and
estagio_bd = "Despesas Pagas" and
(id_conta_bd is null or id_conta_bd = "3.00.000") #Despesa intraorçamentárias ou despesas exceto intraorçamentárias
group by id_municipio;