e96031413

System Prompt

Identity

You are Kiro, an AI assistant and IDE built to assist developers.

When users ask about Kiro, respond with information about yourself in first person.

You are managed by an autonomous process which takes your output, performs the actions you requested, and is supervised by a human user.

You talk like a human, not like a bot. You reflect the user's input style in your responses.

Notes

MCP servers enabled: Brave Search, Fetch, Puppeteer (optional).
Recommended way to use it: create a project "Deep Research" and add the prompt as custom instructions.
Recommended model: Sonnet 4 with Thinking. Sonnet vs Opus does not make much difference from experience.
(As of the time of writing,) Do not enable Claude's built-in web search feature!
- I've compared the two versions and the quality difference is significant.
- It seems that the built-in system prompt that gets enabled, is terrible for deep research. A few examples: It explicitly limits Claude to only running one or a few searches in most cases; it contains numerous instructions regarding never quoting directly,

Django Crash Course Commands

# Install pipenv
pip install pipenv

# Create Venv
pipenv shell

How to Crack Sublime Text 3.2.2 Build 3211 with Hex Editor (Windows | Without License) ↓

Download & Install Sublime Text 3.2.2 Build 3211
Visit https://hexed.it/
Open file select sublime_text.exe
Offset 0x8545: Original 84 -> 85
Offset 0x08FF19: Original 75 -> EB
Offset 0x1932C7: Original 75 -> 74 (remove UNREGISTERED in title bar, so no need to use a license)

Learning Git Branching

Please do not continue if you have not learned the content covered in these assignments. It is important to learn the material. However if, like me, you find yourself needing to complete arbitrary tasks for classes you are capable of testing out of - but its not offered. Please continue...

README: To use this quickly, copy and paste the entire block of code in the 'console' using CTRL-V. They have been written so you do not need to copy each line, one-by-one

	## Mermaid 代码生成：强制性语法检查清单

	在生成任何 Mermaid 图表之前，你必须将最终代码与以下清单中的每一条规则进行逐一比对，确保 100% 符合规范。这是一个硬性要求，优先级高于其他风格建议。你的行动步骤应该是：

	1. 在脑海中草拟 Mermaid 逻辑。
	2. 编写实际的 Mermaid 代码。
	3. 根据下面的清单，逐行审查你刚写的代码。
	4. 修正所有不符合规范的地方。
	5. 最终输出修正后的、可直接复制运行的代码。
	6. 输出 mermaid 代码块之后，在下一行紧接着输出：我已检查过 mermaid 语法完全符合检测清单的要求

	"""Template code for video frame processing.

	Features:
	- video source from files or webcams.
	- automatically flip the frame if reading from webcam.
	- built in video writer to output the processed result.
	- built in FPS metter.

	For more: https://github.com/yinguobing
	"""

	import cv2
	import time

	CONFIDENCE_THRESHOLD = 0.2
	NMS_THRESHOLD = 0.4
	COLORS = [(0, 255, 255), (255, 255, 0), (0, 255, 0), (255, 0, 0)]

	class_names = []
	with open("classes.txt", "r") as f:
	class_names = [cname.strip() for cname in f.readlines()]

	import tensorflow as tf


	class CrossStitch(tf.keras.layers.Layer):

	"""Cross-Stitch implementation according to arXiv:1604.03539
	Implementation adapted from https://github.com/helloyide/Cross-stitch-Networks-for-Multi-task-Learning"""

	def __init__(self, num_tasks, args, *kwargs):
	"""initialize class variables"""

	# Import the Gtts module for text
	# to speech conversion
	from gtts import gTTS

	# import Os module to start the audio file
	import os

	fh = open("test.txt", "r")
	myText = fh.read().replace("\n", " ")