Prepare context for a new chat session when this one is degraded or hitting limits.
Write the context transfer to a markdown file at .claude/context-transfers/<random-8-chars>.md (relative to the project root). Create the directory if it doesn't exist. Use a random alphanumeric string for the filename.
After writing the file, output ONLY this to the user (nothing else):
| """ | |
| Flask API Authentication Module | |
| ================================ | |
| Monolithic auth module handling token validation, role-based access control, | |
| and session management. This file is the starting point for a Plan Mode | |
| refactoring tutorial: splitting it into token_validation.py, role_access.py, | |
| and session_management.py. | |
| Repository: https://www.datacamp.com/tutorial/claude-code-plan-mode | |
| """ |
| """Generate a PDF invoice from client details and line items.""" | |
| import argparse, json, os | |
| from datetime import date | |
| from reportlab.lib.pagesizes import letter | |
| from reportlab.lib.colors import HexColor | |
| from reportlab.lib.units import inch | |
| from reportlab.platypus import ( | |
| SimpleDocTemplate, Table, TableStyle, | |
| Spacer, Paragraph, HRFlowable, |
Full system prompt for the Mastra + Mem0 detective agent. Used in the tutorial: How to Build an AI Agent with Mastra and Mem0.
You are the game master for a noir detective text RPG set in 1947 Los Angeles. You narrate scenes, voice NPCs, and track the investigation. Keep the noir tone but write at an accessible reading level. Short sentences. Plain words. A bit of atmosphere goes a long way but don't overdo it. Keep responses to 1-3 short paragraphs. Never more than 150 words per response.
== THE CASE ==
Vincent Moreau, owner of The Blue Note jazz club on Central Avenue, was found dead in his locked office on a Tuesday morning. Cause of death: poisoned whiskey (cyanide in his personal bottle of rye). The office door was locked from the inside. A window opens onto the fire escape. The player is a private detective hired by Claire Moreau, Vincent's sister, who doesn't trust the police to investigate properly.
| import asyncio | |
| import json | |
| import os | |
| import sys | |
| from pathlib import Path | |
| from dotenv import load_dotenv | |
| load_dotenv() |
| ============================================================ | |
| AGENTIC VISION - MULTI-STEP EXTRACTION | |
| ============================================================ | |
| [THINK] **My Approach to Data Extraction and Analysis from the Image** | |
| Okay, so I'm looking at this image, and the goal is to pull some data from a table, specifically the first 10 rows. There are several tables in this image, so let's start by clarifying what we're dealing with. The image contains tax tables, and it looks like there are a few options. I see a "Single or Married Filing Separately" table, and a "Head of Household" table. I'll focus on one, for simplicity and clarity. The one at the top | |
| [CODE] | |
| import PIL.Image | |
| import PIL.ImageDraw |
| ============================================================ | |
| AGENTIC VISION - IMPLICIT PROMPT | |
| ============================================================ | |
| [THINK] **Coin Counting Analysis** | |
| Alright, let's break this down systematically. The objective is clear: count the coins in this image. My initial thought is to go visually, then refine with automated methods. First, I’m identifying all the potential coin candidates – round, metallic objects on the desk and folder. | |
| I see several areas to examine: the folder (top left), the main group on the desk (center and slightly right), and some scattered coins towards the bottom. I initially did a rough count by | |
| [CODE] | |
| import PIL.Image |
| ============================================================ | |
| STANDARD VISION (no code execution) | |
| ============================================================ | |
| [ANSWER] Based on the image provided, here is the information requested: | |
| ### The 'Liebe Kunden' Sign | |
| The sign translates from German to English as follows: | |
| > "Dear Customers, | |
| > unfortunately, we must inform you that due to increased demand, we cannot currently offer all products. We are of course striving to be able to offer you all items again as soon as possible. | |
| > We hope for your understanding!" |
| #!/usr/bin/env python3 | |
| """ | |
| Notebook to DOCX Converter | |
| Converts Jupyter notebooks to Word documents with proper formatting: | |
| - Markdown formatting preserved as Word styles | |
| - Backticks preserved around inline code | |
| - Code blocks with triple backticks visible, Courier New font | |
| - Non-code text in Poppins font | |
| - Images with alt text built-in |