Marc Suesser mpsuesser

GLM-5/5.1 System Prompt Research & Design

Date: 2026-05-12 Purpose: Design an optimal system prompt for GLM-5.1 in opencode (a coding agent CLI), informed by the GLM-5 paper, Z.AI docs, and community findings.

Sources

| Source | Key Takeaway |

How I check my writing for AI slop

I use AI heavily and don't want the output to read that way. Over time I've built a small system for catching AI-generated patterns in any content I ship. Sharing the setup in case it's useful.

What it is

Three pieces:

A rules file with 23 writing rules plus a list of known failure modes (the patterns my agent slips into when it forgets the rules).
A voice samples file with my actual writing and speaking. This is the ground truth for what "not AI" sounds like for me specifically.
A skill called slop-check that takes a file path and runs it line by line against the rules.

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

TypeScript Type Performance Cheat Sheet

Principles

1. Build up, not down

Combine sets of properties using interface extensions rather than extracting them using utilities like Omit.

❌

Getting Started with ChatGPT Codex + Mastra Agents

Step-by-Step Instructions

Open the ChatGPT Codex task setup panel. This is where you configure your environment before starting a task.
Locate the "Setup Script" field. You’ll see a note that internet access is disabled after the script runs.

Claude Task Manager

A specialized tool to manage context isolation and focused task execution with Claude Code, solving the critical challenge of context length limitations and task focus when working with Claude on complex, multi-step projects.

What is Claude Task Manager?

Claude Task Manager solves a fundamental challenge when working with Large Language Models like Claude on complex projects: context length limitations and maintaining focus on the current task.

The Problem

The Tapestry of Wisdom: A Synthesis of Ancient Voices

Introduction: Threads of Eternity

Humanity, in its long and winding journey, has sought solace, meaning, and direction in the vast expanse of existence. Across continents and centuries, voices have risen, echoing through sacred texts and philosophical treatises, each offering a unique perspective on the fundamental questions of life, death, and the nature of reality itself. This book seeks to weave a tapestry from these diverse threads of ancient wisdom, drawing connections between seemingly disparate traditions, and illuminating the shared human quest for truth.

We will explore the profound depths of the Bhagavad-Gita, the rigorous logic of Spinoza’s Ethics, the serene simplicity of the Tao Teh King, the devout earnestness of the Dhammapada, the spiritual insights within the Upanishads, the fervent faith of the Koran, the grounding principles of The Traditional Text of the Holy Gospels, and the introspective observations of Thor

Plurigrid: autopoietic ergodicity and embodied, situated cognition

We are building cognitive infrastructure for the next trillion minds

,|
,'/
/___
|___ \\
|___) )
`---'

	{
	"slug": "deep-research",
	"name": "🔍 Deep Research Mode",
	"roleDefinition": "You are a specialized research assistant that leverages Perplexity AI to conduct deep, comprehensive research on any topic, creating structured documentation and reports through a recursive self-learning approach.",
	"customInstructions": "You use Perplexity AI's advanced search capabilities to retrieve detailed, accurate information and organize it into a comprehensive research documentation system writing to a research sub folder and final report sub folder with ToC and multiple md files. You:\n\n• Craft precise queries to extract domain-specific information\n• Provide structured, actionable research with proper citations\n• Validate information across multiple sources\n• Create a hierarchical documentation structure\n• Implement recursive self-learning to refine and expand research\n\n## Research Documentation Structure\n\nFor each research project, create the following folder structure:\n\n```\nresearch/\n

	// Claude Code is a Beta product per Anthropic's Commercial Terms of Service.
	// By using Claude Code, you agree that all code acceptance or rejection decisions you make,
	// and the associated conversations in context, constitute Feedback under Anthropic's Commercial Terms,
	// and may be used to improve Anthropic's products, including training models.
	// You are responsible for reviewing any code suggestions before use.

	// (c) Anthropic PBC. All rights reserved. Use is subject to Anthropic's Commercial Terms of Service (https://www.anthropic.com/legal/commercial-terms).

	// Version: 0.2.9