MarcusTseng

OpenClaw after 50 days: all prompts

Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)

These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.

Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.

My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.

LM Studio execution error

marcus@StrixHalo:~$ lmstudio  
[43309:0123/003154.438250:FATAL:sandbox/linux/suid/client/setuid_sandbox_host.cc:169]  
The SUID sandbox helper binary was found, but is not configured correctly.  
Rather than run without sandboxing I'm aborting now.  
You need to make sure that /tmp/.mount_lmstuda9V2kN/chrome-sandbox is owned by root and has mode 4755.
Trace/breakpoint trap (core dumped)

這篇文章旨在作為快速參考與展示。要更多完整的資訊，請見 John Gruber 原本的規格與 Github 偏好的 Markdown（Github-flavored Markdown，簡寫為GFM）資訊頁。

如果你正在找 Markdown Here 的小抄（Cheatsheet），這裡也有一篇。你也可以看看更多 Markdown 的工具。

譯註：可以參考這份中文版文件，有更詳盡的 Markdown 語法說明；如果需要可以練習的線上編輯器，可以試試看HackMD。

	#!/bin/bash
	#
	# 在 llama-vulkan-radv distrobox 內啟動兩個 llama-server:
	# :8081 Qwen3.5-122B (主腦, multi-modal, 256K ctx)
	# :8080 Gemma-4-E4B (輔助/快速反應, 40K ctx)
	#
	# 行為:
	# - 健康檢查取代固定 sleep
	# - 落地 log 與 PID 到 ~/.local/state/llama/
	# - 收到 INT/TERM 自動清理子行程

	{%- set image_count = namespace(value=0) %}
	{%- set video_count = namespace(value=0) %}
	{%- macro render_content(content, do_vision_count, is_system_content=false) %}
	{%- if content is string %}
	{{- content }}
	{%- elif content is iterable and content is not mapping %}
	{%- for item in content %}
	{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
	{%- if is_system_content %}
	{{- raise_exception('System message cannot contain images.') }}

	#!/bin/bash

	# --- 1. Vulkan 驅動偵測 (針對 Strix Halo 修正版) ---
	if [ -f "/usr/share/vulkan/icd.d/radeon_icd.x86_64.json" ]; then
	export VK_ICD_FILENAMES=/usr/share/vulkan/icd.d/radeon_icd.x86_64.json
	fi

	# 統一記憶體優化 (GFX1151 專用)
	export GGML_VULKAN_DEVICE=0
	export GGML_VULKAN_UNIFIED_MEMORY=1

	#!/bin/bash

	# --- 1. 設定路徑 ---
	#https://github.com/TheTom/llama-cpp-turboquant
	REPO_DIR="~/llama-cpp-turboquant"
	# https://github.com/kyuz0/amd-strix-halo-toolboxes
	TOOLBOX_NAME="llama-vulkan-radv"

	echo "--- Starting Update & Build for TurboQuant ---"

MarcusTseng

OpenClaw after 50 days: all prompts

LM Studio execution error

目錄