clonn

install this https://officialskills.sh/duckdb/skills/query https://github.com/phuryn/pm-skills/tree/main/pm-toolkit/skills/grammar-check https://github.com/phuryn/pm-skills/tree/main/pm-product-strategy/skills/startup-canvas https://github.com/phuryn/pm-skills/tree/main/pm-product-strategy/skills/swot-analysis https://github.com/phuryn/pm-skills/tree/main/pm-product-strategy/skills/lean-canvas https://github.com/phuryn/pm-skills/tree/main/pm-marketing-growth/skills/marketing-ideas

https://github.com/phuryn/pm-skills/tree/main/pm-execution/skills/create-prd https://github.com/NousResearch/hermes-agent/blob/main/skills/autonomous-ai-agents/claude-code/SKILL.md

clonn

A practical guide for adapting OpenClaw’s core bootstrap files and runtime settings to better suit GPT-5.4, with a focus on execution-first behavior, completion discipline, concise outputs, and better tool-use convergence.

This time I changed the approach to: keep OpenClaw’s original structure, then add the execution tendencies that GPT-5.4 needs, instead of rewriting everything from scratch.

The basis for this adjustment is:

OpenClaw officially defines AGENTS.md as operating instructions plus memory, SOUL.md as persona, boundaries, and tone, and TOOLS.md as tool usage instructions. These files are injected directly in the first round of a new session. MEMORY.md is for long-term memory and is recommended only for the main session. BOOT.md is a startup checklist and should remain very short. The official documentation also clearly states that at session start, it should first read SOUL.md, USER.md, and the memory files for today and yesterday, while the main session should al

clonn

## X OAuth Local Development Lesson (Important)

I was stuck on this for a long time, so documenting it clearly:

### 1️⃣ You must use `localhost` exactly

The default redirect URI:

```
http://localhost:8080/callback

clonn

#!/bin/bash

# ==============================================================================
# Moltbot Deployment Script for Ubuntu 24.04
# Optimized for: 4GB Swap, Node v24, Google DNS, and Custom Port Access
# ==============================================================================

# Exit immediately if a command exits with a non-zero status
set -e

clonn

Clawdbot System Architecture Analysis

本文檔詳細解析 Clawdbot 的 Prompt Flow、System Prompt、框架、工具系統、整體流程，以及任務完成的定義。

---

1. 整體架構概覽

┌─────────────────────────────────────────────────────────────────┐

clonn

# https://github.com/anthropics/claude-code/issues/4002
# Error: File content (28375 tokens) exceeds maximum allowed tokens (25000). 
# You have to prepare to max account before

export CLAUDE_CODE_MAX_OUTPUT_TOKENS=100000
export MAX_MCP_OUTPUT_TOKENS=1000000

# 設定之後再重新跑 claude code
# After configuring the settings, rerun Claude Code.

clonn

function printEyes(space = 2) {
    // Determine if we should use dot or star based on space size
    const symbol = space > 3 ? "*" : ".";
    
    // Create one eye with proper spacing
    const innerSpace = " ".repeat(space);
    const eye = "(" + innerSpace + symbol + innerSpace + ")";
    
    // Combine both eyes
    console.log(eye + eye);

clonn

# edit ssh config
sudo vim /etc/ssh/sshd_config

LoginGraceTime 0


# restart ssh
sudo service ssh restart 

clonn

Node.js on Apple Silicon

Node Version Manager (https://github.com/nvm-sh/nvm) works perfectly across native node installations as well as emulated Rosetta installations. The trick I am using here is to install one LTS version of node under Rosetta and another stable version as native binary.

TODO

• find a way how to run the same node version on both platforms

clonn

{
    "url": "https://DOMAIN",
    "secret": "----",
    "database": "mongo",
    "mongo": {
        "host": "127.0.0.1",
        "port": 27017,
        "username": "",
        "password": "",
        "database": "",