NEWS &
ANALYSIS.
Editorial coverage, product analysis, and workflow reporting across AI tools, models, and agent systems.
380 posts in the archive
Filter by Tags (828)
OpenClaw Can't Handle Bilibili/Xiaohongshu Natively? bibigpt-skill Fixes It
English translation: how bibigpt-skill extends OpenClaw with Bilibili, Xiaohongshu, Douyin, podcast, and structured video-summary workflows.
How to Set Up Claude Cowork (Complete Playbook) — with Full Visuals
Republished and structured guide from Ruben Hassid on setting up Claude Cowork, including full extracted visuals and a practical 30-minute onboarding plan.
The Most Beginner-Friendly Obsidian Image Hosting Tutorial (Tencent COS + PicList)
English translation of a practical Obsidian image hosting workflow: set up Tencent COS, connect PicList, and enable automatic image upload inside Obsidian.
The Real Threat Behind Anthropic's 21 Plugins: Why SaaS Companies Lost $285 Billion
In 25 days, Anthropic launched 21 plugins and triggered a $285B SaaS market wipeout. A former Google PM spent 4 weeks testing them all. His verdict: this isn't a product launch—it's an extinction event.
OpenClaw 9-Layer System Prompt Pattern
The complete 9-layer system prompt pattern used by OpenClaw. Includes bootstrap protocol, memory management, and skill loading architecture.
OpenClaw 9-Layer Prompt Architecture
Why your AI agent needs layered prompts. Deep dive into OpenClaw's 9-layer architecture with design rationale and implementation code.
agent-browser: Electron App Automation via CDP
Control Electron applications automatically using Chrome DevTools Protocol through agent-browser, enabling UI automation for desktop apps like Slack, VS Code, and Discord.
Electron App Automation with agent-browser and CDP
Guide to automating Electron applications using Chrome DevTools Protocol and agent-browser for UI control and interaction.
AI-Assisted Writing Workflow with Claude
Guide on using Claude and voice input to overcome writer's block by dumping thoughts first, then having Claude ask clarifying questions as a journalist.
Engineering Better AI Agent Prompts with Software Design Principles
Author shares approach to writing clean, modular AI agent code by incorporating software engineering principles from classic literature into prompt engineering.
Essence Architecture: First Principles Thinking Framework
A philosophical framework for seeing through surface appearances to underlying mathematical and logical structures using systems theory and first principles.
Using Linear as AI Task Management Hub
Experience report on using Linear as a central hub for AI-managed task workflows with PR submission and status tracking.
AI-Powered Todo List Automation
Discusses using AI to automate task management, addressing the problem of postponed tasks never getting done.
Debug Logging Service for AI Agent Development
A debugging technique where agents write code, verify interactions, and access real-time logs from a centralized server for effective bug fixing and feedback loops.
Building Commercial Apps with Claude Opus
Experience sharing on rapid app development using Claude Opus as a CTO, product manager, and designer combined.
Mastering Claude Code Efficiency: The Golden Formula
A verified technique to maximize Claude Code productivity using targeted prompts, deep inquiry, ultrathink mode, and plan mode to uncover hidden assumptions.
SEO/GEO Optimization Tips Using Skills in 2026
Best practices for styling AI-generated content and leveraging skills for SEO/GEO optimization in international markets.
Vercel's React Best Practices as Reusable Skill
Vercel distilled 10 years of React expertise into a skill, demonstrating how organizations should package internal best practices as reusable AI agent skills.