Xinwei Xiong (cubxxw) · An Open Archive of Practice and Thought

AI can rapidly complete concepts, architectures, and plans while delaying falsifiable feedback.

Claude Tag turns Slack into a shared agent runtime with identity, memory, and tools.

High output disproved my diagnosis of weak execution.

In Quanzhou, Master Hongyi’s Vinaya practice and a Buddhist temple’s Hindu pillars changed how I understand play, commitment, and the choice to keep building.

A framework for testing AI industry ideas: start with durable demand, map constraints and scarcity, redesign the workflow, and validate it with real failures.

Metrics do more than measure organizations: they train attention and ethics.

A second brain preserves more than notes: over time it exposes the decision function behind what we protect, postpone, commit to, and let reality revise.

Freedom is not the absence of schedules; defaults can quietly live the day for us.

AI can generate endless content but cannot bear experience’s cost.

Cave danger and social silence are different risks.

Observation protects us through distance, but can keep love and action from beginning.

Creators need more than applause: they need precise evidence that a work arrived.

Cheap storage makes forgetting a core AI capability.

Note-taking tools do not merely preserve experience; they edit attention and identity.

The same person changes across cities.

When novelty fades, travel must be judged by the relationships and obligations that still survive departure—not by distance, shock, or cities collected.

Every path charges in uncertainty, repetition, lost options, and identity.

AI makes production abundant, not unconstrained.

Views, clicks, and sales arrive quickly; refunds, trust, and cash flow take time.

“Think less, do more” can cure armchair thinking—or disguise haste as courage.

Procrastination can look like intense research and polished systems.

Profit proves that exchange occurred and an organization may survive.

A dinner-table argument about profit forced me to examine how vision, research, and system-building can become elegant ways to avoid the verdict of reality.

A small side-scrolling journey through Xinwei Xiong's life, travels, open-source work, products, and questions.

A version-pinned guide to Open Design 0.16.1: its four-plane architecture, local and cloud paths, BYOK privacy boundaries, SSRF controls, and practical fit.

A practical Claude Code guide to verification, permissions, worktrees, subagents, workflows, goals, loops, and routines, with current limits and safe defaults.

Loop engineering turns repeated prompting into a verifiable system.

"Treat life as a game you're playing."

A practical AI video editing pipeline for solo creators: structure shoots, automate rough cuts, keep judgment human, and publish safely across platforms.

When the cost of building approaches zero, having built something no longer proves anything, so people go look at who built it.

A distribution strategy for solo builders: turn product work into durable content, choose channels deliberately, and measure the audience you actually own.

When execution cost approaches zero, the price of building the wrong thing doesn't shrink — it becomes payable in full.

Part two of "The Super Individual's Gear Stack," on the bottom layer — production.

A four-layer AI stack for super individuals: separate production tools from judgment, distribution, and reputation assets that compound over time in practice.

A design for auditing Mac developer tools with read-only evidence, bounded AI judgments, privacy safeguards, graceful fallbacks, and false-positive tests.

Agent Skill and SKILL.md design through a storage-cleanup case study: architecture, permission boundaries, prompt contracts, real-machine tests, and lessons.

Build an evidence-driven AI knowledge base with executable workflows, method cards, voice rules, review gates, and feedback loops that improve content work.

I rebuilt a 120-post Hugo blog with AI agents, human review, MCP, GitHub Actions, a cover pipeline, and a measured GEO experiment.

A practical map of defensible AI agent businesses: vertical workflows, accountable delivery, agent infrastructure, and moats that survive model progress.

A practical trust stack for unattended AI agents: hard tool controls, regression evals, checkpoints, rollback, and focused human review for risky actions.

Build a personal intelligence system that turns monitored sources into decisions, with honest boundaries for RSS, RSSHub, agents, MCP, safety, and evaluation.

A dated, reproducible agent-fleet cost model that tests low-cost APIs, weighs open-weight options, and routes work by measured success and operational risk.

A practical framework for proactive AI agents: memory, runtimes, triggers, interruption budgets, human approval, and the discipline to stay quiet by default.

AI news pipelines can collect, translate, summarize, and deduplicate at scale.

Starting from a single image — a shaft of sunlight passing through an eye clouded by cataracts — this piece dismantles the self step by step: no-self, the five aggregates, dependent origination, until the sheer relativity of concepts makes you dizzy: "You…

A practical Chatbot-to-Agent-to-Skill framework for turning domain judgment into reusable workflows, with Amazon Ads boundaries, metrics, and human approval.

Explore direction with AI, then define the finish line yourself.

AI's core selling point is removing friction — faster, less effort, painless.

A practical framework for reliable AI workflows: separate claims from logs, preserve evidence, run evals, set failure thresholds, and escalate risk to humans.

Build a safe AI second brain with Obsidian and Claude: structure your vault, isolate sensitive notes, preview changes, back up data, test, and roll back.