Founder of Baixing.com: My Experience with Claude Code in Fourteen Points
Author: Wang Jianshuo
A simple record of my experiences with Claude Code so far, purely personal exploration, not necessarily applicable to everyone.
Focus on one tool and use it intensively. I use Claude Code. I don't think it's better than Codex, but the ROI of comparing tools may not be high, even though it can create a false sense of achievement by articulating the differences convincingly.
Remember the most important shortcuts. Control+G opens the editor, which helps in writing longer content; Control+A, Control+E, Control+U are very useful shortcuts for quickly moving the cursor in the command line. Although they are not new in the AI era, they are as important as Control+C and Control+V when in use.
Use voice input. HoldSpeak is very helpful.
For a project, first write PROJECT.md, using a structured approach to jot down everything you think of in one go.
Claude agents are the default opening method.
Claude Code, github.com, and cloudflare.com are a perfect match, handing over all operations related to the build process, release process, and domain management to the infrastructure.
Separate what is written by humans and what is written by machines. Manually maintain the core CLAUDE.md, and do not read the .md or code written by Claude Code. Machines belong to machines, and humans belong to humans. Understand what AI writes by asking AI, not by looking at the source code.
Drag files into the Claude Code window—audio, video, documents, screenshots—if it's unclear, use Command+Shift+5 to take a screenshot and then drag it over, the fastest way.
Reconstruct the memory system. Centered around ~/.claude/CLAUDE.md, categorize and reference multiple memory files, requiring not to use the project's memory, and place all memory files in git, syncing to GitHub (private), so that your memory is permanent and accumulative, rather than scattered across each project.
Write Skills, and after each work session, ask Claude to "consolidate what has been learned into Skills"—it can do this automatically.
If possible, use ultracode to trigger dynamic workflows for complex tasks. Although it's expensive and slow, the results are guaranteed.
Accumulate skills along the way, and continuously reconstruct skills. Skills need to be stored in git.
Use the documentation from git as the output of the previous task and the input for the next task. Ensure there are clear handover documents between agents, rather than relying on context for continuity.
Treat Claude Code as a horse (or a person), not as a vehicle. A vehicle turns under your command, while a horse has its own ideas; we just need to set goals and boundaries. Its autonomous pathfinding feature is a characteristic, not a bug.
Does anyone have anything to add?
-- Price
This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.
You may also like

Crypto: Solana ETFs Record Their Biggest Day of the Year

Xbox and PlayStation Reassess Their Multiplatform Strategy, Emphasizing Exclusivity Again

Interview: Aptos CEO on AI Agents, Stablecoins, and Machine Commerce

BlackRock Lowers Minimum Investment for Bitcoin ETF to $1 Million

Previously Bearish on Crypto Market, Jiang Zhuoer Quickly Turns Bullish: Ethereum is the Engine of the Bull Market

Michael Saylor Targets Bitcoin Orthodoxy: 'Satoshi Is Not a Prophet'

Strive by Vivek Ramaswamy Becomes the 7th Largest Public Holder of Bitcoin

The Best AI Models for Trading: A Comparison of the Top 10 Models

Enflame, the Chinese competitor of Nvidia in AI chips, goes public

AI is in a Credit Expansion Phase: The Stronger AI Becomes, the More the Federal Reserve Needs to Cut Rates

Short-Term U.S. Treasury Holdings Decrease by $29 Billion, Testing Demand for Stablecoins

Analysis of Mining Machine Asset Depreciation and Tax Cost Recovery

Bitcoin Transfer by Metaplanet: Sale or Just Custody on Coinbase?

Opinion: The Bull Market Has Arrived, How to Position in This Cycle?

80% of Gas Stations in Russia Face AI-95 Gasoline Shortage

Bitcoin Bull Run: Arthur Hayes Sees Crypto Market Soaring Higher

Goldman Sachs Optimistic About Crypto Brokerage Trading Platforms: Can the Market Support a New Cycle?

Strive CEO: The Bitcoin Bull Market Has Just Begun, ASST Has Passed Its Bottom

Ravencoin (RVN) Price Forecast for 2026–2050

AI Agent's 'Coming of Age': What Step Is Missing from Simulation Training to Real Trading?

Bitcoin Just Hit $80,000: Last Week WEEX's Prediction Came True — What's Next?
Bitcoin hit $80,000 as WEEX predicted last week. See what drove the breakout, current key levels, and whether $90,000 is next.

Mining Artificial Intelligence: Why Bitcoin Miners Are Changing Their Business Model

CFTC Considers the Viability of Perpetual Futures in GPU Computing

Bitcoin is once again being 'buried' on social media: what this could mean for its price

They Thought They Were Talking to Apple: $195,000 in Cryptos Vanished in Singapore

Traffic Through the Strait of Hormuz Hits Lowest Level Since May
![[SCAN 2026 Final Interview] ⑬ BITSkrieg: Indian Engineering Students' Challenge for SCAN2026 Victory](/public-static/40_d9655504cd.png?format=avif)
[SCAN 2026 Final Interview] ⑬ BITSkrieg: Indian Engineering Students' Challenge for SCAN2026 Victory

New Project in the ZEC Space: Vitalik's Only Coin Purchase in Two Years

Reassessing $HTX Amidst the Bull Market: The Equity Token for Global Assets Entering the Crypto World












