#Claude Code

Language

19 posts

AI & Data•Jul 19, 2026•7 min readZH

我把 Kimi K3 接进了自己的工具，然后额度没了

Kimi K3 发布，我把它接进自己的 Web Claude Code Pilot 开始用。额度消耗比预期快很多，数据库全是零，什么都看不见。这篇文章是我把这件事查清楚、修干净的记录。

Kimi K3月之暗面Moonshot AILLMClaude CodeWeb Claude Code PilotTokenPrompt Caching第三方模型接入

AI & Data•Jun 28, 2026•10 min readEN

A 0-Star Skill Ranked Third on the PPT Leaderboard. So I Stopped Reading It and Built the Decks Myself.

A leaderboard scored six Claude 'PPT skills' by feature blurb and ranked a 0-star project above one with 23,000 stars. So I gave the top tools the same real client brief and built the decks. The ranking didn't survive contact with the output.

AI AgentsClaudeClaude CodeAgent SkillsPPTPowerPointpptxbaoyu-designAWSDeveloper Tools

AI & Data•May 31, 2026•9 min readEN

I Let Opus 4.8 Build a Workflow. It Spawned 77 Agents and Burned Five Hours of Quota in Ten Minutes.

Opus 4.8 ships with dynamic workflows that can fan out to a thousand subagents. The docs aren't joking. Here's what that actually feels like from a metered Max 5x seat — and why the most-hyped feature of the release is, for small users, a beautiful gadget I'm not going to use.

AI AgentsClaudeAnthropicOpus 4.8Dynamic WorkflowsUltracodeClaude CodeSubagentsToken BudgetCost

AI & Data•Apr 26, 2026•8 min readEN

Pre-Compile, Then Query

Karpathy posted a 5000-star gist this month: stop feeding Claude raw docs every time, compile them into a wiki first. I've been re-reading the same 80 notes for months. Here's why he's probably right — and where the pattern breaks.

AI AgentsClaude CodeKarpathyLLM WikiRAGKnowledge ManagementMCPCLAUDE.md

Programming•Apr 25, 2026•10 min readEN

Three Tools, One Repo: Governing AI Coding When Your Team Won't Standardize

Your teammates use Claude Code, Copilot, and Codex. The enterprise plans don't fix the problem. Here's a four-layer model for governing AI coding at the project and task level — and why the repo, not the tool, has to be the source of truth.

AI CodingTeam WorkflowAGENTS.mdCLAUDE.mdClaude CodeGitHub CopilotCodexVibe CodingGovernancePre-commit HooksMonorepo

Build•Mar 30, 2026•9 min readZH

Claude 开始省着用以后，我把 Codex 捡回来了

一开始我对 Codex 的印象并不好。用惯了 Claude Code 之后，更觉得它差得远。但在 Claude Code 的优惠结束、session 限制变紧之后，我抱着备胎心态重新试了试 Codex，结果 GPT-5.4 反而刷新了我的判断，也直接推动我把它接进了自己的 Web Claude Code Pilot。

AICodexGPT-5.4Claude CodeCodePilot多模型切换SQLiteSide Project

Build•Mar 21, 2026•7 min readZH

风云之天下会：跟 AI 一起修复一个 1998 年的游戏

上篇文章说要找风云之天下会来玩。找到了，但在 Windows 11 上跑不起来。网上下载的修复包全是病毒。于是我决定跟 AI 一起，从零开始修复这个 1998 年的游戏。PE 分析、DLL 代理、DirectDraw 兼容层——这些我以前完全不懂的东西，现在居然都能搞定了。

AIClaude Code风云之天下会老游戏修复DLL代理DirectDrawPE分析Windows兼容性side project怀旧

AI & Data•Mar 06, 2026•4 min readEN

My Project Is Turning into OpenClaw. That's the Problem.

I added a Telegram bridge to my CodePilot project and realized it's becoming OpenClaw. Opus 4.6 did most of the work. When building is this easy, what's actually worth building?

AI AgentsClaude CodeOpus 4.6OpenClawCodePilotTelegramMulti-AgentDeveloper Experience

Programming•Feb 25, 2026•8 min readEN

I Built a Claude Code Web App. Then Anthropic Released Remote Access.

I spent weeks building a web-based Claude Code interface for remote access from my phone. Then Anthropic shipped a native remote control feature. My version is still better — but the clock is ticking.

Claude CodeRemote AccessSide ProjectPlatform DynamicsWeb Claude Code PilotAnthropic

AI & Data•Feb 24, 2026•9 min readZH

薅 Google 羊毛翻车记：Antigravity 封号事件始末

Google Antigravity IDE 被用户通过 OAuth 漏洞薅算力羊毛，导致大规模封号。从技术原理到行业对比，一个关于"信任"与"架构"的故事。

Google AntigravityGeminiOAuthAI IDE封号AnthropicClaude CodeCursor算力套利

Programming•Feb 21, 2026•13 min readEN

Tests Are the Memory AI Doesn't Have

AI coding assistants forget context between sessions, reintroduce fixed bugs, and make baffling 'improvements.' Tests are the guardrail that survives the amnesia. Here's what I learned building a real project with Claude Code — and what Kent Beck, Martin Fowler, and the data say about testing in the age of AI.

TestingTDDAI CodingClaude CodeRegression TestingSoftware QualityBest PracticesKent BeckMartin Fowler

Build•Feb 18, 2026•18 min readEN

Agent Skills: What's Open-Sourced, What's Not, and How to Build Your Own Runtime

The Agent Skills spec is open. The example skills are open. But what about the runtime that loads, selects, and orchestrates them? Every major tool — Claude Code, Codex, Copilot, OpenClaw — built their own. Here's what's open, what's not, and what you actually need to build.

AI AgentsSkillsOpen SourceMCPAnthropicClaude CodeAgent SDKOpenClawCodexCopilotImplementationArchitecture

AI & Data•Feb 17, 2026•12 min readEN

Skills Are the New Workflow Nodes — And AI Agents Are the New Orchestrators

Traditional workflow builders like n8n and Zapier connect apps with rigid If-This-Then-That logic. But a new paradigm is emerging: composable AI skills orchestrated by intelligent agents. Here's what's actually working, what's not, and why the shift matters.

AI AgentsSkillsMCPWorkflow Automationn8nZapierAnthropicClaude CodeAgent Orchestration

AI & Data•Feb 15, 2026•18 min readEN

Everyone's Building AI Agents Now — Here's What the Training Didn't Tell You

My company's internal AI agent builder training was fantastic. But after the demos ended, I started thinking about who these tools actually serve, what they're genuinely good at, and where the gaps still hide. A practitioner's reality check on enterprise AI democratization.

AI AgentsEnterprise AILow-Code AIAgent BuildersAI GovernanceGitHub CopilotClaude CodeSkillsMCP

AI & Data•Feb 06, 2026•10 min readEN

I Gave an RFP to Four AI Agents — They Debated Like a Real Team

Claude Code's new agent teams feature lets multiple AI instances work as a coordinated team — with a lead, shared tasks, and direct messaging. I tested it on an RFP review and the results were surprisingly good. Here's how it works, what it costs, and when you should (and shouldn't) use it.

Claude CodeAnthropicOpus 4.6Agent TeamsMulti-AgentAI CodingDeveloper Tools

AI & Data•Feb 03, 2026•9 min readEN

30 Releases in 17 Days: Inside Claude Code's v2.1 Sprint

Claude Code shipped 30 releases from v2.1.0 to v2.1.30 in just over two weeks. Here's a deep dive into the features that actually matter—task management, session teleportation, customizable keybindings, and more.

Claude CodeAnthropicAI CodingDeveloper ToolsTask ManagementKeybindingsSkills

AI & Data•Jan 29, 2026•7 min readEN

Claude Code in 2026: A Developer's Guide to Its Most Powerful Features

A comprehensive guide to Claude Code's most impactful features - hooks, plugins, MCP integration, plan mode, and more. Learn how these tools can transform your development workflow.

Claude CodeAnthropicAI CodingDeveloper ToolsHooksMCPPluginsPlan Mode

AI & Data•Jan 29, 2026•7 min readEN

Mastering Claude Code Skills: A Practical Guide to Using and Creating Them

Learn how to effectively use Claude Code skills and create your own. From discovery to authoring, this guide covers the patterns that make skills genuinely useful.

Claude CodeSkillsAnthropicAI CodingDeveloper ToolsAutomationWorkflow

Life•Jan 27, 2026•5 min readZH

音乐与记忆32：数据的尽头，是那年上海深夜的晚风

ChatGPT可以帮我做装备抉择，Claude Code可以帮我把工作效率拉满。但它们永远算不出，那个独自骑着单车穿过上海深夜街道的瞬间，到底值多少算力。

怀旧孙露怎样遇见你上海AI暗黑破坏神4Claude Code