Writing
Developer tools
37 articlesFilter articles Developer tools
Ideas to revisit
Developer tools
-
Impeccable：把 AI 前端设计要求变成可检查的工作流
Impeccable 把 PRODUCT.md、DESIGN.md、61 条确定性规则和浏览器组件 Review 组合成 AI Coding 的前端设计验收流程。
Chinese -
Muse Gadgets 把 ESP32 和 Raspberry Pi 接进 Muse
Muse Gadgets 用 ESP32 与 Linux Device SDK 把屏幕、按钮、传感器、执行器、文件和命令接成 Muse 的设备端点。
Chinese -
EmDash 1.0 separates plugin catalogs from publishing
EmDash 1.0 separates author identity, signed releases, plugin discovery, and runtime permissions. Installers verify records independently.
English -
Cloudflare redesigns its CLI for agents
Cloudflare launches cf in open beta, using Wrangler usage data to explain default JSON, command search, and typed configuration.
English -
Cloudflare 把 CLI 重新做给 Agent
Cloudflare 发布 cf open beta，用 Wrangler 的实际使用数据解释默认 JSON、命令搜索和类型化配置。
Chinese -
Why old CLAUDE.md rules can hinder a model upgrade
Use prompt audits, instruction layers, and migration evals to retain real requirements, reassess model workarounds, and enforce hard limits in code.
English -
模型升级后，旧 CLAUDE.md 为什么可能拖后腿
拆解 Prompt Audit、指令分层和迁移 Eval：模型能力变化后，哪些规则应保留，哪些模型补丁要重新验收，哪些限制必须下沉到 Hook 或策略层。
Chinese -
Microsoft connects AI-built tools to app delivery
After Copilot Code builds an internal tool, Managed Runtime handles Git, dev environments, Entra ID, connectors, previews, deployment, and governance.
English -
Microsoft 把 AI 内部工具的发布链也接上了
Copilot Code 生成内部工具后，Managed Runtime 接管 Git、受控开发环境、Entra ID、连接器、预览、部署和企业治理。
Chinese -
GitHub Agentic Autofix starts retaining repair experience
GitHub Agentic Autofix reads and writes Copilot Memory. How security repair knowledge crosses agent workflows, and why verification, scope, and expiry matter.
English -
GitHub Agentic Autofix 开始积累修复记忆
GitHub Agentic Autofix 会读取并写入 Copilot Memory。本文拆解安全修复经验如何跨 Agent 复用，以及验证、范围和过期为什么重要。
Chinese -
Jev-Code-Reviewer prioritizes large PRs as P0/P1/P2
Jev-Code-Reviewer prioritizes PR changes, expands P0 by default, and retains the original diff and fallback paths so reviewers see key changes first.
English -
Jev-Code-Reviewer：大 PR 先分 P0/P1/P2
Jev-Code-Reviewer 给 PR 改动做注意力排序，默认展开 P0，同时保留原始 diff 和失败回退路径，帮助人先看关键改动。
Chinese -
Debugging agents with traces, spans, and OpenTelemetry
The GitHub Copilot OpenTelemetry update explains agent traces, spans, metrics, events, content capture boundaries, and a telemetry adapter for Lora PI Kit.
English -
Agent 有日志还查不清？读懂 Trace、Span 与 OpenTelemetry
从 GitHub Copilot 的 OpenTelemetry 更新出发，解释 Agent Trace、Span、Metrics、Events、内容采集边界，以及 Lora PI Kit 如何接入标准遥测。
Chinese -
Why pinning a Git SHA can still run different code
Plugin4Shell exposes a supply-chain gap: a pinned SHA records the expected version, but installers must also verify the actual HEAD after checkout.
English -
固定 Git SHA 为什么还可能跑到别的代码
Plugin4Shell 暴露了一个供应链边界：固定 SHA 只写下期望版本，安装器还必须在 checkout 后验证真实 HEAD。本文结合 Git 文档、本地无害复现和 GitHub 分支限制解释机制。
Chinese -
json-render constrains UI with a component catalog
Vercel Labs json-render defines components, actions, and data bindings before generating schema-constrained JSON that can be checked and replayed.
English -
json-render：先锁组件目录，再让 AI 生成界面
Vercel Labs 的 json-render 先定义组件、动作和数据绑定目录，再让模型生成符合 schema 的 JSON。生成式 UI 的边界因此可以验证、记录和回放。
Chinese -
How to score a coding agent that finishes 80% but fails
Android Bench 2.0 keeps pass rate as a hard gate and adds completion rate to diagnose progress and unfinished acceptance requirements.
English -
Coding Agent 做完 80% 还失败，Eval 怎么记
Android Bench 2.0 保留 Pass rate 作为硬门禁，再用 Completion rate 解释长任务已经完成多少，以及问题卡在哪一类验收。
Chinese -
FDE growth: 519 overseas jobs, 28 in China, 6 projects
A study of 519 overseas job listings, 28 roles at major Chinese firms, and 6 projects examines FDE responsibilities, growth, costs, and scalability.
English -
FDE 为什么突然火了：519 条海外 JD、28 条国内大厂岗位和 6 个真实项目
用 519 条海外公开 JD、28 条国内大厂岗位和 6 个真实项目，拆解 FDE 的职责、增长、国内落地、成本与规模化条件。
Chinese -
OpenCloak: replace personal data before sending it to AI
OpenCloak replaces names, emails, and other personal data with stable stand-ins locally, then restores them when the model responds.
English -
OpenCloak：发给 AI 之前，先在本地把个人信息换成假值
OpenCloak 在本地把姓名、邮箱等敏感字段替换成稳定假值，模型响应回来后再恢复，减少个人信息直接发送给 AI 服务。
Chinese -
Splash: a local LLM inference stack built for each model
Splash combines model packages, kernels, memory planning, and compatible local APIs into a model-specific inference stack for coding agents.
English -
Splash：把本地 LLM 推理栈按模型重做
Splash 把模型包、Kernel、内存计划和本地兼容 API 组合成按模型定制的推理栈，面向 Coding Agent 的本机模型运行。
Chinese -
Foreman: an independent supervisor for coding agents
How Foreman separates a coding agent from supervision, using runtime evidence, Jev judgments, and deterministic policy to continue, verify, stop, or escalate.
English -
Foreman：给 Coding Agent 加一个独立监工
拆解 Foreman 如何把 Coding Agent 的执行循环与独立监督分开，用运行证据、Jev 判断和确定性 policy 决定继续、验证、停止或交给人工。
Chinese -
Turn production agent failures into regression tests
Use Kitaru Replay, Evaluator, and Regression Suite to preserve production failures as repeatable agent tests, with tool policies and CI gates.
English -
Agent 线上出过的错，怎么自动变成以后每次改动都要重跑的测试？
结合 Kitaru 的 Replay、Evaluator 和 Regression Suite，说明怎样把线上失败固定成可重放的 Agent 回归测试，并用工具策略与评测结果接入 CI。
Chinese -
Skills Manager: sync one skill to multiple coding agents
Skills Manager distributes a local skill library to Claude Code, Codex, Cursor, and Gemini CLI while managing version and configuration consistency.
English -
Skills Manager：把一份 Skill 同步给多个 Coding Agent
介绍 Skills Manager 如何用本地 Skill Library 统一分发到 Claude Code、Codex、Cursor 和 Gemini CLI，并处理版本与配置一致性。
Chinese -
What Tau solves by splitting an AI agent into three layers
Tau separates model adapters, the agent core, and the application so tools and frontends can work together without depending on each other.
English -
A reliable agent might leave the code alone today
GitHub Agentic Workflows jsweep checks whether a change is worthwhile and treats noop as valid, instead of forcing automation to produce a diff.
English -
一个靠谱的 Agent，今天可能不改代码
从 GitHub Agentic Workflows 的 jsweep 看 Agent 如何先判断有没有值得修改的目标，把 noop 作为正式结果，而不是为了自动化强行制造改动。
Chinese -
HyperFrames makes video a buildable HTML project
How HyperFrames gives agent-generated video an inspectable workflow of HTML, animation, assets, lint, preview, and rendering.
English -
HyperFrames：把视频做成可构建的 HTML 工程
介绍 HyperFrames 如何把 Agent 生成视频拆成 HTML、动画、素材、lint、preview 和 render 可检查流程，让视频生产进入工程循环。
Chinese -
Herdr turns the terminal into an agent runtime
How Herdr manages existing coding-agent terminals with persistent sessions, blocked states, cross-machine control, and agent coordination.
English -
Herdr 不替换 Agent，它把终端做成运行时
拆解 Herdr 如何接管现有 Coding Agent 所在终端，提供持久会话、阻塞状态、跨机器控制和 Agent 协作，而不重写底层 Agent。
Chinese -
RTK: filter shell output before it reaches a coding agent
RTK filters test, Git, search, and build noise before command output enters model context, applying context engineering at the tool-output boundary.
English -
RTK：Coding Agent 不该把整段 Shell 输出塞进上下文
介绍 RTK 如何在命令输出进入模型上下文前过滤测试、Git、搜索和构建噪声，把 Context Engineering 做到工具输出边界。
Chinese -
Google packages Skills and MCP in one plugin
How the Google Cloud Developer Plugin packages Skills, MCP configuration, and rules, and what this means for distribution, versions, and permissions.
English -
Google 把 Skill 和 MCP 打成一个插件
拆解 Google Cloud Developer Plugin 如何把 Skill、MCP 配置和规则按 Agent Plugins 规范打包，暴露跨 Coding Agent 的分发、版本与权限问题。
Chinese -
Munim Computer Use lets agents act on desktop controls
Munim Computer Use reads the accessibility tree and operates desktop controls by element ID, reducing reliance on fragile screenshot-coordinate automation.
English -
Munim Computer Use：让 Agent 按控件操作桌面
介绍 Munim Computer Use 如何先读取可访问性树，再按元素 ID 操作桌面控件，减少依赖截图坐标的脆弱自动化。
Chinese -
jcode moves coding-agent bottlenecks into the harness
How jcode handles multi-agent resources, state synchronization, and verification in its harness, beyond the capabilities of the model alone.
English -
jcode：把 Coding Agent 的瓶颈从模型转到 Harness
介绍 jcode 如何把多 Agent 的资源、状态同步和验证放到 Harness 层，说明并行 Coding Agent 的瓶颈不只是模型能力。
Chinese -
Coding agent security is now a supply-chain problem
Coding agents read and execute skills, MCP tools, dependencies, and repository instructions. These need software supply-chain controls.
English -
AI Coding Agent 的安全问题已经进了供应链
说明 Coding Agent 会读取并执行 Skill、MCP、依赖和仓库指令，因此这些组件应按软件供应链治理，而不只是做 Prompt 安全。
Chinese -
GitHub Agentic Workflows：把 Agent 装进 GitHub Actions
介绍 GitHub Agentic Workflows 如何把需要判断的自动化放进 GitHub Actions，同时保留权限、输出、审批和安全边界。
Chinese -
GitHub Agentic Workflows: agents inside GitHub Actions
How GitHub Agentic Workflows puts judgment-based automation inside GitHub Actions while retaining permissions, controlled outputs, approval, and security.
English -
AI Engineering Harness: verifiable delivery for AI code
A multi-agent engineering workflow uses isolated worktrees, CI, cold-start review, evidence gates, and layered context to control delivery of AI-generated code.
English -
AI Engineering Harness：把 AI 代码放进可验证的工程闭环
介绍一个多 Agent 工程工作流，如何用独立 worktree、CI、冷启动审查、证据门和分层上下文控制 AI 生成代码的交付。
Chinese -
MiniMax image and video generation for Hermes Agent
A Hermes MiniMax plugin with image-01, Hailuo async video tasks, CN/global endpoint fallback, end-to-end tests, and a PyPI release.
English -
用 MiniMax 为 Hermes Agent 接入图片与视频生成
记录 Hermes 的 MiniMax 图片与视频插件实现，包括 image-01、Hailuo 异步任务、CN 与 global endpoint fallback、端到端测试和 PyPI 发布。
Chinese -
StepFun image generation for Hermes Agent
The Hermes StepFun image plugin: directory layout, model routing, API calls, billing endpoints, version fixes, and publishing.
English -
用 StepFun 为 Hermes Agent 接入图片生成
记录 Hermes 图片生成插件接入 StepFun 的目录结构、模型路由、API 调用、计费 endpoint 差异、版本修复和发布流程。
Chinese
No long-form articles match this language.
Reading list
News notes
- English
- Chinese
- English
- Chinese
- Chinese
- English
- Chinese
- English
- English
- Chinese
- English
- Chinese
- English
- Chinese
- English
- Chinese
No news notes match this language.
No articles match this language. Show all languages Clear all filters