Skip to content

#Skills

0 items today
9/18Fri
9/12Sat
9/11Fri
  2. OpenAI Developer Blog · Codex66

    OpenAI on How to Rewrite Skills and Prompts for GPT-6 Astra

    In an official blog post, OpenAI lays out recommendations for adjusting Skills, AGENTS.md, and task prompts under GPT-6 Astra: Skill descriptions should be as short as possible and state clearly when they apply, and multi-flow Skills should use a root document for minimal routing instead of turning the Skill into an overly specific step-by-step checklist.

    Why it matters: OpenAI has published guidance on cleaning up Skills, AGENTS.md, and prompts under GPT-6 Astra, and it carries over to existing repository setups.

9/10Thu
  1. Vibe Code Textbook · Articles78

    编程智能体的四种提示词模式：plan mode、skills 与保存的提示词

    文章从 Claude Code、Codex 和 Gemini CLI 的官方文档中整理出四种提示词模式：先计划再编辑、给智能体一个可运行的检查、让智能体反过来访谈你、把反复重打的提示词存成文件，并给出各家对应的命令、参数和文件格式。

    Awaiting translation

    Why it matters: 横向对照 Claude Code、Codex、Gemini CLI 三家文档，给出计划模式、可运行检查、访谈式提问和保存提示词四种模式的命令与文件格式。

9/8Tue
  1. Hacker News · Agent Skills60

    i-have-adhd：让编码智能体不再把答案埋在废话里的 Skill

    i-have-adhd 是一个给编码助手用的 Skill，目标是让回答先给行动、步骤编号、结尾只留一个具体下一步，不再写“希望有帮助”之类的客套话。它由 10 条规则组成，全文在 SKILL.md 中，并给出前后对比：原本绕一大圈讲 auth 流程的回答，变成先执行 npm install jsonwebtoken@latest、再改 src/auth.ts:42 的具体步骤。

    Awaiting translation

  2. Habr · Cursor82

    How Cursor engineers merge 800+ PRs a month: using validation skills and evals to build trust in AI agents

    Cursor engineer Lauren Tan shares how she gets AI agents to submit and merge PRs on their own: the key is validation—letting the agent run code, capture CPU traces, and open an iOS simulator to check its own work.

    Why it matters: Cursor engineers break trust in AI agents down into reusable validation skills, feature maps, and evals, so readers can build their own automated validation workflows.

9/7Mon
9/5Sat
  1. Ryan Lopopolo66

    An agent platform built for inventing agents: decoupling capability interfaces from their implementations

    Author Ryan Lopopolo argues that an agent is a parameterized program built on top of a set of capabilities: models and configurations, reasoning and tool-call loops, computers, disks, context, Skills, tools, connectors, runtimes, network policies, identity, IAM, guardrails, I/O channels, and system prompts.

    Why it matters: Drawing on his experience building multiple agents, the author proposes a platform architecture that decouples capability interfaces from their implementations — a useful reference for teams building Agent platforms.

9/2Wed
8/31Mon
  1. 宝玉71

    AI 原生思维：像训练大模型一样训练自己

    宝玉在演讲中提出 AI 原生思维，主张做 AI 产品要盯着模型能力边界线找需求，并按能力、成本、价值三条边界判断值不值得做。他以自己做的字幕翻译 App BaoCut 为例，说明从模拟字幕组的 V1 转向以终为始的 V2 后，用词级时间戳对齐、术语表注入和 Agent 自验证替代人工校对，一次成本优化把调用从 33 次降到 12 次、单集处理从 31 分钟降到 18 分钟。

    Awaiting translation

8/29Sat
8/28Fri
8/27Thu
  1. Addy Osmani · Blog71

    如何审计你的 Agent 配置文件：CLAUDE.md、Skills 与 Hooks 的定期清理

    Addy Osmani 建议每隔几周运行一次 Claude Code 的 /doctor，单独用 /memory 检查记忆，并让每条指令重新证明自己的价值，因为模型、harness 和代码库都在变，旧配置会留下。

    Awaiting translation

    Why it matters: 作者结合自身配置审计经验与近期研究，说明 Agent 配置文件为何会腐化，以及如何按节奏清理。

8/26Wed
  1. Cline · Blog71

    Building a Code Review Agent on the Cline Loop with the Cline SDK

    The Cline team built a code review agent with the Cline SDK, splitting review into two agent loops—review and judge—then using a driver script to batch-submit the surviving issues as a single COMMENT event to the GitHub PR.

    Why it matters: A full breakdown of the plugin, Hooks, and two-stage loop behind a code review agent, transferable to other automated review scenarios.

8/25Tue
  2. Hacker News · Agent Skills34

    Agent Skills 都用什么语言编写？GitHub 数据揭示非英语占比升至 16.3%

    GitSkills 数据集对 187 万个去重 Skill 做语言识别后发现，14.3% 的 Skill 正文不是英语，其中中文占 6.2%，高于 GitHub 仓库文档 3.3% 的中文比例。非英语 Skill 占比从 2026 年 Q1 的 13.0% 升至 Q2 的 16.3%，三个月涨 3 个百分点，而 GitHub 整体非英语文档从 3.7% 到 13.0% 用了十年。

    Awaiting translation

8/24Mon
8/17Mon
8/15Sat
  1. Drew Breunig62

    Drew Breunig：编码 harness 是「情境化智能体」

    Drew Breunig 提出用「情境化智能体」来定义 harness：Harrison Chase 所说的系统提示词、规划工具、文件系统和子智能体构成开发者控制的核心循环，harness 则管理循环之外的世界，包括会话、环境、仓库、记忆、Skills、团队、组织和模型这些由内向外、使用人数递增而变动递减的层次。

    Awaiting translation

8/14Fri
  1. InfoQ · AI Coding Presentations80

    InfoQ 演讲：300 个精准 token 胜过 10 万个噪声 token，上下文工程的架构

    Baruch Sadogursky 与 Patrick Debois 在 InfoQ 演讲中用 Claude Code 现场演示：把全部项目文档塞进 CLAUDE.md 后，给接口加错误处理会因约定冲突返回 500，改用按描述懒加载的 Skill 后同一提示词通过测试。

    Awaiting translation

    Why it matters: 两位作者用现场演示拆解上下文工程的四类反模式，并给出 Skill、检索通道、外部记忆与评测的对应做法。

8/5Wed
  2. Vercel · v0 Blog62

    Vercel ships v0 API for programmatic access to its app-generation agent

    Vercel ships v0 API, giving programmatic, headless access to the v0 app-generation agent: send a prompt, v0 generates an app, spins up a dev server in the Vercel Sandbox, and returns a preview URL you can embed in your own UI. The API is now generally available.

    Why it matters: v0 opens up its app-generation capability as an API, so readers can judge how to wire it into their own product or agent workflow.

8/3Mon
  1. OpenAI · Codex Cookbook71

    Iterating on a Development Workflow with Codex: From AGENTS.md to Phased Build Files

    The OpenAI Codex Cookbook lays out a set of repository conventions for wiring Codex into your development process: use AGENTS.md for persistent repository instructions, PLANS.md as the source of phase plans, and split the work into phased build files under harness/build/, with each phase spelling out its goals, acceptance criteria, boundaries, and approval gates.

    Why it matters: OpenAI lays out a complete directory convention for constraining Codex with AGENTS.md, PLANS.md, and phased build files—one you can adapt to your own repository.

8/2Sun
7/31Fri
7/29Wed
7/28Tue
  1. Paper Compute · Engineering Blog48

    如何为 AI 智能体构建基础设施：从 tokenmaxxing 转向 valuemaxxing

    面对 GitHub 等基础设施被 AI 智能体流量压垮的现状，作者主张从 tokenmaxxing 转向 valuemaxxing，用任务完成数、节省时间和避免返工来衡量价值，而非 token 消耗量。他指出 Claude Code 会话默认 30 天后删除，导致已付费的上下文白白流失，并认为 Skill 是比 markdown 文件更好的上下文路由方式，但大规模管理 Skill 仍无解。

    Awaiting translation

  2. 宝玉34

    关于 Agent 的几个判断：通用 Agent 通吃、插件生态与模型护城河

    宝玉针对 @cellier_ 提出的三个 Agent 判断给出补充：通用 Agent 赛道将是少数赢家通吃，小通用 Agent 同样没有生存空间。他认为开放与封闭的差别不在开源或能否切换模型，而在插件生态，Skill 加 MCP 让 Agent 能完成各类任务。他还判断 Agent 产品体验护城河不深，模型能力和成本才是拉开差距的关键，小团队更适合基于 Agent 做插件。

    Awaiting translation

7/26Sun
  1. Hacker News · Context Engineering 讨论82

    Anthropic publishes new context engineering rules for Claude 5

    Thariq Shihipar, a member of Anthropic's engineering team, wrote up the new context engineering rules for Claude 5, saying the team has cut over 80% of the system prompt from Claude Code for models like Claude Opus 5 and Claude Fable 5, with no measurable loss on coding evals.

    Why it matters: Anthropic lays out the new context engineering rules for Claude 5 and explains how to trim the system prompt, CLAUDE.md, and Skills.

7/24Fri
7/22Wed
7/12Sun