AI Hero's skills repo ships v1.1, renaming /to-prd to /to-spec, merging /to-plan and /to-issues into /to-tickets, and adding new Skills like /wayfinder, /research, and /prototype.
Why it matters: The author walks through the full Skill flow from grilling to deployment and gives the migration commands for the renames, the merge, and the new /wayfinder—useful for anyone building an AI development workflow.
作者主张把业务 AI 建在 marketplace plugin 的通用原语层上，而不是绑定单一厂商，这样厂商位于工作流之下而非包裹工作流。
Awaiting translation
The Claude Code team defines an AI agent loop as repeatedly running a work cycle until a predefined stopping condition is met, and splits it into four types—turn-based, goal-oriented, time-based, and proactive—along four dimensions: what triggers it, how it stops, the underlying instructions it uses, and the tasks it fits.
Why it matters: The Claude Code team breaks loops into four types—turn-based, goal-oriented, time-based, and proactive—and lays out how each is triggered, how it stops, and how tokens are controlled.
有用户反馈 Claude Code 接入第三方模型后不会主动调用 Skills，只会使用 MCP，需在命令或提示词中显式点名才会触发。该用户使用 CC Switch + glm5.2，另有用户称同样组合下提示词触发即可自动调用，也有人表示用 bedrock 的 opus 同样存在问题。
Awaiting translation
Paper Compute 发布 paper console 平台，主张 Skill 不应凭记忆手写，而应从已运行的 Agent 会话中提取。该平台指向已完成的会话，依据真实命令、真实报错和有效修复自动生成 Skill，并在控制台中供团队查看和复用。文章引用 2026 年 3 月一篇关于 AI 开发中机构知识的研究，称提交记录丢弃了决策背后的推理，即“Decision Shadow”。
Awaiting translation
AI Hero 的 skills 目录发布 v1，通过在各 Skill 上启用 disable-model-invocation: true，让 Skill 描述不再进入模型选择 Skill 时查看的上下文窗口，Skill 描述的 token 成本降低 63%。
Awaiting translation
Why it matters: v1 用 disable-model-invocation 把 Skill 描述移出上下文窗口，并区分用户调用与模型调用，读者可据此判断自己的 Skill 组织方式。
作者介绍了 Kami（日语“纸”），一个 Claude Code Skill 和设计系统，用来解决 AI 生成文档外观千篇一律的问题，思路不是优化提示词而是收紧约束。
Awaiting translation
作者为 prismvideos.com 构建媒体生成 Agent 时，发现竞品 Higgsfield 基于开源个人 Agent Hermes 推出的 Supercomputer 已具备跨会话记忆、Skills、自动化、计算机和文件系统，而自建这些功能需要数周。
Awaiting translation
Inside Claude Code, Anthropic has already built up hundreds of Skills in active use. The team sorts them into nine categories—library and API references, product validation, data fetching and analysis, business process automation, code scaffolding, code quality and review, CI/CD and deployment, runbooks, and infrastructure operations—and notes that the best Skills should fall cleanly into one of them.
Why it matters: Anthropic’s internal framework for categorizing hundreds of Skills, along with its experience writing them, can carry over to a team building its own Skill library.
Drew Breunig 提出，当 AI 智能体可以解释一切时，面向人类的文档应转向帮读者建立心智模型，而非追求完整参考。他认为人们愿意写 Skill 却抗拒写文档，是因为智能体承担了大部分写作、可边用边改、能立即产生价值且不必反复精修，Skill 本身也兼具文档作用。
Awaiting translation
Lovable 上线 Skills 功能，把重复交代的工作方式写成可复用的 markdown 技能文件，在相关任务出现时按需加载。技能以文件夹形式组织，主文件 SKILL.md 含 name、description 和 instructions，description 是决定是否触发的唯一依据，支持文件只在主文件引用且确实需要时才加载。
Awaiting translation
Why it matters: 官方详解 Lovable Skills 的文件结构、触发机制与写法，并给出可对照的正反示例。
宝玉观察到 Codex、Claude 桌面版、Cursor 3.0、TRAE SOLO 几乎同时收敛到左侧会话、中间对话、右侧工作区的三栏布局，认为这是 Agent 交互的当前最优解。
Awaiting translation
作者把 Claude Code 的使用进阶分为六个段位：提示词工程师、协作规划师、上下文工程师、工具装备师、Skills 工程师和指挥官。
Awaiting translation
Superpowers 5.1.0 发布，重做了 git worktree 的使用方式，以适配 Claude Code 和 Codex 对 worktree 的一等支持。该版本移除了早期遗留的废弃 slash 命令，将 code reviewer 子智能体改为带自定义提示词的普通子智能体，并新增对 Factory Droid 的支持、优化 OpenCode 集成。
Awaiting translation
宝玉翻译并解读 Manthan Gupta 对 Hermes Agent 记忆系统的拆解，指出 Hermes 拥有四套记忆：MEMORY.md 与 USER.md 提示词记忆、SQLite 会话存档 session_search、作为程序记忆的 Skills，以及可选的 Honcho 用户建模层。
Awaiting translation
Prime Radiant 发布两款新技术的研究预览：Greenfield 把现有软件（代码库、文档、API 客户端等）转成行为规格语料，Iterative Development 则是一套基于 Superpowers 的智能体方法论，把大规格拆成需求、打包成开发 epic 后交给编码智能体实现。
Awaiting translation
Why it matters: Prime Radiant 公开两套工具的研究预览，读者可了解从旧代码库提取行为规格再驱动智能体重建产品的思路。
Anthropic 的 Thariq Shihipar 复盘了 Claude Code 工具设计中的取舍，核心主张是工具要贴合模型自身能力，而判断能力边界只能靠观察输出和反复实验。
Awaiting translation
Why it matters: Anthropic 工程师复盘 Claude Code 工具设计的取舍，给出可迁移到自建智能体的判断方法。
Based on the Claude Code source code that leaked unexpectedly last week, Drew Breunig mapped out how the system prompt is assembled: components fall into two categories—always included and conditionally included—and shift based on toggles like output_style, repl_mode, user_type_ant, skills_enabled, and mcp_connected.
Why it matters: The author breaks down the dynamic assembly logic behind Claude Code's system prompt, showing how conditional context engineering works in practice.
飞书开源命令行工具 lark-cli，让 AI Agent 直接发消息、查日历、写文档、建多维表格、发邮件和管理任务，安装方式为 npm install -g @larksuite/cli 加 npx skills add https://github.com/larksuite/cli -y -g。
Awaiting translation
Thariq Shihipar, an engineer on Anthropic’s Claude Code team, summed up what the team learned from using hundreds of active Skills internally, sorting them into nine categories: library and API references, product validation, data acquisition and analysis, business process automation, code scaffolding, code quality and review, CI/CD and deployment, operations runbooks, and infrastructure operations.
Why it matters: Anthropic’s internal classification system for hundreds of Skills, along with its writing tips, can be adapted to help teams design their own Skills.
Superpowers 5 发布，作者称最喜欢的改动是 Visual Brainstorming 伴随工具，它会在智能体认为有内容需要展示时提示用户，通过本地 web 服务器加载智能体写出的 HTML 片段，并把浏览器里的点击和反馈回传给智能体，以替代 Claude 常生成的 ASCII 图。
Awaiting translation
Why it matters: 作者是 Superpowers 维护者，文中说明了 5.0 的视觉头脑风暴、spec 评审循环和子智能体开发三项变化，可据此判断是否值得接入现有工作流。
OpenAI 用 Codex 配合仓库内的 Skills、AGENTS.md 和 GitHub Actions 维护 Agents SDK 仓库，把验证、发布准备、示例集成测试和 PR 评审变成可重复流程。
Awaiting translation
Why it matters: OpenAI 官方公开了用 Skills、AGENTS.md 和 GitHub Action 维护 Agents SDK 仓库的完整配置，可迁移到其他开源项目。
作者认为纠结选 Claude Code、Codex 还是 Cursor 是问错了问题，因为三家都在拼通用编码能力这一商品化层，而真正拉开差距的是组织自己的领域术语、数据布局、认证流程和发布规则。
Awaiting translation
A Martin Fowler team article breaks down context engineering for coding agents, sorting context configuration into reusable prompts (instructions and guidelines), context interfaces (tools, MCP Servers, Skills), and workspace files. It then splits these by "who decides what gets loaded" into three categories: the LLM, the human, and the agent software.
Why it matters: Using Claude Code as an example, this piece walks through how to configure context for coding agents and lays out the trade-offs between loading on demand and building up gradually.
Jesse Vincent 提出 Latent Space Engineering，即通过提示词把模型推入更有利于完成任务的潜在空间，而非只往上下文窗口塞事实信息。
Awaiting translation
Why it matters: 作者提出用情绪化提示词把模型推入更佳状态，并给出多个可迁移的实操例子。
OpenAI's developer blog explains how to systematically test Codex Agent Skills with evals, turning "it feels better" into comparable scores.
Why it matters: It lays out a complete workflow for systematically validating Codex Skills with evals, from defining success criteria to deterministic checks and scoring.
Crafter Station 发布首个上下文工程 Skill /intent-layer，可通过 npx skills add crafter-station/skills --skill intent-layer -g 安装，支持 Claude Code、Codex、Cursor、Copilot 等 10 多个智能体。
Awaiting translation
作者为 Discord 游戏项目搭建了一条 AI 内容流水线，用 Claude Code Skill 把图像生成、Discord 表情包转换和 Sora 视频动画串成可复用工具。
Awaiting translation
作者认为 Claude Code Skills 按需触发，仓库里放 40 到 100 个 Skill 在调用前不占上下文，而 MCP 每个会话都要加载全部工具描述并逐项目开关配置。
Awaiting translation
作者实测 OpenAI Codex CLI 新增的 Skills 支持，该功能目前藏在 feature flag 后，需用 codex --enable skills 开启。
Awaiting translation
Why it matters: 作者实测 Codex 的 Skills 支持，对比 Claude Code 的加载方式，并给出目录结构与触发规则。
Superpowers 4.0 发布，核心改动是把实现步骤后的代码评审拆成两个智能体：先由 spec review 智能体确认实现符合计划，通过后 code review 智能体再检查代码质量，两步都改为循环执行，协调智能体知道实现者修复后要重跑评审。
Awaiting translation
Claude Code lets the model know which Skills exist by injecting their names and descriptions into the system prompt. When there are too many Skills, or the description fields are too long, the system prompt stops listing them, so the model can't use them — and the prompt also tells the model not to use any Skill that isn't listed.
Why it matters: The author explains why Claude Code doesn't trigger installed Skills, and gives a temporary fix using environment variables that you can apply right away.
Harper Reed 用 Claude Code 接入 Pipedream 等 MCP 服务器处理邮件，让 Claude 检查收件箱、查日历和联系人后起草回复，但只保存为草稿由他逐封审核后发送。
Awaiting translation
作者把自己的软件开发工作流工具集 Superpowers 移植到了开源智能体编程工具 OpenCode。
Awaiting translation
Author Jesse Vincent spent an afternoon porting Superpowers and the whole SKILL.md system to the OpenAI Codex CLI, shipping it with Superpowers 3.3.0.
Why it matters: The author ported Claude's SKILL.md system to the Codex CLI, with tool mappings and install instructions, so you can judge whether reusing Skills across models is feasible.
The author built the episodic-memory plugin for Claude Code so it can search past session logs. By default, Claude Code deletes the .jsonl session logs under ~/.claude/projects after one month; you can extend retention via cleanupPeriodDays in ~/.claude/settings.json.
Why it matters: The author turned Claude Code's session logs into semantically searchable episodic memory, so readers can judge for themselves how long-term context is preserved across sessions.
Jesse Vincent 为 Claude Code 创建新插件 superpowers-lab，用作开发中 Skill 的孵化器。
Awaiting translation
Anthropic rolled out its first-party Skills system simultaneously on Claude Code, Claude.ai, and the Claude API, and author Jesse Vincent quickly followed with a new version of Superpowers built on the official Skills.
Why it matters: Drawing on nearly a month of hands-on use, the author compares the official Skills with his own setup and lays out the trade-offs involved in migrating.
作者发布 Superpowers 2.0，把 skills 抽成可 fork 和本地管理的独立 git 仓库，方便添加、定制和分享 skills。随后他在 claude --debug 日志中发现 Claude Code 会把 SKILL.md 的 YAML name 字段转成 SlashCommand，并认为可以自动激活它们，这比他设计的引导方式更可靠。
Awaiting translation
Author Jesse Vincent released Superpowers, a set of Skills built on Claude Code's new plugin system. Once installed, it injects a guiding prompt through the session-start hook, prompting Claude to proactively search for and use these Skills.
Why it matters: The author packaged his own coding-agent workflow into an installable Skill plugin, so readers can directly reuse his implementation flow from brainstorming to TDD.