1
阿里千问开放 AI 眼镜生态，支持自建导游、教练、巡检等多种 skill
千问开放平台上线，开发者可自建导游、视障辅助等技能，AI眼镜生态迎来新玩法
IT之家 8 月 15 日消息，阿里千问开放平台于 8 月 10 日上线，同时支持 App、PC 和 AI 眼镜三端。据官方最新介绍，在眼镜端，千问提供 技能平台和行业定制 两大模块。 在技能平台上，开发者可以调用已开放的眼镜能力，结合特定场景和人群需求创建 Skill。 调用“眼镜拍照”插件 ，为…
2
蒸馏《基层中国的运行逻辑》后，让 AI 帮你分析求学、考公、投资与创业
把《基层中国的运行逻辑》炼成 AI 方法论工具箱，帮你看懂地方权力结构，求学考公投资创业都有参考。
这个项目，把 @聂辉华 老师写的《基层中国的运行逻辑》这本书总结成了一个 skill，它把县乡村治理框架（条块、含权量、双均衡、三座大山…）提炼成可被 Cursor / Claude Code / Codex / Grok 反复调用的方法论工具箱，用来解释地方新闻与权力结构，也用来做选择：求学、考公
3
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
面向软件工程智能体的技能多目标优化新方法，值得一读
arXiv:2604.09297v3 Announce Type: replace-cross Abstract: Agent skills are increasingly used to configure coding agents for software engineering (SE) …
4
Show HN: GitHub Status Check Skill
快速检查GitHub服务状态的技能，让开发者第一时间掌握宕机与恢复信息。
A simple skill to tell AI agent to check GitHub status if something goes wrong after push to GitHub. Especially useful when actions are down otherwise…
5
开发者苦 “造轮子” 久矣，HarmonyOS 7 正在抹平系统能力的接入鸿沟
HarmonyOS 7 让开发者告别造轮子，三次越界打通设备、服务与空间，系统能力接入更简单。
Skill和Agent也能被封装调用
6
Skill packs are now available on skills.sh
一条链接打包多个agent技能，团队共享与标准化从此更简单
You can now bundle multiple agent skills into a shareable pack on skills.sh . Hand anyone a curated set via a single URL, or share it with your GitHub…
7
Ask HN: I still don't understand why AI agents need "skills"
AI 智能体为何需要“技能”？用 Markdown 文档真的够吗？HN 开发者吵出了架构真相。
I’ve asked AI a few times and I still don’t get it. Why do frameworks like Claude Code or Codex have the concept of “skills” instead of just using wel…
8
Show HN: Cross-Harness self hosted registry and analytics for AI Agents
解锁AI代理开发黑盒：自托管注册表与分析工具，让你看清MCPs和Skills的真实使用数据。
Article URL: https://github.com/Observal/Observal Comments URL: https://news.ycombinator.com/item?id=48994984 Points: 5 # Comments: 0
9
让Skill“有图可依”：openJiuwen首发多模态Skill范式Skill-Omni
openJiuwen首发多模态Skill范式Skill-Omni，让Agent从“读得懂”升级为“看得见”，将视觉知识沉淀为可复用的技能。
从文字说明书到多模态经验库
10
SkillFab: An Agent-Native Skill Production Platform
面向AI代理的原生技能生产平台SkillFab，让技能制作更智能高效。
arXiv:2607.03780v1 Announce Type: cross Abstract: SkillFab is an agent-native platform for turning missing capabilities into reviewed, reusable Agent …
11
OpenSquilla发布0.5.0 Preview：多模型集成登顶DRACO双榜，对比名单中出现最新旗舰Fable 5
集成多模型并智能路由，自动选模型省钱又高效，登顶DRACO双榜，平均成本仅$0.12
少烧钱、真交付
12
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
让AI学会自我评估技能运用，动态进化评分标准，精准提升智能体能力。
arXiv:2607.01874v1 Announce Type: new Abstract: Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool wor…
13
14
Show HN: Skillmaxxing – make every agent self-evolving
让AI agent自动复盘工作，把经验沉淀为可复用的"技能"，无需手动触发，几天内自动生成4个合理技能，越用越强。
we built an agent plugin that lets an agent reflects after real work saves the reusable part as a "skill", or improves one it already has. No command,…
15
Cisco AI Defense Skill Scanner
一款由思科开源的AI技能安全扫描器，5分钟快速检测提示注入与数据泄露风险。
Article URL: https://github.com/cisco-ai-defense/skill-scanner Comments URL: https://news.ycombinator.com/item?id=48656076 Points: 2 # Comments: 0
16
Building Your First AI Agent Skill: From Markdown to APIs
一份从零构建AI Agent技能的实战指南，覆盖规范、演练、模板与安全，适合开发者快速上手。
AI agent skills are easier to build than they look, and they scale from a simple markdown file to something that runs scripts and calls APIs. Here is …
17
What Is SKILL.md? A Practical Guide to AI Agent Skills
从单一公司功能到多平台标准，一文说清SKILL.md如何成为AI编码代理的核心技能定义文件。
If you work with AI coding agents, you have probably seen SKILL.md mentioned and wondered what it actually is. In a matter of months it went from one …
18
SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation
提出SkillMoV混合视图路由架构，用原型条件门控统一多视角能力估计，创新融合视图选择与专家路由
arXiv:2606.17615v1 Announce Type: cross Abstract: Estimating human proficiency from video is a key challenge for automated skill assessment, with appl…
19
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
新基准SkillsBench，系统评估AI Agent技能在不同任务间的通用性与迁移能力，为智能体研究提供重要参考。
arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LL…
20
Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents
看LLM代理如何通过Skill-to-LoRA实现从技能使用到行为学习的token高效进化
arXiv:2606.16769v1 Announce Type: new Abstract: Agent skills are commonly distributed as SKILL.md files: human-readable procedural documents that desc…