<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Skills on AI Agents News</title>
    <link>https://aiagentsnews.top/tags/skills/</link>
    <description>Recent content in Skills on AI Agents News</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Wed, 29 Jul 2026 01:16:56 +0000</lastBuildDate>
    <atom:link href="https://aiagentsnews.top/tags/skills/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Superpowers framework: TDD workflows for coding agents</title>
      <link>https://aiagentsnews.top/posts/superpowers-framework-tdd-workflows-for-coding-agents/</link>
      <pubDate>Wed, 29 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/superpowers-framework-tdd-workflows-for-coding-agents/</guid>
      <description>Hermes Atlas&#39;s Superpowers framework targets the 80% SWEbench gap by enforcing spec validation before code generation in autonomous agents.</description>
    </item>
    <item>
      <title>Agent skills explained: procedural knowledge packets</title>
      <link>https://aiagentsnews.top/posts/agent-skills-explained-procedural-knowledge-packets/</link>
      <pubDate>Mon, 20 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-skills-explained-procedural-knowledge-packets/</guid>
      <description>Learn how agent skills use a mandatory SKILL.md file to load procedural knowledge on demand, preventing context bloat in complex systems.</description>
    </item>
    <item>
      <title>Agent skills hit 1,000: Why modular JSON beats prompts</title>
      <link>https://aiagentsnews.top/posts/agent-skills-hit-1000-why-modular-json-beats-prompts/</link>
      <pubDate>Sun, 19 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-skills-hit-1000-why-modular-json-beats-prompts/</guid>
      <description>With over 1,000 distinct agent skills now available, the shift to modular JSON Schema packages ends ad-hoc prompting for engineers.</description>
    </item>
    <item>
      <title>Agent skills: Migrate 4 rule files to one SKILL.md</title>
      <link>https://aiagentsnews.top/posts/agent-skills-migrate-4-rule-files-to-one-skillmd/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-skills-migrate-4-rule-files-to-one-skillmd/</guid>
      <description>Merge 4 fragmented rule locations into one portable SKILL.md package. Learn the 5-step migration path to unify your team&#39;s AI conventions today.</description>
    </item>
    <item>
      <title>Agent tools explained: six types for builders</title>
      <link>https://aiagentsnews.top/posts/agent-tools-explained-six-types-for-builders/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-tools-explained-six-types-for-builders/</guid>
      <description>Learn how six distinct agent tool categories range from low-risk search to high-risk desktop control, plus why Model Context Protocol matters.</description>
    </item>
    <item>
      <title>crewAI Skills: Modular Agent Architecture Explained</title>
      <link>https://aiagentsnews.top/posts/crewai-skills-modular-agent-architecture-explained/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/crewai-skills-modular-agent-architecture-explained/</guid>
      <description>crewAI 1.14.6a1 adds a Skills Repository to decouple logic, addressing fragility in the 79% of businesses already deploying agents.</description>
    </item>
    <item>
      <title>Modular AI agents: Why SkillasCode beats prompts</title>
      <link>https://aiagentsnews.top/posts/modular-ai-agents-why-skillascode-beats-prompts/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/modular-ai-agents-why-skillascode-beats-prompts/</guid>
      <description>Monolithic prompts fail at scale. Learn how SkillasCode helps manage the 40% of apps needing agents by year-end without security drift.</description>
    </item>
    <item>
      <title>Skill standard fixes agent crosstool portability</title>
      <link>https://aiagentsnews.top/posts/skill-standard-fixes-agent-crosstool-portability/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/skill-standard-fixes-agent-crosstool-portability/</guid>
      <description>Learn how the SKILL.md entrypoint combines YAML frontmatter with markdown to create portable units for four distinct agent components.</description>
    </item>
    <item>
      <title>Gaia skills: Verifying 235 AI capabilities via code</title>
      <link>https://aiagentsnews.top/posts/gaia-skills-verifying-235-ai-capabilities-via-code/</link>
      <pubDate>Thu, 09 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/gaia-skills-verifying-235-ai-capabilities-via-code/</guid>
      <description>Gaia&#39;s registry verifies 235 total skills through code execution runs. Learn how the G7 Trust Taxonomy grades capabilities from S to ungraded.</description>
    </item>
    <item>
      <title>Agent skills catalog: 18k tools from 307 repos</title>
      <link>https://aiagentsnews.top/posts/agent-skills-catalog-18k-tools-from-307-repos/</link>
      <pubDate>Sat, 04 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-skills-catalog-18k-tools-from-307-repos/</guid>
      <description>Aggregating 18,142 skills from 307 repositories, this project defines 357 canonical standards to solve AI agent fragmentation.</description>
    </item>
    <item>
      <title>Skillspector Review: Stop Blind AI Skill Installs</title>
      <link>https://aiagentsnews.top/posts/skillspector-review-stop-blind-ai-skill-installs/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/skillspector-review-stop-blind-ai-skill-installs/</guid>
      <description>Executable scripts are 2.12x more likely to harbor vulnerabilities. I review how NVIDIA&#39;s SkillSpector uses dual-stage analysis to catch these threats.</description>
    </item>
  </channel>
</rss>
