RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One topic. Every takeSeek and you shall find

Reading up on Agent Skills

6 deep · digging since nov 25, 25

  • addyosmani.com favicon
    AddyOsmani.com - Agent Skills

    AI coding agents skip senior-engineer practices by default, so Addy Osmani created Agent Skills to encode workflows like specs, tests, and reviews as non-optional agent steps.

  • skills.sh favicon
    vercel-react-native-skills by vercel-labs/agent-skills

    A collection of best practices and rules for building React Native and Expo apps, covering performance, animations, and platform optimizations.

  • cursor.com favicon
    Dynamic context discovery

    Cursor introduces dynamic context discovery, pulling only necessary data into the context window via files, reducing agent tokens by up to 46.9%.

  • code.claude.com favicon
    Slash commands - Claude Code Docs

    Claude Code's slash commands and skills let users extend and control the AI's behavior via reusable instructions, dynamic context injection, and subagent execution.

  • dima.day favicon
    Build Software. Build Users

    Quality software requires understanding users deeply, so the author proposes building agentic user simulations before coding—then iterating between user and software development.

  • www.sawyerhood.com favicon
    The Bitter Lesson of LLM Extensions

    The evolution of LLM extensions shows that giving agents general-purpose computing abilities is more effective than specialized tool protocols like MCP.