Fragmented - AI Developer Podcast 304 - Agent Skills - when to use them and why they matter
33 snips
Feb 9, 2026 They explain when to reach for agent skills versus simpler commands and why skills reduce repetition across teams. You’ll hear how skills are organized as folders with markdown, scripts, and assets. They unpack progressive disclosure and context forks to keep agents lean. They also cover installing skills, tool selection, and important security warnings about untrusted skill code.
AI Snips
Chapters
Transcript
Episode notes
Replace Repetition With Skills
- Use skills for repeated tasks instead of copy-pasting prompts to reduce toil and increase consistency.
- Share skills across teammates so the whole team benefits from deterministic, reusable tooling.
Progressive Disclosure Solves Context Bloat
- Progressive disclosure is the key feature that differentiates skills from stuffing everything into the session context.
- Skills lazily load full instructions only when the agent decides it needs them, avoiding context bloat.
Package Skills As Small Folders
- Build a skill as a folder with a skill.md and optional scripts, references, and assets to package behavior for agents.
- Include scripts for deterministic work and examples in assets to improve LLM output reliability.