Skip to main content

Agent skills

LinkedIn Learning · July 2026

Agent skills. LinkedIn Learning
1 / 31

  1. Slide 1: Agent skills. LinkedIn Learning
  2. Slide 2: Three themes: good skills are not complicated skills, skills are software, skills need to be maintained
  3. Slide 3: Lesson 1: run a skill
  4. Slide 4: What is a skill? Describe a task in plain language, the agent scans skill descriptions, loads the matching SKILL.md, and follows a repeatable workflow
  5. Slide 5: Invoking skills. Implicit: describe the task and the agent matches the skill description. Explicit: name the skill and skip the inference. Same workflow either way
  6. Slide 6: Lesson 2: inspect a skill
  7. Slide 7: Skill components: SKILL.md for required instructions, assets for curated data, references for deeper context, scripts for repeatable exact work
  8. Slide 8: Progressive disclosure: metadata stays visible while the agent scans, the skill body enters context after it triggers, extras load only when needed
  9. Slide 9: Anatomy of a skill: frontmatter with a name and a description that triggers it, then the body instructions
  10. Slide 10: Lesson 3: learn from existing skills
  11. Slide 11: Trust checklist: read the skill, installs are easy to game, check the author, check the commit history, watch for AI slop, skills are software
  12. Slide 12: Skill characteristics: installs, commits, and reputation can look strong while the source still needs review. A trustworthy skill is readable, narrow, current, and honest about what it can touch
  13. Slide 13: Hidden instructions: a rendered skill can look harmless while a hidden comment in the source changes the task
  14. Slide 14: Global vs local install. Global: always available, useful for personal habits, can pollute context. Local: scoped to the project, better for targeted updates, more maintenance
  15. Slide 15: Symlinks: one real skill lives in one place, each agent directory points at it, update the source once and every link gets the change
  16. Slide 16: Lesson 4: decide what should be a skill
  17. Slide 17: Should this be a skill? Will this recur? Can the steps be written down? Does local context matter? Would a teammate use it?
  18. Slide 18: Skills vs MCP. Use a skill when the process should travel with the project. Use MCP when the agent needs to touch the world
  19. Slide 19: Where skills meet MCP: skills are repeatable workflows, MCP is live tools and fresh state, and a skill can drive MCP tools
  20. Slide 20: Loading context: MCP is static, with every tool definition loaded up front. Skills are dynamic, loading their body on trigger and resources only when needed
  21. Slide 21: Proactive vs reactive: encode a workflow you already know before the agent needs it, or turn a correction from a real task into a skill
  22. Slide 22: Prompts, scripts, skills, MCP: a prompt is a fast instruction, a script is exact execution, a skill is workflow plus context loaded by trigger, MCP is tools and resources over a live connection
  23. Slide 23: Lesson 5: build a tiny skill
  24. Slide 24: Lesson 6: make it reusable
  25. Slide 25: Understand the workflow: visit svgl.app, search for the company logo, copy the SVG or PNG, paste it into the assets folder, reference it in markdown
  26. Slide 26: Checking coverage: the API covers visiting, searching, and copying, a tool call covers pasting, and the skill must specify how to reference the file
  27. Slide 27: Reusable skill brief: outcome, trigger, inputs, process, constraints, and what belongs in SKILL.md vs references, scripts, and assets
  28. Slide 28: Building skills is iterative: create the smallest useful skill, test it on a real task, observe vague steps and errors, update the instructions
  29. Slide 29: Lesson 7: maintain a skills repo
  30. Slide 30: Maintain the loop: use, inspect, adapt, build, maintain
  31. Slide 31: Continuously curated skills compound