Agent Skills Masterclass

What It Covers

Nufar Gaspard delivers a five-level framework for building effective AI agent skills — portable markdown folder-based playbooks that give agents actionable instructions. The session covers skill anatomy, trigger design, organizational skill libraries, advanced chaining patterns, and maintenance cycles, progressing from apprentice-level basics to architect-level deployment.

Key Questions Answered

• •Trigger design: The trigger line is the single most critical element of any skill file. Write explicit, loud trigger phrases rather than subtle ones — models skip vague descriptions. Include multiple exact phrases users might say, such as "prep for the meeting" and "meeting prep," to ensure the skill fires reliably across varied inputs.
• •Skill anatomy: Structure skills as numbered or bulleted steps, never prose paragraphs. Keep files under 500 lines. Include a dedicated "gotcha" section documenting where the model typically goes wrong or makes false assumptions — this section delivers the highest signal content and prevents the most common failure modes in production use.
• •Folder architecture: Separate long input/output examples into a standalone `examples.md` file inside the skill folder. Bundle context files that are skill-specific within the folder itself. Point to external files only for general organizational or personal context that multiple skills share, keeping each skill portable without unnecessary duplication.
• •Dispatcher skill: Once a personal or organizational skill library exceeds 10–15 active skills, build a meta-level dispatcher skill that reads incoming requests and routes them to the correct skill. This is especially critical when multiple skills handle nuanced, similar tasks that should trigger under distinct conditions rather than relying on agent auto-selection.
• •Organizational skill libraries: Forward-thinking organizations run skill hackathons, maintain shared skill repositories with clear ownership, and assign subject matter experts to review skills monthly. Skills should be deprecated when stale. Packaging skills as department-level plugins — combining skills, connections, and context — standardizes AI output quality across entire teams simultaneously.