Skill Issue: How to Write Skills That Actually Work

AgentCon 2026, Miami Video Coming Soon
A presentation at AgentCon in June 2026 in Miami, USA by Baruch Sadogursky

Abstract

A skill is software — so write it like software. You already wrote skills; the reason they don’t actually work is that you stopped at the prompt. This talk fixes that across five practices: kill the non-determinism with scripts (tested green and red), make the mandatory behavior certain with rules, test the fuzzy parts with evals that isolate the context’s own contribution (bleeding, leaking, and lift — not vibes), review them across models with versioning and rollback, scan them as both code AND prompts, and distribute them through a registry with discovery and telemetry that measures install and activation. And because the policy that governs all of this is itself a context artifact, it gets the same treatment — reviewed, tested, and gated in CI. The talk itself is a plugin: every prescription on stage is a real rule shipping on the Tessl registry.

Resources

The Repos & Plugins

Skills — Standard & Platform

Tessl — Platform & Registry

Tessl Blog — Skills

Tessl Blog — Evals

Tessl Blog — Context Engineering

Determinism in the Demos

Agents Referenced

Speaker