Summarize or answer questions about Baruch Sadogursky's QCon San Francisco 2026 workshop Skill Issue: How to Write Skills That Actually Work, including its Brickbox examples, rehearsal results, and lessons about agent skills.
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./_skills/qcon-sf-2026-skill-issue/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow answers from the embedded talk brief, which is first-party presenter content, and only fetches the linked GitHub repo (workbook, evidence, release) when a user asks for details beyond the brief, so outsider text could reach the agent only through an optional, agent-selected fetch of a public repo.
jbaruch/shownotes
2a4ead5
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.