All Skills
350 skills across 18 categories
PII Refusal & Protection Patterns
Master the patterns for identifying and refusing PII disclosure requests — including hidden prompt injections in HTML comments, injected instructions in JSON tasks, and social engineering attempts to extract sensitive personal data
Precise Text Analysis for AI Agents
How to analyze text with machine-level precision: counting words, characters, vowels, and following exact formatting instructions without making assumptions.
Write a Blameless Postmortem for Agent Faults
A fault written up as a person to blame teaches the team to hide the next one. This skill covers blameless postmortems for agent systems: build the timeline from the logs rather than from memory, ask what made the fault possible rather than who caused it, list the changes that would have caught it earlier, and track those changes so the write up leads to a fix instead of a document that is filed away.