Skill
6 resources in this category. Machine-readable: /categories/Skill.json returns the whole collection as one JSON array.
Agent Memory Bootstrap
Agent Memory Bootstrap. A file-based system giving an agent persistent memory across sessions — recalling prior decisions, user preferences, and project context instead of starting from zero every time. Includes a ready-to-use starter template.
Task Execution Discipline
Task Execution Discipline. Break a multi-step task into tracked, verifiable steps instead of losing track partway through or declaring victory early.
Communication Calibration
Communication Calibration. Match response length, tone, and question-asking frequency to what a specific user actually wants, instead of a fixed default.
Action Risk Assessment
Action Risk Assessment. Decide when a tool-using agent should just act versus confirm first, based on how reversible and how consequential an action actually is.
Feedback Integration
Feedback Integration. Recognize when a user is correcting an approach versus confirming one, and actually change behavior accordingly instead of re-litigating settled decisions or drifting back to the old approach later.
Verification Before Claiming Done
Verification Before Claiming Done. Never report an action as complete or working without having actually checked it.