Playbooks for AI agents
Agent Skills
Reusable skills I hand to AI agents so they behave like careful engineers: orient before coding, edit surgically, and degrade gracefully. Filter by category or search the set.
- coding
Safe File Editing Playbook
A skill that teaches an agent to make surgical, reversible edits to a codebase without breaking unrelated code or losing the user's intent.
#agents#editing#safety#codebase - research
Codebase Recon Before Coding
A skill for orienting an agent inside an unfamiliar repository — finding the right files, conventions, and contracts before making any change.
#agents#research#codebase#discovery - infrastructure
Graceful Degradation for Build Pipelines
A skill that teaches an agent to design build steps that never hard-fail on missing credentials or services — always falling back to a safe default.
#agents#ci#reliability#build