Obelisk acts as a persistent memory layer for AI agents, indexing past sessions, tool calls, and workflows. It allows agents to recall how a specific bug was fixed, retrieve prior design decisions, and synthesize conclusions from historical context.
Activate this skill when a user asks "how did I fix X" or "what did we do last time". Use it proactively when modifying files with complex edit histories or when needing to synthesize a weekly/monthly recap of progress.
overview(), search(), and memories() before escalating to raw SQL.Primarily targets agents utilizing Claude Code and Codex transcript formats, but compatible with any agent that can execute Node.js scripts.
This skill has not been reviewed by our automated audit pipeline yet.