Hermes Diagnostic Review

Overview

Review the user's own Hermes session history, read-only, to find recurring mistakes, failed tool calls, and problems the user had to re-fix or re-explain. Turn the findings into a suggestion-only report plus proposed reusable skills. Nothing is ever applied automatically: every change stays human-gated.

This skill is the reasoning half of a diagnostic-review loop. The deterministic companion hermes-maintenance-loops improvement CLI (in the hermes-loops package) accepts an explicitly supplied outcome packet and emits suggestion-only records from a frozen classification rubric. It does not score, keep, or revert anything. This skill does the collection and judgment; the CLI is an optional downstream recorder, not the review's gate.

When to Use

Trigger on requests like:

• "review my recent sessions for improvements"
• "what did I mess up or keep fixing lately"
• "find recurring mistakes in my history"
• "mine my sessions for reusable skills"
• "scan my sessions for failed tool calls"

Do not use for: pruning, exporting, or backing up session history (that is hermes-session-maintenance); evaluating Hermes's own costs, architecture, or skill library (that is hermes-self-evaluation).