Run self-improve on an expert's mental model to sync with codebase. Use periodically to keep expertise files accurate.
Syncs an expert's knowledge file with the current codebase using self-improvement. Run after code changes to keep expertise accurate and up-to-date.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install google-ecosystem@melodic-software<domain-name> [check-git-diff]Run the self-improve workflow on an agent expert's expertise file to maintain accuracy.
$1: Domain name (required, e.g., "database", "websocket")$2: Check git diff flag (optional, "true" or "false", default: "true")You are running the self-improve workflow to sync an expert's mental model with the actual codebase.
Extract:
$1 (required)$2 (optional, default: true)If no domain provided, STOP and ask for domain name.
Check if expert directory exists using Glob:
Glob: .claude/commands/experts/{$1}/expertise.yaml
If not found:
Glob: .claude/commands/experts/*Delegate to the self-improver agent with:
.claude/commands/experts/{domain}/expertise.yamlThe agent will:
Display the self-improve report:
## Self-Improve Complete: {domain}
### Changes Made
- [List of changes]
### Expertise Health
| Metric | Value |
| --- | --- |
| Line count | X/1000 |
| Files validated | X/X exist |
| Functions verified | X/X accurate |
### Recommendations
- [Any recommendations for manual review]
# Sync after making changes (checks git diff)
/tac:improve-expertise database true
# Full rescan without git diff check
/tac:improve-expertise database false
# Default behavior (checks git diff)
/tac:improve-expertise websocket
| Trigger | Command |
|---|---|
| After any build/fix work | /tac:improve-expertise {domain} true |
| Periodic maintenance | /tac:improve-expertise {domain} false |
| Suspect drift | /tac:improve-expertise {domain} false |
| Before major planning | /tac:improve-expertise {domain} false |
Last Updated: 2025-12-15