Slash Command393 repo starsupdated today

retro

The retro slash command provides a learning management interface for a SQLite-backed knowledge database, enabling users to view system statistics, search accumulated learnings via full-text indexing, list all entries by category, and graduate mature knowledge entries into agent skills. Use this when reviewing learning progress, discovering relevant past insights through search, or promoting validated learnings into permanent agent capabilities.

View source Repository: vexjoy-agent

Install in Claude Code

Copy

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/notque/vexjoy-agent/HEAD/commands/retro.md -o ~/.claude/commands/retro.md

Then start a new Claude Code session; the slash command loads automatically.

Definition

retro.md

# Retro Knowledge System

Interact with the learning database: view stats, search entries, and graduate mature learnings into agents/skills.

## Usage

```
/retro # Status overview (default)
/retro list # Display all accumulated knowledge
/retro search TERM # Full-text search across learnings
/retro graduate # Graduate mature knowledge into agents/skills
```

## Subcommands

### status (default)
Shows learning system health: entry counts, categories, graduation status, injection method.

### list
Displays all accumulated knowledge grouped by category from the learning database.

### search
Full-text search (FTS5) across all learnings. Returns results ranked by relevance.

### graduate
AI-driven evaluation of mature learning entries for embedding into specific agents/skills. Queries design/gotcha entries, evaluates each for prescriptive readiness, drafts modifications to the target agent/skill, and applies after user approval.

## Instructions for Claude

When the user invokes `/retro`, load and follow the skill at `skills/retro/SKILL.md`.

Parse the argument to select the subcommand:
- No argument or "status" → run status subcommand
- "list" → run list subcommand
- "search TERM" → run search subcommand
- "graduate" → run graduate subcommand

All retro operations go through `python3 ~/.claude/scripts/learning-db.py` — never parse learning files manually.

## Related

- `scripts/learning-db.py` — Python CLI for all database operations
- `hooks/session-context.py` — Injects pre-built dream payload and high-confidence patterns at session start
- `scripts/learning.db` — SQLite database with FTS5 search index