Slash Command419 repo starsupdated 2d ago

do

The /do slash command intelligently analyzes user requests through a five-phase process: classifying request complexity, routing to appropriate agents and skills, enhancing context with parallel reviewers, executing the plan, and learning from patterns. Use this when you need requests automatically directed to specialized agents based on domain, complexity, and required skill sets rather than manually selecting tools.

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/do.md -o ~/.claude/commands/do.md

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

Definition

do.md

# /do - Smart Router

Route user requests to the correct agent + skill combination.

## Instructions

Call the Skill tool with `do`. Follow its classification, routing, enhancement, and execution phases.

```
Base directory: $CLAUDE_PROJECT_DIR or the current working directory
Skill file: skills/meta/do/SKILL.md
```

**Phase 1: CLASSIFY** — Assess complexity, check parallel patterns
**Phase 2: ROUTE** — Select agent + skill, display routing banner
**Phase 3: ENHANCE** — Stack retro knowledge, anti-rationalization, parallel reviewers
**Phase 4: EXECUTE** — Create the plan and dispatch through `build-dispatch.py`. The builder emits `Call the Skill tool with \`skill-name\`.` once for the primary skill and each callable stack skill.

Learning capture runs automatically via hooks — no router step (see "Learning Capture" in the skill).

The routing banner MUST be the first visible output:
```
===================================================================
 ROUTING: [brief summary]
===================================================================

 Selected:
   -> Agent: [name]
   -> Skill: [name]

 Invoking...
===================================================================
```

For complete routing, force-route triggers, and domain agent mappings, read `skills/meta/do/SKILL.md`; the routing manifest is generated by `scripts/routing-manifest.py` from the INDEX files (single source of truth).

ARGUMENTS: $ARGUMENTS