/do
Smart router: classify requests and route to the correct agent + skill
$ npx -y skills add notque/vexjoy-agent --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/do
Context preview
What this command does when you run it.
Smart router: classify requests and route to the correct agent + skill
Command definition
do.mddescription: "Smart router: classify requests and route to the correct agent + skill"
argument-hint: "[request]"
allowed-tools: ["Read", "Bash", "Grep", "Glob", "Skill", "Task"]
/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
Read more
description: "Smart router: classify requests and route to the correct agent + skill" argument-hint: "[request]" allowed-tools: ["Read", "Bash", "Grep", "Glob", "Skill", "Task"]
/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
Essays and writing behind this toolkit live at vexjoy.com. VexJoy Agent connects plain-English requests to specialist agents, skills, and workflows. /do selects the knowledge and tools needed for your task.
Repo: notque/vexjoy-agent
Other commands on vexjoy-agent.
github-notifications
Triage GitHub notifications: fetch, classify, report actions needed.
github-profile-rules
`github-profile-rules` — extract programming rules and coding conventions from a GitHub user's public profile via API.

