Skip to content

feat(skills): add quickstart onboarding skill#1260

Open
mlbrilliance wants to merge 1 commit intoruvnet:mainfrom
mlbrilliance:feat/quickstart-skill
Open

feat(skills): add quickstart onboarding skill#1260
mlbrilliance wants to merge 1 commit intoruvnet:mainfrom
mlbrilliance:feat/quickstart-skill

Conversation

@mlbrilliance
Copy link

Summary

  • Adds a single new skill file .claude/skills/quickstart/SKILL.md — an interactive onboarding concierge for new users
  • Auto-activates on natural language like "get started", "how do I use this", "which command should I use"
  • Routes beginners to the right command, workflow, or swarm topology with copy-pasteable examples
  • Covers first-time setup, intent routing, concept clarification, and troubleshooting

Motivation

Directly addresses:

Both issues describe the same core problem: new users don't know where to start. This skill leverages the existing autodiscovery system to catch beginner intent and map it to the right workflow — no new CLI code required.

Scope

  • 1 new file added: .claude/skills/quickstart/SKILL.md
  • 0 files modified — no changes to CLI source, README, branding, defaults, or existing skills
  • Follows existing skill format conventions (YAML frontmatter, progressive disclosure, troubleshooting section)

Test plan

  • Verify skill file loads correctly in Claude Code session
  • Confirm auto-activation on trigger phrases ("get started", "new to ruflo", "how do I use this")
  • Confirm negative triggers don't activate (users already running swarms, specific CLI errors)
  • Validate all referenced commands match current CLI interface

🤖 Generated with Claude Code

Adds a beginner concierge skill that auto-activates on natural
language like "get started" or "how do I use this" and routes
new users to the right command, workflow, or swarm topology.

Single new file, no code changes. Addresses ruvnet#1196 and ruvnet#1251.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant