Skip to content
Agent Orchestration
Skill

/ralph-validate

Run project validation (tests, lint, build) with ralph-starter

BOOST
From plugin
ralph-starter
1079 skills1 agent
Install
$ npx -y skills add rubenmarcus/ralph-starter --skill ralph-validate --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/ralph-validate

Context preview

The summary Claude sees to decide when to auto-load this skill.

Run project validation (tests, lint, build) with ralph-starter

SKILL.md

ralph-validate.SKILL.md
description: Run project validation (tests, lint, build) with ralph-starter
disable-model-invocation: true

Run all detected validation commands for a project.

1. Use `ralph_validate` with the project path 2. Auto-detects validation commands from:

  • `package.json` scripts (test, lint, build)
  • Makefile targets
  • Common patterns for the detected project type

3. Returns pass/fail status with output for each command

Use `ralph_status` first to check the overall project state and implementation plan progress.

Ships withralph-starter

Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.

Get the whole plugin

Other skills on ralph-starter.