Skip to content
TrustedSkillsbeta
Back to all skills

Ralph Plan

Official
mastra-ai·vlatest·agents

Ralph-Plan by mastra-ai generates detailed, actionable plans from ambiguous goals, breaking down tasks for efficient execution.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add mastra-ai/mastra --skill ralph-plan -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

mastra-ai

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned mastra-ai/mastra at 788ceed5b3.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
788ceed5b3
Manifest
.claude/skills/ralph-plan/SKILL.md
Scanned
1 file, 160 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The ralph-plan skill enables AI agents to create detailed, multi-step plans based on user requests. It can break down complex tasks into manageable actions, including specifying tools and resources needed for each step. The resulting plan is structured and designed for execution by an agent or human.

When to use it

  • Complex Task Breakdown: You need a large task broken down into smaller, actionable steps.
  • Agent Workflow Design: You want to define the precise actions an AI agent should take to achieve a goal.
  • Project Planning Assistance: Generate a plan for completing a project with specific deliverables and timelines.
  • Content Creation Outline: Develop a detailed outline for writing a long-form article or creating a presentation.

Key capabilities

  • Plan Generation: Creates structured plans from user prompts.
  • Action Specification: Defines individual actions within the plan.
  • Tool/Resource Identification: Identifies necessary tools and resources for each action.
  • Multi-Step Planning: Supports complex, multi-step processes.

Example prompts

  • "Create a plan to organize my home office."
  • "Generate a detailed plan for writing a blog post about AI agents."
  • “Outline the steps needed to launch a new product.”

Tips & gotchas

The quality of the generated plan depends heavily on the clarity and detail provided in the initial prompt. Be specific about desired outcomes and constraints for best results.