general-workflow-planner

Official

Turn high-level goals into executable research steps

Authorlearningmatter-mit
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It converts a high-level scientific objective into a concrete, chronological execution plan that an AI can directly carry out with existing AtomisticSkills and MCP tools.

Core Features & Use Cases

  • Objective to action decomposition: Breaks a proposed or literature-derived workflow into key scientific stages (e.g., generation → relaxation → stability → dynamics).
  • Skill registry mapping: Matches each conceptual step to verifiable skill directories under .agents/skills and documented MCP tools.
  • Dependency-aware planning: Builds data-flow dependencies between steps and flags missing capabilities that require new scripts/skills.
  • Detailed Action Plan output: Produces a straightforward list of steps (with suggested hyperparameters) that can be inserted into research_plan.md.

Quick Start

Ask your AI to use general-workflow-planner to decompose your literature or user-proposed materials research objective into a detailed, chronological research_plan.md action list using only existing skills and MCP tools.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: general-workflow-planner
Download link: https://github.com/learningmatter-mit/AtomisticSkills/archive/main.zip#general-workflow-planner

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.