Skip to content

The Hands-on AI Plugin

One plugin, one install, three categories of work. Bundles the Business-First AI Framework (methodology), the AI Registry (documentation tooling), and Agentic Coding (feature-spec writing) — everything you need to take an AI workflow from idea to documented production system. 1 agent + 13 skills.

These are plain-text Markdown files that work in any AI tool. Install as a Claude Code plugin for the full experience, or download individual skills as ZIPs for ChatGPT, M365 Copilot, Cursor, and other platforms.

One-command install in Claude Code with automatic agent routing and slash commands:

Terminal window
/plugin marketplace add jamesgray-ai/handsonai-plugins
/plugin install handsonai@handsonai

See Using Plugins for setup details across Claude.ai upload, Cowork, and API usage.

The plugin is organized into three coherent toolkits. Use them independently or together.


The seven-step methodology for going from a workflow idea to a deployed AI system: Analyze → Deconstruct → Design → Build → Test → Run → Improve. Run the full flow with the orchestrator agent, or invoke any individual step as a skill.

Walks you through the full 7-step framework end-to-end. The agent calls the right skill at each step, gathers inputs from you between steps, and produces working artifacts (specs, prompts, agents) along the way.

When to use it: Use this when you have a workflow you want to apply AI to and want guided, end-to-end help. If you’d rather drive each step yourself, invoke the skills directly.

SkillSlash commandWhat it does
analyze/handsonai:analyzeAudit your workflows (individual or organizational lens) to find where AI creates the most value
deconstruct/handsonai:deconstructBreak a workflow into structured steps using the 6-question framework
design/handsonai:designDesign the AI workflow architecture and produce an AI Building Block Spec
build/handsonai:buildGenerate platform-appropriate artifacts (prompts, skills, agents) from the approved spec
test/handsonai:testTest workflow artifacts and evaluate output quality
run/handsonai:runGenerate a Run Guide for deploying and operating the workflow
improve/handsonai:improveEvaluate a running workflow for quality and evolution opportunities

Full documentation: The Business-First AI Framework walks through the methodology with worked examples for each step.


Once you’ve built workflows worth tracking, you need a registry. These four skills give you naming conventions, documentation templates, and Notion-backed registration for keeping a clean catalog of what you’ve built.

Slash command: /handsonai:naming-workflows

Generates consistent, outcome-focused names and descriptions for business workflows, then creates entries in your Notion Workflows database. Follows domain-specific naming patterns (Sales, Marketing, Product, Education, Operations) so your registry stays organized as it grows.

Slash command: /handsonai:writing-workflow-sops

Writes Standard Operating Procedure documentation for workflows and saves them as Markdown files, with optional linking to your workflow tracker. Selects a full or lightweight SOP template based on autonomy level (deterministic vs. guided/autonomous) and adapts for execution mode (Manual, Augmented, Automated).

Slash command: /handsonai:writing-process-guides

Writes Business Process Guide documentation that explains the strategic context and rhythm of a complete business process — when to execute it, why it matters, and how its component workflows fit together. The strategic companion to tactical SOPs.

Slash command: /handsonai:registering-building-blocks

Registers any AI building block — Skills, Agents, Prompts, or Context MDs — in your Notion AI Building Blocks database. Resolves the asset type from your request, extracts metadata from the appropriate source file, generates a Quick Start Prompt, checks for duplicates, and creates or updates the registry entry.

Recommended workflow: Name → Document procedure (SOP) → Connect workflows (Process Guide) → Register building blocks. Each skill works independently if you don’t need the full sequence.


For turning ideas into shippable feature specs before you write code. Two skills — one for fuzzy ideas, one for production specs.

Slash command: /handsonai:writing-vision-briefs

Captures a fuzzy idea as a structured Vision Brief — the essence of an idea before formal requirements. Walks you through problem, users, vision, capabilities, and success criteria in plain language. Assesses scope and breaks bigger visions into epics and features. Feeds directly into writing-feature-prds.

Slash command: /handsonai:writing-feature-prds

Creates a Product Requirements Document for one feature with user stories, acceptance criteria, and a linked GitHub issue. Stress-tests the PRD for edge cases and ambiguity before finalizing.

Full documentation: Agentic Coding shows the full feature-development workflow these skills plug into.


Earlier versions of the marketplace shipped specialized agents for executive writing, HBR-style editorial review, AI news research, and meeting prep, plus several portable prompts. They’ve moved to the Example Gallery as study material — copy and customize them for your own workflows.

MIT — fork, modify, and ship freely.