User Guide: {Product Name}

User Guide: {Product Name}

Client: {client-name} Version: {version} Date: {date} Language: {language}


1. What This Digital Talent Does

{Product name} is a digital talent that helps you with {domain}. It can:

  • {Capability 1 -- e.g., "Capture and structure requirements from stakeholder interviews"}
  • {Capability 2 -- e.g., "Generate solution designs following your methodology"}
  • {Capability 3 -- e.g., "Produce formatted diagrams and documentation"}
  • {Add all capabilities}

What It Does NOT Do

  • {Exclusion 1 -- e.g., "It does not make decisions on your behalf -- it produces artifacts for your review"}
  • {Exclusion 2 -- e.g., "It does not access external systems directly"}
  • {Add all exclusions from scope definition}

2. Getting Started

Prerequisites

  • Claude Code installed and configured
  • Access to the {product-name} workspace/repository
  • {Any other prerequisites}

Opening the Workspace

  1. Open your terminal
  2. Navigate to the {product-name} directory: cd {workspace-path}
  3. Launch Claude Code: claude
  4. Verify the talent responds: type /help to see available skills

Quick Test

Try this command to verify everything works:

/{simplest-skill-command} {sample-input}

You should see: {expected result description}


3. How to Start a New Request

Step 1: Create a Request Folder

{Describe how to initiate a new piece of work -- folder creation, file setup, etc.}

{Example folder structure or command}

Step 2: Provide Input

{Describe what input the user needs to provide and where to put it.}

Step 3: Run the Appropriate Skill

{Describe how to choose which skill to run, or how the workflow begins.}


4. Skills Reference

{Skill 1 Name}

  • Command: /{command-name} {arguments}
  • What it does: {Description}
  • Input: {What you need to provide}
  • Output: {What it produces and where}
  • Example:
/{command-name} {example-argument}

{Expected output description}


{Skill 2 Name}

  • Command: /{command-name} {arguments}
  • What it does: {Description}
  • Input: {What you need to provide}
  • Output: {What it produces and where}
  • Example:
/{command-name} {example-argument}

{Expected output description}


{Skill N Name}

{Repeat this block for every skill in the product.}


5. Standard Workflow

{If the product has a standard workflow, document the typical sequence here. If skills are independent, write "Skills can be used independently in any order." and skip subsections.}

Typical Sequence

  1. {Step 1} -- Run /{skill} to {action}
  2. {Step 2} -- Run /{skill} to {action}
  3. Review checkpoint -- {Describe where the talent pauses for your approval}
  4. {Step 3} -- Run /{skill} to {action}
  5. {Final step} -- Run /{skill} to {action}

Approval Checkpoints

The talent will pause and ask for your approval at these points:

  • After {step}: {Why approval is needed}
  • After {step}: {Why approval is needed}

6. Understanding Outputs

Where to Find Outputs

All outputs are saved in: {output-directory}/

Output File Naming

Files follow this pattern: {naming-pattern}

Example: {concrete-example}

Output Format

{Describe the standard sections/structure of output documents so the user knows what to expect.}


7. Troubleshooting

Common Issues

Problem Likely Cause Solution
Skill produces incomplete output Missing input data Verify all required fields are present in your input file
Wrong language in outputs Language not set correctly Check CLAUDE.md Section 1 for language setting
Skill not found Command name mismatch Run /help to see all available skills
Output saved to wrong location Path resolution issue Provide an absolute path or verify default directory exists
{Problem} {Cause} {Solution}

Getting Help

  • Check the Configuration Guide for adjusting settings
  • Check the Skill Reference Card for quick command lookup
  • Contact {support-contact} for issues not covered here

8. Tips and Best Practices

  • {Tip 1 -- e.g., "Provide as much context as possible in your input -- the talent produces better results with richer input"}
  • {Tip 2 -- e.g., "Review outputs before sharing with stakeholders -- the talent is a tool, not a decision-maker"}
  • {Tip 3 -- e.g., "Use the orchestrator for end-to-end workflows to ensure consistency across steps"}
  • {Add product-specific tips}