Workthrough logo

Workthrough

Community
bear2u
workthrough

Automatically document all development work and code modifications in a structured workthrough format. Use this skill after completing any development task, bug fix, feature implementation, or code refactoring to create comprehensive documentation.

Overview

Publisherbear2u
Repositorymy-skills
Skill nameworkthrough
Stars
932
Forks
210
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by bear2u on GitHub. Read the source before you install it.

Installation

Install the Workthrough AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bear2u/my-skills.git /tmp/my-skills
mkdir -p .claude/skills
cp -r /tmp/my-skills/skills/workthrough .claude/skills/workthrough
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workthrough in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Workthrough on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Workthrough is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

This skill automatically generates detailed workthrough documentation for all development work, capturing the context, changes made, and verification results in a clear, structured format.

When to Use This Skill

Use this skill automatically after:

  • Implementing new features or functionality
  • Fixing bugs or errors
  • Refactoring code
  • Making configuration changes
  • Updating dependencies
  • Resolving build/compilation issues
  • Any significant code modifications

Documentation Structure

The workthrough documentation follows this structure:

  1. Title: Clear, descriptive title of the work completed
  2. Overview: Brief summary of what was accomplished and why
  3. Changes Made: Detailed breakdown of all modifications
  4. Code Examples: Key code snippets showing important changes
  5. Verification Results: Build/test results confirming success

Implementation Guidelines

When generating workthrough documentation:

1. Capture Complete Context

  • What problem was being solved?
  • What errors or issues existed before?
  • What approach was taken?
  • Why were specific decisions made?

2. Document All Changes Systematically

  • List each file modified with full paths
  • Describe what changed in each file
  • Include before/after code snippets for significant changes
  • Note any dependencies added or removed
  • Document configuration updates

3. Show Code Examples

Use clear, well-formatted code blocks:

language
// file: src/path/to/file.tsx
<div className="example">
  {/* Show relevant code changes */}
</div>

4. Include Verification

  • Build output showing success
  • Test results
  • Error messages (if any remain)
  • Exit codes
  • Screenshots (if relevant)

5. Use Clear Formatting

  • Use markdown headers (##, ###)
  • Use bullet points and numbered lists
  • Use code blocks with syntax highlighting
  • Use blockquotes for output/logs
  • Keep paragraphs concise

Document Organization

Save workthrough documents with this naming convention:

workthrough/YYYY-MM-DD-brief-description.md

Or organize by feature/project:

workthrough/feature-name/implementation.md
workthrough/bugfix/issue-123.md

Example Workthrough Structure

markdown
# [Clear Descriptive Title]

## Overview
Brief 2-3 sentence summary of what was accomplished.

## Context
- Why was this work needed?
- What was the initial problem/requirement?
- Any relevant background information

## Changes Made

### 1. [First Major Change]
- Specific modification 1
- Specific modification 2
- File: `path/to/file.tsx`

### 2. [Second Major Change]
- Specific modification 1
- File: `path/to/another-file.ts`

### 3. [Additional Changes]
- Dependencies added: `package-name@version`
- Configuration updates: `config-file.json`

## Code Examples

### [Feature/Fix Name]
```typescript
// src/path/to/file.tsx
const example = () => {
  // Show the key code changes
}

Verification Results

Build Verification

bash
> build command output
✓ Compiled successfully
Exit code: 0

Test Results

bash
> test command output
All tests passed

Next Steps

  • Any follow-up tasks needed
  • Known limitations or future improvements

## Automation Instructions

After completing ANY development work:

1. **Gather Information**
   - Review all files modified during the session
   - Collect build/test output
   - Identify the main objective that was accomplished

2. **Create Document**
   - Generate workthrough document in `workthrough/` directory
   - Use timestamp or descriptive filename
   - Follow the structure guidelines above

3. **Be Comprehensive**
   - Include all relevant details
   - Don't assume future readers have context
   - Document decisions and reasoning
   - Show concrete examples

4. **Verify Completeness**
   - Confirm all changes are documented
   - Include verification results
   - Add any relevant warnings or notes

## Quality Standards

Good workthrough documentation should:
- Be readable by other developers
- Provide enough detail to understand changes
- Include verification that changes work
- Serve as a reference for similar future work
- Capture important decisions and context

Avoid:
- Overly verbose descriptions
- Unnecessary technical jargon
- Missing verification steps
- Vague or unclear explanations
- Incomplete code examples

## Output Location

Unless specified otherwise, save workthrough documents to:

workthrough/YYYY-MM-DD-brief-description.md


Create the `workthrough/` directory if it doesn't exist.

## Integration with Workflow

This skill should be triggered automatically at the end of development sessions. The documentation serves as:
- A development log/journal
- Knowledge base for the project
- Onboarding material for new developers
- Reference for debugging similar issues
- Record of architectural decisions

Remember: Good documentation is a gift to your future self and your team.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Workthrough AI skill do?

Automatically document all development work and code modifications in a structured workthrough format. Use this skill after completing any development task, bug fix, feature implementation, or code refactoring to create comprehensive documentation.

Why use Workthrough on TypingMind?

Because you install it once and use it with any model. Workthrough is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Workthrough in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bear2u/my-skills/tree/master/skills/workthrough. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Workthrough?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Workthrough?

As many as you like. As long as a model supports skills, you can use Workthrough with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Workthrough AI skill free?

Yes. It is published on GitHub by bear2u under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇