Walkthrough logo

Walkthrough

OrganizationPopular
udecode
walkthrough

Present final screenshots or rendered artifacts as an annotated walkthrough when visual evidence is requested.

Overview

Publisherudecode
Repositorydotai
Skill namewalkthrough
Stars
1.2K
Forks
82
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Walkthrough 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.
    https://github.com/udecode/dotai/tree/main/skills/walkthrough
  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/udecode/dotai.git /tmp/dotai
mkdir -p .claude/skills
cp -r /tmp/dotai/skills/walkthrough .claude/skills/walkthrough
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Walkthrough 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 Walkthrough 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 Walkthrough 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.

Walkthrough

Explain a completed change with a few annotated visuals. Run this after final verification. A walkthrough explains proof; it does not replace proof. Reuse the final verified frames. Do not repeat the browser walk or send messages without explicit authorization.

Honor The Caller Contract

The caller decides whether the walkthrough is required. Follow the stricter repo rule when one exists.

The caller chooses scope and whether an artifact is required. Workflow, docs, and backend changes do not create a visual obligation on their own.

When the caller requires a walkthrough and it cannot be produced, block closeout with the exact missing tool, access, or artifact. Do not waive it silently.

When the caller requires a diff check and no relevant UI or rendered-output change exists, record:

txt
Walkthrough: N/A — no UI or rendered-output change in this packet.

For a caller that requires a diff baseline, read baseline.md before the first mutation. It owns capture, comparison, and honest reconstruction.

Read The Minimum Evidence

Read only what explains the completed result:

  • the latest request and acceptance criteria;
  • the baseline, diff receipt, and final diff;
  • final screenshots or rendered proof already captured;
  • the final route, role, data fixture, viewport, theme, or source artifact.

Reuse valid final-state screenshots. Do not rerun an expensive flow only to capture the same state.

Show the inspected saved record, receipt, message, packet or final artifact, not just a control that promises it. Reuse the verifier's recorded artifact inspection when its source, identity, state and hash still match; open only missing or stale evidence. When a preview and a downloadable/readable artifact both exist, their material claims must agree. Report a contradiction as a failure without repeating an already-proved operation just for presentation.

Pick The Shortest Story

Use one to four frames. Each frame should explain one point:

  1. where the user acts;
  2. what changed or became possible;
  3. what consequence appears;
  4. what proves the result.

Prefer the shortest sequence a non-developer can understand in under one minute. Do not turn every field or test into a callout.

For QA, product-owner, or end-to-end walkthroughs, keep one subject, one user goal, one decision scope, and one time context across the whole sequence. If a frame changes any of them, label it as a separate example instead of implying causality. A screen captured after an action is not proof that the action caused that state unless the identity and time boundary match.

Capture The Real Artifact

For UI or rendered-output changes:

  • capture the real final affected surface in its verified state;
  • preserve the correct role, data, viewport, theme, and open or selected state;
  • use the repo-required browser or capture tool;
  • reuse existing final proof when it shows the required state.

For an explicit walkthrough of non-UI work, render the real final source, diff, report, document, CLI result, or provider read-back. Never invent a product screen to make backend or workflow work look visual.

Prefer light mode when both themes are equally truthful. Keep the verified theme when the change concerns dark mode or switching would misrepresent the result.

Save originals and annotated copies under a repo-approved ignored directory. Default to:

txt
tmp/walkthrough/<slug>/

Use paired names:

txt
01-<step>-original.png
01-<step>-annotated.png

Annotation

When annotation is required, read annotation.md. Retain the original and use the permitted deterministic annotation tool. This skill never authorizes changing product evidence.

Protect Sensitive Data

  • Do not send credentials, tokens, private URLs, customer data, personal data, health data, or other repo-restricted content to an image tool.
  • Use deterministic sanitized fixtures or crop and redact before annotation.
  • Do not present a mockup, recreated HTML, or synthetic screen as completed product work.
  • Do not claim the annotation itself proves runtime behavior.

Write Plain Technical Prose

Annotation labels, captions and the final handoff follow unslop. They also:

  • Cover objective, owner, chosen fix, invariant, alternatives, blast radius, verification, and remaining risk when they apply.
  • Never make the reader inspect the diff to understand why the result is correct and safe.

Final Handoff

In a project with plan pages, put the annotated images on the plan page, which is published with them, and keep the reply to the page link. Otherwise show every annotated image inline with an absolute local path. Give each image one short caption stating what to notice. Name the related test, browser, external, or source proof.

When a PR or tracker needs images, follow the owning repo's upload policy and replace local paths with hosted URLs there.

Close only when:

  • the caller's applicability rule was classified correctly;
  • the baseline and receipt exist when the caller uses a diff gate;
  • the frames cover the user action and consequence;
  • QA and product-owner flows keep one subject, goal, decision scope, and time context, or label each discontinuity as a separate example;
  • the final frame shows the saved artifact itself, not only its navigation control;
  • preview and final artifact claims agree, or the walkthrough reports their contradiction as a blocker;
  • originals and annotated copies are saved;
  • every annotation matches its original;
  • annotated images appear on the plan page, or inline when the project has none;
  • the owning proof is named.

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 Walkthrough AI skill do?

Present final screenshots or rendered artifacts as an annotated walkthrough when visual evidence is requested.

Why use Walkthrough on TypingMind?

Because you install it once and use it with any model. Walkthrough 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 Walkthrough in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/udecode/dotai/tree/main/skills/walkthrough. 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 Walkthrough?

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 Walkthrough?

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

Is the Walkthrough AI skill free?

It is published on GitHub by udecode. Check the repository for licensing terms. 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 👇