Prowler Tour logo

Prowler Tour

OrganizationPopular
prowler-cloud
prowler-tour

Keeps product-tour definitions aligned with the UI features they describe. Trigger: When modifying UI components that have associated tours, editing tour definition files, or renaming data-tour-id attributes.

Overview

Publisherprowler-cloud
Repositoryprowler
Skill nameprowler-tour
Stars
14.8K
Forks
2.4K
Bundled files
3
LicenseApache-2.0
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 prowler-cloud on GitHub. Read the source before you install it.

Installation

Install the Prowler Tour 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/prowler-cloud/prowler.git /tmp/prowler
mkdir -p .claude/skills
cp -r /tmp/prowler/skills/prowler-tour .claude/skills/prowler-tour
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prowler Tour 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 Prowler Tour 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 Prowler Tour 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.

prowler-tour

Report-only. This skill never edits tour files or UI files; it inspects the change, reports drift it finds between tours and the covered UI, and recommends actions for the developer to apply.

Early-exit rule

Run this check first. Most UI edits are not tour-related — exit cheaply.

  1. Glob ui/lib/tours/*.tour.ts.

  2. For each tour, check whether any coversFiles glob pattern matches any file in the current change.

  3. If no tour matches, respond exactly:

    No tour affected — skipping alignment check

    and exit. Do not proceed to the checklist.

  4. If at least one tour matches, continue to "Drift checklist" for that tour.

Drift checklist

For each affected tour, evaluate every item. Skip items that obviously do not apply, but list explicitly which items were checked.

  1. Orphan selectors — every step's target (which composes to data-tour-id="<tour-id>-<step.target>") must resolve to a real element in the codebase. Grep ui/ for the expected attribute value; report any step whose target is missing.
  2. Renamed selectors — a data-tour-id attribute was edited in this change. Match it back to any tour step referencing the old value.
  3. Outdated copy — a popover title/description references a button label, heading, or term that no longer exists on the covered page.
  4. Obsolete steps — a step describes a section, panel, or workflow that was removed.
  5. Missing steps — a new feature was added on the covered surface without a corresponding step (e.g. a new panel, a new primary action, a new wizard stage).
  6. Reordered flow — the user's path through the feature changed (e.g. query builder moved before scan selection) and the step order no longer reflects it.

Version-bump decision tree

Apply per tour after listing drift:

  • NO bump when the change is cosmetic. Examples: fix a typo, soften copy, rename a data-tour-id selector while keeping the same step, swap one screenshot for another, tighten wording.
  • BUMP version when the user-visible flow changes materially. Examples: a new step was added or removed; the order changed; an anchored target was retargeted to a different panel; the tour now covers a new feature on the surface.

When in doubt, ask: "Would a user who already saw the previous version miss something useful by not seeing this one?" If yes, bump.

Output format

When emitting a report, follow the exact structure in references/output-format.md. The structure is mandatory because the report is consumed downstream and tolerates no field reordering.

What this skill MUST NOT do

  • Do not edit *.tour.ts files. This skill is report-only.
  • Do not edit UI files to add or rename data-tour-id attributes.
  • Do not invent new tours. Authoring a new tour is a separate, deliberate decision — the developer makes it, not the skill.
  • Do not flag drift in tours whose coversFiles do not match any file in the current change. Stick to the early-exit rule.

See also

  • references/output-format.md — exact report template (read when emitting a report).
  • references/tours-architecture.md — code map for the tour abstraction under ui/lib/tours/.
  • assets/tour-template.ts — boilerplate for authoring a new *.tour.ts.

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 Prowler Tour AI skill do?

Keeps product-tour definitions aligned with the UI features they describe. Trigger: When modifying UI components that have associated tours, editing tour definition files, or renaming data-tour-id attributes.

Why use Prowler Tour on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/prowler-cloud/prowler/tree/master/skills/prowler-tour. 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 Prowler Tour?

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 Prowler Tour?

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

Is the Prowler Tour AI skill free?

Yes. It is published on GitHub by prowler-cloud under the Apache-2.0 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 👇