Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rampstackco/claude-skills --skill interactive-product-tourgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rampstackco/claude-skills/interactive-product-tour)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/interactive-product-tour"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/interactive-product-tour/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rampstackco/claude-skills/interactive-product-tour"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/interactive-product-tour.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00138 | $0.03677 |
| Opus 5 | $0.00069 | $0.01839 |
| Sonnet 5 | $0.00028 | $0.00735 |
| Haiku 4.5 | $0.00014 | $0.00368 |
Grade A, and why
interactive-product-tour scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Product Tour
A senior product marketing director's playbook for designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. The discipline of building help systems that surface at moments of need and disappear when not needed.
Most product tours fail in one of two ways. They paint every button, link, and feature with "click for tour" hints until the visual noise is so great that users develop blindness to the dots. Or they show a single first-login tour the user skips or skims, after which the same help never re-surfaces when the user actually hits a moment of friction. Help that is invisible at the moment of need is help that does not exist.
The tours that work do something different. They trigger when the user is at a moment of friction, not all the time. They surface contextual hints when the user enters a section they have not explored, clicks into a feature requiring setup, or returns after a long absence. The system knows what the user knows and surfaces help at the right moment.
The voice is the senior product marketing director who has watched feature adoption double when tours were redesigned and watched it collapse when more tooltips were piled onto every surface. Practical, opinionated about the trigger logic that distinguishes useful help from visual noise, willing to call out when no in-product tour at all is the right answer.
When to use this skill: scoping an in-product help system for the first time, auditing a tour system that produces engagement metrics with no adoption lift, designing the trigger logic that decides when help surfaces, or deciding which features warrant tours vs documentation.
What this skill covers
This skill spans in-product tours, tooltips, and contextual help. The growth-tooling distinctions:
onboarding-wizard-designis the sequential first-run experience. This skill is contextual help WITHIN the product, surfacing across the lifecycle.chatbot-flow-designis conversational help. This skill is non-conversational tour and tooltip help.interactive-product-tour(this skill) is trigger logic, tour architecture, contextual placement, completion tracking, and the discipline of being absent until needed.discovery-research-synthesisis research that informs tour content. Input, not part of.pm-spec-writingis the spec for engineers building the tour. This skill is about WHAT to build; pm-spec-writing is about communicating it.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/common-tour-failures.md 5.7 KB
- references/completion-tracking-and-re-trigger.md 7.1 KB
- references/contextual-placement-patterns.md 6.8 KB
- references/dismissal-and-non-intrusion-patterns.md 7.0 KB
- references/power-user-vs-new-user-patterns.md 7.2 KB
- references/tour-anti-patterns.md 7.1 KB
- references/tour-architecture-patterns.md 6.4 KB
- references/tour-decision-criteria.md 6.8 KB
- references/trigger-logic-patterns.md 7.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 252 lines · 138 tokens per session scan A becd45906aef
interactive-product-tour is a skill published in the GitHub repository rampstackco/claude-skills (832 stars, last pushed 2d ago), licensed MIT. It adds 138 tokens to every session and 3,677 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
johnny-suede-design
Suede Labs AI full-stack surface builder that runs design, copy, and visual QA as one pass: landing pages, brand surfaces, product UI, dashboards, campaigns, launch pages, and reference-to-target restyles (suedify). Use when a build needs layout and words together, when a redesign or launch surface has to ship end to…