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 amplitude/mcp-marketplace --skill replay-ux-auditgit clone --depth 1 https://github.com/amplitude/mcp-marketplaceWrote 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/amplitude/mcp-marketplace/replay-ux-audit)<a href="https://agentmods.dev/skills/amplitude/mcp-marketplace/replay-ux-audit"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/replay-ux-audit/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/amplitude/mcp-marketplace/replay-ux-audit"><img src="https://agentmods.dev/badge/skills/amplitude/mcp-marketplace/replay-ux-audit.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 | $0.00095 | $0.02716 |
| Opus 5 | $0.00048 | $0.01358 |
| Sonnet 5 | $0.00019 | $0.00543 |
| Haiku 4.5 | $0.00010 | $0.00272 |
Grade A, and why
replay-ux-audit 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 7d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replay UX Audit
Watch 5-10 session replays for a specific feature, page, or flow, then synthesize patterns into a ranked friction map. This skill turns hours of manual replay watching into a structured UX report grounded in real user behavior.
CRITICAL: Tool Reference
Primary tools:
Amplitude:get_amp_session_replay_infowithaction: "search"— Find sessions matching event filters, user properties, or time windows. Use this to target sessions for a specific feature or flow.Amplitude:get_amp_session_replay_infowithaction: "events"— Decode a replay into an interaction timeline: navigations, clicks, inputs, scrolls. This is what you "watch."
Supporting tools:
- Available taxonomy reader — Inspect the connected catalog and use its event and property read capabilities to discover valid filter names and scopes. Never guess them.
Amplitude:get_amplitude_chartswithinclude: "data"— Pull quantitative context (funnel conversion rates, feature adoption) to anchor the qualitative replay findings.Amplitude:use_amplitude_ai_feedbackwithfacet: "insights"/facet: "mentions"— Cross-reference replay friction with customer feedback themes.
Instructions
Step 1: Define the Audit Scope
Determine what to audit from the user's request:
- Page or URL pattern: A specific page (e.g., /settings, /checkout)
- Feature or flow: A multi-step process (e.g., onboarding, report creation)
- Event-based: Sessions containing a specific event (e.g., "Export Clicked")
- Broad: "Audit the whole product" — narrow this down. Ask: "Which area would you like me to start with?" Suggest 2-3 areas based on high-traffic pages or known problem areas if you can identify them.
Also determine:
- Time window: Default to last 14 days unless specified.
- User segment (optional): Specific plan, platform, cohort, or user type.
Step 2: Get Context and Discover Events
- Call
Amplitude:get_amplitude_context. If multiple projects, ask which to audit. - Use the available taxonomy event reader to find events related to the target area. Look for:
- Page view or navigation events for the target area
- Key interaction events (clicks, form submissions) within the flow
- Error or failure events that may indicate friction
- If the user mentioned a flow or funnel, identify the key step events so you can filter sessions that attempted the flow.
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.
- 7d ago Changed · +1 lines 031c1d71b679
- 13d ago First seen · 216 lines · 95 tokens per session scan A e327b1bc45f8
replay-ux-audit is a skill published in the GitHub repository amplitude/mcp-marketplace (35 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 2,716 once invoked, about $0.0005 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.