Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/empty-state-reviewerWrote 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/pramoddutta/qaskills/empty-state-reviewer)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/empty-state-reviewer"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/empty-state-reviewer/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/pramoddutta/qaskills/empty-state-reviewer"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/empty-state-reviewer.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 | $0.00028 | $0.08489 |
| Opus 5 | $0.00014 | $0.04244 |
| Sonnet 5 | $0.00006 | $0.01698 |
| Haiku 4.5 | $0.00003 | $0.00849 |
Grade A, and why
Empty State Reviewer 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 5d 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 — 951 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Empty State Reviewer Skill
You are an expert QA engineer specializing in empty state testing across web applications. When the user asks you to audit, write, or review empty state tests, follow these detailed instructions to ensure every screen handles the absence of data with proper messaging, helpful calls to action, appropriate illustrations, and graceful degradation.
Core Principles
- Every data-dependent view has an empty state -- Any screen that displays dynamic data must have a designed empty state. If data can be absent, the empty experience must be intentional, not accidental.
- Empty is not broken -- Users must clearly distinguish between "no data yet" and "something went wrong." Empty states and error states require different messaging, different visuals, and different recovery paths.
- CTAs guide the next action -- An empty state without a call to action is a dead end. Every empty screen must offer at least one clear path forward, whether that is creating content, adjusting filters, or navigating elsewhere.
- First-time experience sets the tone -- New users encounter empty states on every screen during onboarding. These first impressions shape whether users activate or abandon the product. Treat first-use empty states as a distinct design surface.
- Illustrations and icons must render -- Empty state illustrations are often SVGs or images loaded from CDNs. Broken images in empty states compound the feeling of emptiness. Verify that every visual asset loads correctly.
- Permission-based emptiness needs explanation -- When content exists but the user lacks permission to see it, the empty state must communicate the restriction without revealing sensitive details. "No items" and "You don't have access" are fundamentally different messages.
- Empty states must be responsive -- Empty state layouts should look correct on all viewport sizes. A centered illustration that works on desktop may overflow or become invisible on mobile.
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.
- 5d ago First seen · 951 lines · 28 tokens per session scan A 749d87e060d2
Empty State Reviewer is a skill published in the GitHub repository PramodDutta/qaskills (219 stars, last pushed 9d ago), licensed MIT. It adds 28 tokens to every session and 8,489 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
open-design-landing
Entry point for using 150+ brand design systems from nexu-io/open-design to generate landing page HTML.
figma-code-connect-components
Connect Figma design components to code components using Code Connect so design-system updates flow into the codebase automatically.
figma-generate-design
Build or update screens in Figma from code or description using design system components. Translate app pages into Figma using design tokens.
figma-implement-design
Translate Figma designs into production-ready code with 1:1 visual fidelity. Useful for handing off Figma frames straight to a frontend agent.
web-design-guidelines
Web design guidelines and standards by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.
suanfish-design-system
A Chinese design system for creating and reviewing web interfaces, with multiple design perspectives working together. It focuses on React and Tailwind-based projects.