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 jpoutrin/product-forge --skill qa-screenshot-validationgit clone --depth 1 https://github.com/jpoutrin/product-forgeWrote 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/jpoutrin/product-forge/qa-screenshot-validation)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/qa-screenshot-validation"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/qa-screenshot-validation/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/jpoutrin/product-forge/qa-screenshot-validation"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/qa-screenshot-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00037 | $0.01968 |
| Opus 5.5 | $0.00015 | $0.00787 |
| Sonnet 5.5 | $0.00007 | $0.00394 |
| Haiku 4.5 | $0.00004 | $0.00197 |
Grade A, and why
qa-screenshot-validation 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 1mo 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Screenshot Validation Skill
Validate captured screenshots for layout correctness and handle masked or clipped elements.
Validation Process
After capturing each screenshot, evaluate it for:
- Element visibility - Is the target element fully visible?
- Layout integrity - Does the layout appear correct?
- Clipping/masking - Are elements unexpectedly cut off?
- Overlapping - Are elements overlapping incorrectly?
- Rendering issues - Missing images, broken icons, etc.
Common Issues to Detect
Masked/Clipped Elements
| Issue | Indicators | Action |
|---|---|---|
| Horizontal clipping | Element cut off on right edge | Resize viewport wider |
| Vertical clipping | Element cut off at bottom | Scroll or resize taller |
| Overflow hidden | Content abruptly ends | Check parent container |
| Modal cutoff | Dialog extends beyond viewport | Resize to fit modal |
Layout Problems
| Issue | Indicators | Action |
|---|---|---|
| Overlapping elements | Text over images, buttons over content | Document as bug |
| Misaligned elements | Uneven spacing, broken grid | Document as bug |
| Missing elements | Expected element not visible | Verify selector, check visibility |
| Broken responsive | Desktop layout on mobile viewport | Document as bug |
Automatic Resize Logic
When an element appears clipped on desktop viewport:
IF element is clipped AND viewport is desktop (>1024px):
1. Try increasing viewport width by 200px
2. Retake screenshot
3. If still clipped, try 1920x1080 (full HD)
4. If still clipped, document as layout bug
Playwright Resize Commands
// Get current viewport
const viewport = page.viewportSize();
// Resize wider
await page.setViewportSize({
width: viewport.width + 200,
height: viewport.height
});
// Standard breakpoints
await page.setViewportSize({ width: 1920, height: 1080 }); // Full HD
await page.setViewportSize({ width: 1440, height: 900 }); // Laptop
await page.setViewportSize({ width: 1280, height: 720 }); // HD
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.
- 1mo ago First seen · 305 lines · 37 tokens per session scan A c3ff41362c5f
qa-screenshot-validation is a skill published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 1,968 once invoked, about $0.0001 per session on Opus 5.5. 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.