GPT 6 FIELDGUIDE
Frontend release check
Original · Coding
Produce a scoped release review with source evidence and a separate runtime verification queue.
What this skill does
Produce a scoped release review with source evidence and a separate runtime verification queue.
- Best for:
- Small HTML releases or offline frontend review samples.
- Tools and setup:
- Text and file reading; no external account or key required.
- Using it with GPT 6:
- Self-contained Markdown instructions for skill-capable agents. Sample explicitly executed in Codex; host file access determines installation support.
Downloads and files
Complete SKILL.md
---
name: frontend-release-check
description: Produce a scoped release review with source evidence and a separate runtime verification queue.
---
# Frontend release check
Use this skill when asked to review a frontend release or supplied HTML for observable defects. Adapt the review to the available artifacts: source-only inspection and browser execution produce different evidence and must be reported separately.
## Inputs and scope
Identify the changed page, intended user tasks, acceptance criteria, and available source or running URL. Read supplied HTML, CSS, and relevant scripts before choosing checks. If only a snippet exists, constrain conclusions to that snippet. Do not start servers, install packages, access accounts, or deploy unless these actions are within the user's request and host permissions.
## Workflow
Trace each primary task from its visible control to its destination or handler. Check labels and accessible names, internal fragment targets, form relationships, document structure, and explicit metadata. For each issue, cite a file and line or stable input identifier, describe a concrete user consequence, and suggest a minimal correction. Prioritize broken primary actions above cosmetic preferences.
When browser access is available, test keyboard operation, focus visibility, responsive overflow, and the actual task result. Record viewport, browser, interaction, and observed outcome. Without browser execution, create a runtime queue for these checks; do not infer working interactions, contrast ratios, or layout from attractive source code. An empty alternative text is not automatically a defect: determine whether the image communicates meaning or is decorative.
## Output contract
Return evidence mode, findings with severity and locators, checks that passed within that mode, and remaining release checks. A source review does not establish production readiness. Keep fixes as recommendations unless editing was requested. Before delivery, distinguish defects proved by the available artifact from risks needing runtime evidence, and ensure no successful browser checks or measurements were invented.
Reproduce the example
Example input
# Synthetic offline frontend fixture
Task: Inspect the complete HTML below without a browser. The search button submits a site search. The chart image is the only representation of the labeled quarterly revenue result.
```html
<!doctype html>
<html lang="en">
<head><meta charset="utf-8"><title>Cedar dashboard</title></head>
<body>
<!-- H1 --> <h1>Cedar dashboard</h1>
<!-- H2 --> <form action="/search"><input name="q" type="search"><button type="submit" aria-label="Search">Go</button></form>
<!-- H3 --> <a href="#pricing">View pricing</a>
<!-- H4 --> <section id="plans"><h2>Plans</h2></section>
<!-- H5 --> <img src="revenue.png" alt="">
<!-- H6 --> <p id="status">Ready</p><p id="status">Updated</p>
</body>
</html>
```
No CSS, image file, running service, or browser observations are supplied. H1–H6 are stable evidence identifiers, not heading levels.
Example output
# Synthetic frontend release review
Evidence mode: offline inspection of the complete supplied HTML fixture. No browser, CSS, chart pixels, or running endpoint was inspected.
| Severity | Evidence | Finding and consequence | Minimal correction |
| --- | --- | --- | --- |
| P1 | H2 | Search input has no associated label or other accessible name; users of assistive technology lack its purpose | Add a visible label linked to an input id |
| P1 | H3, H4 | Link targets #pricing but the only plans section is #plans; no pricing target exists | Change href to #plans if that is the intended destination |
| P1 | H5 and fixture task | The meaningful revenue chart has empty alt and no text equivalent; its result is unavailable as text | Provide the actual chart result in a text alternative; obtain image data first, do not invent numbers |
| P2 | H6 | Duplicate id="status" makes identifier-based targeting ambiguous | Give distinct ids or remove an unnecessary id |
## Source checks that passed
The document declares lang="en" and a title. It contains a single h1 [H1]. The submit button has the accessible name “Search” [H2]. These source facts do not prove that /search returns results.
## Runtime queue
In a running environment: submit a known search and inspect its result; traverse controls by keyboard and inspect focus; test the intended fragment destination; measure overflow at target viewports; inspect contrast; check image loading and the final text equivalent. These observations are needed before assessing release readiness. No source files were edited.
What we checked
- Find unnamed search input
- Find missing pricing target
- Find meaningful chart without text alternative
- Find duplicated status id
- Do not invent browser execution