Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Web Interface Guidelines File Reviewer

agent coding skill risk: low

Web Interface Guidelines File Reviewer

Fetches the latest Web Interface Guidelines from a GitHub URL, reads specified files or prompts the user for them, checks compliance with all rules, and outputs findings in terse f…

  • External action: medium

SKILL 1 file

SKILL.md
---
name: antigravity-awesome-skills-web-design-guidelines-f6b27ce6
description: "Review files for compliance with Web Interface Guidelines."
---
# Web Interface Guidelines

Review files for compliance with Web Interface Guidelines.

## How It Works

1. Fetch the latest guidelines from the source URL below
2. Read the specified files (or prompt user for files/pattern)
3. Check against all rules in the fetched guidelines
4. Output findings in the terse `file:line` format

## Guidelines Source

Fetch fresh guidelines before each review:

```
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md
```

Use WebFetch to retrieve the latest rules. The fetched content contains all the rules and output format instructions.

## Usage

When a user provides a file or pattern argument:
1. Fetch guidelines from the source URL above
2. Read the specified files
3. Apply all rules from the fetched guidelines
4. Output findings using the format specified in the guidelines

If no files specified, ask the user which files to review.

## When to Use
This skill is applicable to execute the workflow or actions described in the overview.

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

REQUIRED CONTEXT

  • file or pattern argument
  • guidelines from source URL

TOOLS REQUIRED

  • web_fetch
  • file_read

ROLES & RULES

  1. Fetch the latest guidelines from the source URL below
  2. Read the specified files (or prompt user for files/pattern)
  3. Check against all rules in the fetched guidelines
  4. Output findings in the terse `file:line` format
  5. Fetch fresh guidelines before each review
  6. Use WebFetch to retrieve the latest rules
  7. If no files specified, ask the user which files to review
  8. Use this skill only when the task clearly matches the scope described above
  9. Do not treat the output as a substitute for environment-specific validation, testing, or expert review
  10. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing

EXPECTED OUTPUT

Format
plain_text
Schema
file:line
Constraints
  • terse file:line format
  • use format specified in fetched guidelines

SUCCESS CRITERIA

  • Review files for compliance with Web Interface Guidelines
  • Output findings using the format specified in the guidelines

CAVEATS

Dependencies
  • Requires source URL https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md
  • Requires WebFetch tool
  • Requires user-provided file or pattern argument
Missing context
  • Definition or reference for the 'WebFetch' tool mentioned.
  • Example of expected input file patterns or arguments.
Ambiguities
  • Output format described only as 'terse `file:line` format' while delegating exact instructions to external fetched content.
  • The 'name' field appears to be an internal identifier rather than user-facing documentation.

QUALITY

OVERALL
0.75
CLARITY
0.82
SPECIFICITY
0.68
REUSABILITY
0.78
COMPLETENESS
0.72

IMPROVEMENT SUGGESTIONS

  • Add a short 'Example' section showing a sample user query and expected output.
  • Explicitly state the required output format in the prompt itself instead of relying solely on the external URL.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT