Updated: Jul 19, 2026
Version: v1.1
Sources: 1 source
Status: Published

web-design-guidelines

Web interface audit

Vercel

Reviews accessibility, UX, performance, and interface quality against verifiable web guidance.

License: MIT
Risk: Risk level: low

Risk profile

This is a risk profile, not a certification or a safety guarantee.

What can it read? Present: It can read the interface files you point it to, and download the current design rules from the web.
What can it create or change? Not evaluated: The published fields do not say whether this skill can create or change files or other content.
Can it use the internet or send data? Present: It can use the internet to download the latest design rules for each review.
Can it use saved logins or a paid quota? Not evaluated: The published fields do not say whether this skill can use saved logins or a paid quota.
Which action needs your approval? Not evaluated: The published fields do not say which actions need your approval first.
When was the source verified, and has the snapshot changed since? Present: The source was last verified on 2026-07-19. The published snapshot still matches that verification. This is not a live check of the upstream source.

Canonical source: https://github.com/vercel-labs/agent-skills/blob/f8a72b9603728bb92a217a879b7e62e43ad76c81/skills/web-design-guidelines/SKILL.md(opens in a new tab)
Source revision: f8a72b9603728bb92a217a879b7e62e43ad76c81
License: MIT
Verification date: 2026-07-19
Source status: Verified
Change status: Snapshot consistent; The published snapshot still matches the last verification. This is not a live check of the upstream source.

Understand

Covered goals

audit a web interface
review accessibility and UX
identify interface quality risks

Inputs → outputs

UI source code or route
review scope

findings in the terse file:line format required by the fetched guidelines

Recognize

Verbatim from the English source

Triggers

review my UI
audit accessibility
check web UX

Non-triggers

create an unrelated visual identity
claim WCAG conformance without evidence
edit code when only an audit was requested

Choose

Verbatim from the English source

Permissions

read the requested UI source files
fetch the mutable Web Interface Guidelines document from its main branch

External effects

a network request retrieves mutable rules from vercel-labs/web-interface-guidelines main for every review

Compatibility

a runtime that can fetch HTTPS guidance and read the requested UI source files

Required tools

scoped source-file inspection
HTTPS fetch access to the current Web Interface Guidelines command document

Compare

Works withReact best practices Works withWeb app testing

Understand → Recognize → Choose → Compare

Pack for your agent

Pre-written instruction by SkillCodex — your request is neither sent nor used to adapt this text; no content is generated, and copying executes nothing.

Use in your agent

Complete the task with Web interface audit

# Use Web interface audit in your agent

## Objective
Use the existing web-design-guidelines skill only when it directly covers the requested task.

## Prerequisites
- UI source code or route
- review scope
- scoped source-file inspection
- HTTPS fetch access to the current Web Interface Guidelines command document

## Permissions
- read the requested UI source files
- fetch the mutable Web Interface Guidelines document from its main branch

## External effects
- a network request retrieves mutable rules from vercel-labs/web-interface-guidelines main for every review

## Procedure
- Open the canonical source pinned to revision f8a72b9603728bb92a217a879b7e62e43ad76c81.
- Read the skill instructions before calling its tools.
- Ask for confirmation before any paid, destructive, or remote effect not already authorized.
- Run the procedure within the requested scope and retain useful evidence.

## When not to use
- create an unrelated visual identity
- claim WCAG conformance without evidence
- edit code when only an audit was requested

## Expected result
- findings in the terse file:line format required by the fetched guidelines

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

Requires · scoped source-file inspection
Requires · HTTPS fetch access to the current Web Interface Guidelines command document
Requires · UI source code or route

Why it works

Activation is limited to tasks the skill actually covers.
Permissions, tools, and external effects are visible before execution.
Confirmation and the output format keep actions controllable.

Try next

Check the Web interface audit result

# Verify the Web interface audit outcome

## Objective
Check that the web-design-guidelines skill was used within scope and that its effects match the authorized request.

## Checks
- Compare the source and revision with the manifest.
- Separate local, browser, and external evidence.
- Report any permission or effect that was not disclosed.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:d691872aee2533b2e6a0688de5d07dfdbe8fd67353d4cc50ec1d8c75fa2766b9

Verify in your agent

Confirm that Web interface audit produced the right outcome

# Verify Web interface audit in your agent

## Result to check
Verify the use of web-design-guidelines for the current bounded task.

## Failure signals
- The source or revision does not match the manifest.
- A permission or external effect was not disclosed.
- The output does not match the expected artifacts.
- The skill activated for a declared non-trigger.

## Checks
- Compare the SHA-256 of SKILL.md with sha256:f4647ca866a3accf763777f83e7682954f0187cd6bea7eea0399796652414e8f.
- Confirm the permissions actually used and the observed effects.
- Verify artifacts with the narrowest available test.
- Separate local, browser, and external evidence in the report.

## Expected result
- findings in the terse file:line format required by the fetched guidelines

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

Requires · scoped source-file inspection
Requires · HTTPS fetch access to the current Web Interface Guidelines command document
Requires · UI source code or route

Why it works

The check starts from the manifest and expected artifacts, not a general impression.
Observed permissions and effects are compared with what was disclosed.
Local, browser, and external evidence stay separate in the verdict.

Try next

Prepare the next Web interface audit check

# Make the Web interface audit check reusable

## Objective
Turn the successful checks into a bounded checklist for the next use of web-design-guidelines.

## Checks
- Keep only observable signals.
- Tie each permission to its expected effect.
- Add an explicit stop if the source or revision changes.

## Guardrails
- Show the proposed changes before any external action.
- Do not publish, send, delete, pay for, or change remote state without explicit authorization.
- Preserve unrelated changes and stop if the scope becomes ambiguous.

## Output format
- Outcome or verdict.
- Files or actions involved.
- Checks run and observable evidence.
- Remaining blockers or limitations.

sha256:0714ae9828d38c53961d5da593fbdcb5ac12c5a6dd5464f1803c518ff4318664

Pack digest: sha256:356aaef113141fea5180edc0a05263644575fc0b39ee77c90aa25dfcdf14b085

Source provenance

Open the canonical source

Source revision: f8a72b9603728bb92a217a879b7e62e43ad76c81
Digest: sha256:f4647ca866a3accf763777f83e7682954f0187cd6bea7eea0399796652414e8f

Risk profile

This is a risk profile, not a certification or a safety guarantee.

What can it read?

Present

It can read the interface files you point it to, and download the current design rules from the web.

What can it create or change?

Not evaluated

The published fields do not say whether this skill can create or change files or other content.

Can it use the internet or send data?

Present

It can use the internet to download the latest design rules for each review.

Can it use saved logins or a paid quota?

Not evaluated

The published fields do not say whether this skill can use saved logins or a paid quota.

Which action needs your approval?

Not evaluated

The published fields do not say which actions need your approval first.

When was the source verified, and has the snapshot changed since?

Present

The source was last verified on 2026-07-19. The published snapshot still matches that verification. This is not a live check of the upstream source.

Canonical source

https://github.com/vercel-labs/agent-skills/blob/f8a72b9603728bb92a217a879b7e62e43ad76c81/skills/web-design-guidelines/SKILL.md

Source revision

f8a72b9603728bb92a217a879b7e62e43ad76c81

License

MIT

Verification date

2026-07-19

Source status

Verified

Change status

Snapshot consistent

The published snapshot still matches the last verification. This is not a live check of the upstream source.

Choose

Verbatim from the English source

Permissions

read the requested UI source files
fetch the mutable Web Interface Guidelines document from its main branch

External effects

a network request retrieves mutable rules from vercel-labs/web-interface-guidelines main for every review

Compatibility

a runtime that can fetch HTTPS guidance and read the requested UI source files

Required tools

scoped source-file inspection
HTTPS fetch access to the current Web Interface Guidelines command document

# Use Web interface audit in your agent ## Objective Use the existing web-design-guidelines skill only when it directly covers the requested task. ## Prerequisites - UI source code or route - review scope - scoped source-file inspection - HTTPS fetch access to the current Web Interface Guidelines command document ## Permissions - read the requested UI source files - fetch the mutable Web Interface Guidelines document from its main branch ## External effects - a network request retrieves mutable rules from vercel-labs/web-interface-guidelines main for every review ## Procedure - Open the canonical source pinned to revision f8a72b9603728bb92a217a879b7e62e43ad76c81. - Read the skill instructions before calling its tools. - Ask for confirmation before any paid, destructive, or remote effect not already authorized. - Run the procedure within the requested scope and retain useful evidence. ## When not to use - create an unrelated visual identity - claim WCAG conformance without evidence - edit code when only an audit was requested ## Expected result - findings in the terse file:line format required by the fetched guidelines ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.

# Verify the Web interface audit outcome ## Objective Check that the web-design-guidelines skill was used within scope and that its effects match the authorized request. ## Checks - Compare the source and revision with the manifest. - Separate local, browser, and external evidence. - Report any permission or effect that was not disclosed. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.

# Verify Web interface audit in your agent ## Result to check Verify the use of web-design-guidelines for the current bounded task. ## Failure signals - The source or revision does not match the manifest. - A permission or external effect was not disclosed. - The output does not match the expected artifacts. - The skill activated for a declared non-trigger. ## Checks - Compare the SHA-256 of SKILL.md with sha256:f4647ca866a3accf763777f83e7682954f0187cd6bea7eea0399796652414e8f. - Confirm the permissions actually used and the observed effects. - Verify artifacts with the narrowest available test. - Separate local, browser, and external evidence in the report. ## Expected result - findings in the terse file:line format required by the fetched guidelines ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.

# Make the Web interface audit check reusable ## Objective Turn the successful checks into a bounded checklist for the next use of web-design-guidelines. ## Checks - Keep only observable signals. - Tie each permission to its expected effect. - Add an explicit stop if the source or revision changes. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.