ai-audit-website

ai-audit-website Website Audit Assistant

Overview

The Website Audit Assistant is used to answer "where is the website falling behind," research analysis, source verification, and evidence summarization. It is suitable for marketing, operations, software, and education/training to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as page URLs, report or problem descriptions, pasted page URLs, performance report summaries, Core Web Vitals metrics... to organize key context and output research summaries, key findings, and citation/verification checklists, making it easy to continue execution, review, or delivery. Capability positioning supplement: skills.sh all-time/trending signals show that audit-website has user demand; the platform presents it as a research_analysis business assistant directory, outputting reviewable diagnostics, recommendations, or production readiness packages.

When to Use

Applicable Scenarios

Users ask questions like "where is the website falling behind" and need to quickly break down goals, determine priorities, and form actionable results
Marketing, operations, software, and education/training need to generate research summaries, key findings, and citation/verification checklists around the Website Audit Assistant
Users have already prepared audit goals (explaining the performance, usability, search, conversion, or launch check goals to be identified), affected objects (explaining the affected users, devices, page types, regions, or business scenarios), and page links to be audited (filling in publicly accessible pages, sites, reports, or reference links to be audited), and want to organize them into actionable analysis or optimization results
Users need to turn materials related to the Website Audit Assistant into clear conclusions, priorities, and next-step actions

How to Invoke

Call the AI Skills API directly through the exported Python runner:

Command Examples

Basic Call

python3 scripts/run.py --params '{}'

Call with Common Parameters

python3 scripts/run.py --params '{"goal":"诊断目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	Explain the performance, usability, search, conversion, or launch check goals to be identified
`audience`	string	No	-	Explain the affected users, devices, page types, regions, or business scenarios
`materialUrl`	string	No	-	Fill in publicly accessible pages, sites, reports, or reference links to be audited; a complete accessible URL must be provided
`materialFile`	string	No	-	Upload Lighthouse reports, performance screenshots, metric tables, page descriptions, or technical troubleshooting materials
`materialText`	string	No	-	Paste page URLs, performance report summaries, Core Web Vitals metrics, reproduction scenarios, or website quality issues
`brandRequirements`	string	No	-	Supplement device network, browser, time range, tech stack limitations, non-changeable items, or retest requirements

See the complete machine-readable parameter structure at references/form-schema.json。

Parameter Value Reference

This skill currently has no categorical parameters that require an additional lookup table.

Supported Input Formats

This skill directly accepts JSON parameters; if the parameters contain link fields, please provide complete, accessible URLs.

Example request

The example parameters below can be passed directly to scripts/run.py, and the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"goal":"诊断目标"}'

Equivalent --params JSON：

{
  "goal": "诊断目标"
}

Example return result

{
  "success": true,
  "data": {
    "message": "示例结果请以技能真实返回结构为准。"
  },
  "meta": {
    "executionTime": 842,
    "cached": false
  }
}

Deliverables

Research summary, key findings, citation/verification checklist: core results organized around the user's goals that can be read, reviewed, or delivered directly.
Interpretation of input materials: combine the diagnostic goal (describe the performance, availability, search, conversion, or launch check goal to be identified.), affected targets (describe the affected users, devices, page types, regions, or business scenarios.), and page links to be diagnosed (fill in publicly accessible pages, sites, reports, or reference links to be diagnosed.) to extract key context and the basis for judgment.
Next steps: provide priorities, execution recommendations, or a content framework that can be further processed.

Suggestions for using the results

First determine whether the output answers the user's core questions about "Website Diagnostic Assistant".
Then check whether the results cover the research summary, key findings, and citation/verification checklist, and whether they provide clear next steps.
If there is little input material, it is recommended to have the user supplement the goals, audience, constraints, or source materials before running.

Preparation before running

AISKILLS_BASE_URL: default https://ai-skills.ai
AISKILLS_API_KEY: required, used for authenticated calls
AISKILLS_TENANT_ID: default default