ai-performance

ai-performance Performance Diagnosis Assistant

Overview

The Performance Diagnosis Assistant is used to answer "where is performance slowing things down", performance diagnosis, website quality, and experience metrics. It is suitable for technical, product, marketing, and software use after clarifying business goals, content materials, or analysis targets. It combines inputs such as page URL, report or problem description, pasted page URL, performance report summary, Core Web Vitals metrics... to organize key context and output problem attribution, service improvement suggestions, SOPs, or FAQ lists, making it easy to continue execution, review, or delivery. Capability positioning supplement: skills.sh all-time/hot signals show that performance has user demand; the platform displays it as a local_service_ops business assistant directory, outputting reviewable diagnosis, suggestions, or production readiness packages.

When to Use

Applicable Scenarios

Users ask questions like "where is performance slowing things down" and need to quickly break down goals, determine priorities, and form actionable results
technical, product, marketing, and software need to generate problem attribution, service improvement suggestions, SOPs, or FAQ lists around the Performance Diagnosis Assistant
Users have already prepared diagnosis goals (explain the performance, availability, search, conversion, or launch check goals to locate.), affected objects (explain the affected users, devices, page types, regions, or business scenarios.), page links to be diagnosed (fill in publicly accessible pages, sites, reports, or reference links to be diagnosed.), and want to organize them into actionable analysis or optimization results
Users need to turn materials related to the Performance Diagnosis Assistant into clear conclusions, priorities, and next actions

Invocation Method

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

Command Example

Basic Invocation

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

Invocation 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, availability, search, conversion, or launch check goals to locate
`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 diagnosed; a complete accessible URL is required
`materialFile`	string	No	-	Upload Lighthouse reports, performance screenshots, metric tables, page descriptions, or technical troubleshooting materials
`materialText`	string	No	-	Paste page URL, performance report summary, Core Web Vitals metrics, reproduction scenarios, or website quality issues
`brandRequirements`	string	No	-	Supplement device network, browser, time range, tech stack limitations, items that cannot be changed, or retest requirements

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

Parameter Value Reference

The current skill has no classification parameters that require additional lookup.

Supported Input Formats

The current skill directly accepts JSON parameters; if the parameters contain link fields, pass 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

Problem attribution, service improvement suggestions, SOP or FAQ checklist: organize core results that can be directly read, reviewed, or delivered around the user's goals.
Interpretation of input materials: combine the diagnostic goal (explain the performance, availability, search, conversion, or launch check goal to be identified.), affected targets (explain the affected users, devices, page types, regions, or business scenarios.), page link 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 suggestions, or a content framework that can be further processed.

Suggestions for using the results

First determine whether the output answers the user's core question about the "Performance Diagnostic Assistant".
Then check whether the results cover problem attribution, service improvement suggestions, an SOP or FAQ checklist, and whether clear next steps are given.
If there is little input material, it is recommended to have the user supplement the goals, audience, constraints, or original 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