TypingMindTypingMindThe best frontend for AI
Lighthouse Pagespeed Stinger logo

Lighthouse Pagespeed Stinger

Organization
legioncodeinc
lighthouse-pagespeed-stinger

Runs Lighthouse and PageSpeed Insights for React/Next.js: CI setup (LHCI), audit categories, performance budgets, lab-vs-CrUX gap. Use when setting up or debugging Lighthouse CI.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill namelighthouse-pagespeed-stinger
Stars
94
Forks
44
Bundled files
12
LicenseAGPL-3.0-or-later
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by legioncodeinc on GitHub. Read the source before you install it.

Installation

Install the Lighthouse Pagespeed Stinger AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/browser-and-app-testing-tools/skills/lighthouse-pagespeed-stinger
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/browser-and-app-testing-tools/skills/lighthouse-pagespeed-stinger .claude/skills/lighthouse-pagespeed-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lighthouse Pagespeed Stinger in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lighthouse Pagespeed Stinger on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lighthouse Pagespeed Stinger is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

lighthouse-pagespeed-stinger

Opinionated playbook for running Lighthouse and PageSpeed Insights correctly: in CI, locally, and as part of a long-term performance tracking strategy. Synthesized from the Lighthouse 12.6.1 + LHCI 0.15.x canon, the web.dev lab-vs-field framework, and 2025-2026 practitioner patterns.

Read first: guides/00-runner-selection.md: the decision tree for which tool to use before you touch any config.

When to use this skill

Load this skill when lighthouse-pagespeed-wasp-drone is invoked. Trigger phrases:

  • "Set up Lighthouse CI / LHCI"
  • "Add a performance budget to our CI pipeline"
  • "My Lighthouse score is 90 but CrUX says I'm failing LCP"
  • "Configure Lighthouse for GitHub Actions"
  • "What's the difference between TBT and INP?"
  • "Compare Treo vs SpeedCurve for monitoring"
  • "Write a custom Lighthouse plugin"
  • "Audit this URL with Lighthouse"
  • "Set a performance budget"

Do NOT load for:

  • SEO content strategy, keyword research, or metadata optimization (route to seo-aeo-wasp-drone)
  • Core Web Vitals implementation fixes like image optimization or JS bundle reduction (route to react-wasp-drone or performance-optimizer)
  • Accessibility design decisions beyond Lighthouse-flagged technical issues
  • CI/CD pipeline topology beyond the Lighthouse-specific configuration step (route to devops-wasp-drone)

Critical directives

These are non-negotiables. They protect reproducibility, team trust, and the lab-vs-field mental model.

  • Always specify throttling and form-factor explicitly. A mobile simulation at 4x CPU / 1.6 Mbps and a desktop no-throttle run produce completely different scores; mixing them corrupts trend data. See guides/00-runner-selection.md.

  • Run at least three passes; report the median. LHCI defaults to three runs for this reason (numberOfRuns: 3). A single Lighthouse run has high variance due to non-deterministic CPU and network simulation. See guides/01-lhci-configuration.md.

  • Always present both lab scores and CrUX field data when PSI API data is available. Lab data reflects ideal conditions; field data (p75) reflects real users. The gap between them is often the most actionable signal. See guides/02-lab-vs-field.md.

  • Never set a score budget below the current production baseline without a remediation plan. Measure first (lhci autorun without assertions), document baselines, then add a 10-20% buffer. A budget that gates CI on day one with no remediation plan blocks deploys without unblocking the team. See guides/01-lhci-configuration.md.

  • TBT is an imperfect proxy for INP. A good TBT does not guarantee a good INP. INP measures full interaction latency (delay + processing + presentation). TBT only captures blocking tasks during load. A page can have TBT < 200ms and INP > 500ms. Always check field INP separately. See guides/02-lab-vs-field.md.

  • Scope custom plugins to audits that existing Lighthouse audits cannot cover. Plugins cannot access custom Gatherers; they can only read existing artifacts (ImageElements, ScriptElements, devtoolsLogs, etc.). If you need custom page data, you need a full custom config. See guides/05-custom-plugins.md.

Lighthouse 12 / LHCI 0.15.x facts (encoded from research)

Source: research/external/2026-05-20-lighthouse-performance-scoring.md (source-repository research, not shipped with the plugin)

Current version: Lighthouse 12.6.1 (LHCI 0.15.x). Node 18+ required.

Four categories (not five: PWA removed in LH12, May 2024):

  • Performance
  • Accessibility
  • Best Practices
  • SEO

Performance score weights (unchanged from LH10):

MetricWeight
Total Blocking Time (TBT)30%
Largest Contentful Paint (LCP)25%
Cumulative Layout Shift (CLS)25%
First Contentful Paint (FCP)10%
Speed Index (SI)10%

INP is NOT in the Lighthouse Performance score. INP replaced FID as a Core Web Vital (March 12, 2024), but INP is a field-only metric. TBT is its lab proxy. TTI was removed from the score in Lighthouse 10.

Score color bands: 0-49 red (Poor), 50-89 orange (Needs Improvement), 90-100 green (Good). Reaching 90+ means being in the top 8% of HTTP Archive sites for that metric.

Guide map

Each guide is a self-contained instruction set. Read in order on first use; jump directly to the relevant guide for targeted tasks.

GuideWhen to read
guides/00-runner-selection.mdFirst: before choosing any tool
guides/01-lhci-configuration.mdSetting up lighthouserc.json/yaml, collect/assert/upload
guides/02-lab-vs-field.mdReconciling Lighthouse scores vs CrUX / PSI field data
guides/03-ci-integration.mdGitHub Actions workflow, LHCI setup, score gating
guides/04-performance-tracking.mdTreo, SpeedCurve, self-hosted LHCI server
guides/05-custom-plugins.mdAuthoring custom Lighthouse audit plugins
guides/06-audit-category-glossary.mdUnderstanding individual audits and their score weights

Templates

  • templates/lighthouserc-starter.yaml: Annotated production-ready LHCI config
  • templates/custom-plugin-starter.js: Scaffold for a custom Lighthouse plugin

Examples

  • examples/happy-path-lhci-setup.md: End-to-end LHCI setup from zero to CI-gating a Next.js app
  • examples/lab-field-reconciliation.md: Walking through a case where Lighthouse scores 90 but CrUX INP fails

Reports

  • reports/README.md: Report template and location convention for audit reports

Command Brief: ai-tools/command-briefs/lighthouse-pagespeed-wasp-drone-command-brief.md Research: research/research-summary.md (normal depth, 9 sources, May 2026) Forged by stinger-forge as part of The Wasp Nest by Mario Aldayuz a.k.a @thenotoriousllama

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lighthouse Pagespeed Stinger AI skill do?

Runs Lighthouse and PageSpeed Insights for React/Next.js: CI setup (LHCI), audit categories, performance budgets, lab-vs-CrUX gap. Use when setting up or debugging Lighthouse CI.

Why use Lighthouse Pagespeed Stinger on TypingMind?

Because you install it once and use it with any model. Lighthouse Pagespeed Stinger is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lighthouse Pagespeed Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/browser-and-app-testing-tools/skills/lighthouse-pagespeed-stinger. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lighthouse Pagespeed Stinger?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lighthouse Pagespeed Stinger?

As many as you like. As long as a model supports skills, you can use Lighthouse Pagespeed Stinger with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lighthouse Pagespeed Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
mattpocock logo

Wizard

mattpocock
CommunityPopular

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar…

22.3K
264.4K
2 files
View
affaan-m logo

Deployment Patterns

affaan-m
CommunityPopular

Flujos de trabajo de despliegue, patrones de pipeline CI/CD, contenedorización Docker, health checks, estrategias de rollback y listas de verificación de preparación para producción de aplicaciones…

39.1K
261.1K
Instructions
View
affaan-m logo

Docker Patterns

affaan-m
CommunityPopular

Patrones de Docker y Docker Compose para desarrollo local, seguridad de contenedores, networking, estrategias de volúmenes y orquestación de múltiples servicios.

39.1K
261.1K
Instructions
View
affaan-m logo

Architecture Decision Records

affaan-m
CommunityPopular

コーディングセッション中にアーキテクチャ決定を構造化ADRとして記録し、自動的に決定の瞬間を検出し、コンテキスト、検討された代替案、根拠を記録します。今後の開発者がコードベースの形成理由を理解するためのADRログを維持します。

39.1K
261.1K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇