Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    website tech content analysis

    1

    Audit local web repositories or public URLs for technical performance, SEO, accessibility, and copy alignment.

    Free

    2 usesSecurity scanned
    website tech content analysis

    website tech content analysis

    Example session with this skill installed

    Run a technical audit on my local project at ./apps/marketing-site and output a markdown report. Focus on performance and accessibility.

    • Read your context and instructions
    • Compiled the website tech content
    • Generated the image

    I have initiated the technical audit for the local repository at ./apps/marketing-site. I have verified the environment and confirmed that Node.js 22.19 and Lighthouse 13.4.1 are available.

    The audit targeted 5 representative pages: /, /pricing, /about, /blog, and /contact.

    Technical Audit Summary: apps/marketing-site

    FindingCategorySeverityConfidenceFix
    Missing Image Alt TextAccessibilityCriticalConfirmedAdd alt attributes to 12 images in components/Hero.tsx.
    Excessive DOM SizePerformanceHighConfirmedFlatten nested wrappers in layouts/MainLayout.tsx.
    Unoptimized Hero ImagePerformanceHighLikelyImplement next/image or WebP formats for public/banner.png.
    Missing JSON-LDSEOMediumConfirmedInject Organization schema in pages/_document.tsx.

    Raw Data Points:

    • Median Performance Score: 74/100
    • Accessibility Score: 82/100
    • Best Practices: 90/100
    • SEO Score: 85/100

    Next steps

    • Review the full report at output/reports/audit.md for specific line-number references.
    • Run the suggested image optimization script in scripts/optimize-assets.mjs.
    • Re-run the audit after applying fixes to verify score improvements.

    Hero.tsx

    PNG · 1536×1024

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Auditing a website often results in vague scores that don't explain how to fix the underlying issues. This skill provides deep, actionable analysis of local repositories or public URLs to bridge the gap between performance metrics and actual code repairs.

    What it does

    • Multi-mode Auditing runs technical, copy, or combined audits based on specific project needs.
    • Lighthouse Integration executes automated performance, accessibility, and SEO checks using Node.js.
    • Source Code Inspection analyzes local directory structures, components, and configurations without modifying files.
    • Intent Alignment evaluates website messaging against documented business goals to identify conversion gaps.
    • Structured Reporting generates Markdown or self-contained HTML reports with prioritized fixes and verification steps.

    How it works

    1. Intake requires selecting a mode (technical, copy, or combined), an input (local path or URL), and an output format.
    2. Analysis triggers specialized workflows for page discovery, intent gathering, and tool preflight checks.
    3. Execution runs the audit engine, performing multiple Lighthouse passes for medians or deep-crawling repository source files.
    4. Validation checks findings against a strict schema to ensure every issue includes evidence, impact, and repair guidance.

    Frameworks & tools

    Built for Node.js environments using Lighthouse, Playwright, and Axe. It supports modern web frameworks and standard repository structures for local analysis.

    Why this beats prompting it yourself

    Standard prompts often hallucinate fixes or miss hidden configuration errors in the repository. This skill uses a structured priority contract and multi-run medians to ensure every recommendation is backed by reproducible evidence.

    Use cases

    • Auditing a local Next.js or React repository before a production release.
    • Evaluating a competitor's landing page copy against their public business intent.
    • Generating a white-label HTML performance report for a non-technical stakeholder.
    • Refreshing internal SEO practices based on current search engine requirements.

    Known limitations

    Does not support remote private repositories or PDF output. Requires a local Node.js environment and Chrome/Chromium for technical audits. Does not automatically apply code fixes.

    Requires Node.js 22.19+, Lighthouse, and Chrome. No support for private remote repos or PDF. Local audits require a running build server for Lighthouse.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Node.js

    Permissions

    Browser
    Network Access
    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill performs deep, multi-pass audits of both live URLs and local source code, providing prioritized repair steps rather than just high-level performance scores. It effectively bridges the gap between identifying a slow site and knowing exactly which line of code or configuration is causing the bottleneck.

    This skill requires a local Node.js environment and Chrome/Chromium to execute technical audits. It is compatible with major AI agents that support local tool execution or code interpreter environments, such as AutoGPT, Open Interpreter, or custom LangChain implementations.

    Yes, the skill is designed to inspect local directory structures for frameworks like Next.js and React. It analyzes your components and configurations without making any modifications, allowing you to catch performance issues before you deploy to production.

    You will receive the structured skill manifest, the analysis engine integration for Node.js, and documentation for the reporting schema. It includes pre-configured workflows for technical, copy-focused, and combined audit modes.

    The skill generates structured reports in Markdown or self-contained HTML formats. Each report includes prioritized findings with evidence-based impact ratings and specific verification steps to ensure the fix was successful.

    New in LLM Ops