Guide · Agent skill
How to use the Blocked Tracking Links Checker agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
The blocked-links skill is an agent skill that teaches an AI agent to review a site's HTML and JavaScript for links and resources pointing to domains that common adblocker filter lists block, such as analytics and tag-manager hosts. This guide explains what agent skills are, how to install this one, how to ask for it in plain language, and how to read its results. By the end you will know how to get a useful review of your third-party script setup.
Blocked Tracking Links Checkerthedaviddias/Front-End-Checklist · MIT Download the skill Quick start
- 1Download the ZIP. Get the blocked-links ZIP from the Front-End Checklist skill page.
- 2Unzip the folder. Extract it so the blocked-links folder contains SKILL.md and references/rule.md.
- 3Place the skill. Put the folder in ~/.claude/skills/ for personal use, or in a project's .claude/skills/ folder for one project.
- 4Or upload in the Claude apps. In the Claude apps, go to Settings, then Capabilities, then Skills, and upload the ZIP.
- 5Give the agent your code. Share the HTML, JavaScript or project files you want reviewed.
- 6Ask in plain language. Request a check for scripts or links that adblockers might block, or ask why analytics numbers look low.
- 7Verify the findings. Check each flagged resource yourself, for example by loading the page with an ad blocker enabled, before making changes.
What is an agent skill and what does this one do?
An agent skill is a folder of instructions that an AI agent can load when a task matches the skill's description. This skill is called blocked-links and its description says it applies when you review HTML source and JavaScript for links or resource URLs pointing to domains listed in common adblocker filter lists.
When a navigation link's URL matches a tracking domain pattern, an adblocker may block the request entirely. The user clicks and nothing happens. The skill asks the agent to find external scripts, image sources, iframe sources and anchor href values that point to known tracking domains, and to check whether they load with an ad blocker enabled.
- Flags external scripts, images, iframes and API calls on domains commonly listed in filter lists
- Explains why these resources may fail silently for visitors using blockers
- Suggests fixes such as self-hosting scripts, proxying requests through your own domain, or using direct destination URLs with UTM parameters
Install the blocked-links skill
Download the ZIP file for the skill from the Front-End Checklist page. Unzip it so that the blocked-links folder, which contains SKILL.md and references/rule.md, sits in one of the following locations.
For a personal setup, place it in your skills folder at ~/.claude/skills/. To limit it to one project, place it in that project's .claude/skills/ folder instead.
If you use the Claude apps, you can upload the ZIP instead. Go to Settings, then Capabilities, then Skills, and upload it there.
- Personal: ~/.claude/skills/
- Single project: .claude/skills/ inside the project folder
- Claude apps: Settings → Capabilities → Skills (upload the ZIP)
Trigger the skill with natural requests
You do not need a special command. The agent decides whether to use the skill based on the request. Describe what you want in plain language that mentions links, scripts, or adblockers.
Requests that match the skill's purpose include asking the agent to check a page for third-party scripts that adblockers might block, or to explain why analytics numbers look low. Give the agent the HTML or JavaScript to review, or point it at the files in your project.
- Check our HTML for scripts that ad blockers might block.
- Review this page's navigation links for tracking redirects that could break for users with blockers.
- Why do our Google Analytics numbers look lower than expected? Check the tag setup.
- Suggest how to load our analytics script from our own domain.
What to expect from a review
The skill's check step looks at script sources, image and iframe src URLs, and anchor href values. It names the tracking domains it finds, such as googletagmanager.com, hotjar.com, facebook.net and doubleclick.net, and considers whether those resources would load with uBlock Origin enabled. The agent cannot test a live browser unless your environment gives it that ability, so treat its findings as a list to verify.
The fix step recommends self-hosting critical external scripts on your own domain, forwarding requests to third-party analytics APIs through a reverse proxy or server-side route, and replacing tracking redirect URLs with direct destination URLs that have UTM parameters appended.
- Look for script, image, iframe and anchor URLs on known tracking domains
- Test whether resources load with an ad blocker enabled
- Replace tracking redirects in navigation links with direct URLs plus UTM parameters
Read the filter rules behind the findings
The skill's reference file explains that adblocker filter lists such as EasyList and uBlock Origin's static filters work at two levels: element hiding with CSS and network blocking of URLs. Domain-level rules stop the browser from loading any resource from a blocked domain, including scripts, images, fonts and navigation targets.
An example from the reference file shows rules of this form. When a request matches, the browser receives no response and the request silently fails.
||googletagmanager.com^
||hotjar.com^
||facebook.net^
||doubleclick.net^
||analytics.google.com^Know the limits and safety notes
This skill runs no scripts and makes no network requests, and it lists no required tools or dependencies. It is a review and explanation aid built from instructions, so its output depends on the code you give it and on the agent's reasoning.
The skill is aimed at making a site's own resources load. It is not meant for bypassing privacy protections or ad blockers for visitors. Self-hosting trackers can raise privacy and consent questions, so have legal review before you change how analytics or consent works. Sites with no third-party resources will have little for the checks to find.
- Runs scripts: no
- Uses network: no
- Requirements: none listed
- Not for bypassing blockers or privacy protections for users
- Self-hosting may raise privacy and consent questions that need legal review
What people use it for
- Auditing which analytics and tag-manager scripts load on a marketing site
- Finding navigation links that use tracking redirects and replacing them with direct URLs plus UTM parameters
- Investigating why reported analytics traffic is lower than server logs suggest
- Planning a move of critical third-party scripts to your own domain, with privacy review
Frequently asked questions
How do I install the blocked-links agent skill?
Download the ZIP from the Front-End Checklist page and unzip it so the blocked-links folder sits in ~/.claude/skills/ for personal use or in a project's .claude/skills/ folder. In the Claude apps, you can instead upload the ZIP under Settings, then Capabilities, then Skills.
Does the blocked-links skill require anything else to run?
The source lists no requirements. The skill runs no scripts and makes no network requests, so it works as a set of instructions for the agent.
Is the blocked-links skill free to use?
The skill is released under the MIT licence, as stated on its listing. Check the licence file included with the source for the full terms.
Can this skill help me unblock ads for my visitors?
No. The skill is aimed at making a site's own resources load and is not for bypassing privacy protections or ad blockers for users. Self-hosting trackers can raise privacy and consent questions, so get legal review first.
Why does my analytics look lower than expected?
Adblockers can block requests to analytics and tag-manager domains, so those visits are never recorded. Ask the agent to check your scripts and the adblocker filter lists it references, then verify the results in a browser with an ad blocker enabled.
How does this compare with other ways to check blocked resources?
The skill is an instruction set for an AI agent that reviews your code and explains fixes. It does not run tests itself, so it is a complement to testing in a browser with an ad blocker such as uBlock Origin, which the skill's check step names.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Use this skill if you are a front-end developer or marketer who wants an agent to review third-party scripts and navigation links for issues that adblockers cause. Pick something else if you need automated browser testing, or if your goal is to get around blockers for visitors, which this skill does not support.
Download the skill