How to use the Customize Regulatory Profile agent skill

What is an agent skill and what does this one do?

An agent skill is a folder containing a SKILL.md file that tells an agent how to handle a specific kind of task. This skill, named customize, is part of the claude-for-legal regulatory-legal plugin. Its job is narrow: it adjusts a single item in your saved regulatory practice profile.

Before it changes anything, the skill reads your current config, shows you the current values, explains which other tools in the plugin will be affected, and asks for confirmation. Only then does it write the update to the config file.

• Items it can adjust: watched regulators, the policy library index, the materiality threshold, the gap response process, feed configuration and matter workspace paths.
• Shared company details (name, industry, jurisdictions, stage, practice setting) are stored in company-profile.md and affect all 12 plugins, so the skill flags that when you change them.
• It does not run the setup interview. If no completed profile exists, it stops and asks you to run /regulatory-legal:cold-start-interview first.

Install the customize skill from the ZIP

Download the ZIP for the skill from this page and unzip it. The skill is a folder that must contain SKILL.md. Place the folder in one of these locations, depending on whether you want it available everywhere or only in one project.

You can also upload the skill through the Claude apps: open Settings, go to Capabilities, then Skills, and upload the skill there.

• For all your projects: unzip into ~/.claude/skills/
• For one project only: unzip into the project's .claude/skills/ folder
• Or in the Claude apps: Settings → Capabilities → Skills, then upload

Trigger the skill with natural requests

You can invoke the skill with its command, /regulatory-legal:customize, optionally followed by a section name or a description of the change. You can also just describe what you want in plain words. The skill's description lists phrases such as "change my [thing]", "add a regulator", "update my watchlist", "edit my threshold" and "customize".

If you are not sure which section to change, run the command with no argument. The skill will show the customizable map grouped by area, with a one-line summary of each current value, and then ask what you want to adjust.

• "Add the FCA to my watchlist as a leading regulator."
• "Edit my threshold so only high-impact changes reach the weekly digest."
• "Update my policy library path for the data retention policy."
• "Change my comment deadline tracker."

Walk through a change step by step

The skill makes one change at a time and does not re-ask the whole interview. For a typical change it reads the current value, asks for the new one, and explains what happens downstream. For example, adding a regulator means the next /reg-feed-watcher sweep will include it, and /policy-diff will accept inputs from that regulator's rulemaking feed.

Raising or tightening the materiality threshold shortens the weekly digest. Items below the new threshold drop out of the digest but remain searchable. The skill confirms before writing, then closes by telling you the next output will reflect the change.

• Read the current value shown by the skill.
• Give the new value in your own words.
• Read the downstream explanation and confirm.
• Check the closing message confirming the write.

Remove a regulator without deleting it

The skill will not delete a section. If you want to drop a regulator, it offers to mark that regulator [Monitor only] instead. According to the source, monitoring keeps the feed in the archive but removes it from the active digest, so nothing is lost if you change your mind.

• Monitor only keeps the feed in the archive.
• Monitor only removes the feed from the active digest.
• The skill will flag inconsistencies, such as a regulator in scope with no matching jurisdiction in your footprint.

Safety notes: scripts, network and guardrails

According to the skill's listing, it runs no scripts and uses no network access. It works by reading and writing config files on your machine. Because it edits the settings that control what gets flagged, treat each change deliberately.

The skill keeps several safeguards in place. Verify tags on cited regulations, source attribution on feed pulls and the review flag on gap triage are not to be removed. If you lower the materiality threshold to the point where the digest becomes noise, the skill warns you.

• Requires an existing completed setup that created the config files.
• Changing thresholds or watchlists carelessly can cause important regulatory changes to be missed.
• The output is a settings change, not legal advice.