How to use the IP Profile Customizer agent skill

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

An agent skill is a folder of instructions, packaged with a SKILL.md file, that an AI agent loads when a task matches the skill's description. This skill is a guided editor for an IP-legal practice profile that the agent keeps in a local config file.

When you ask to change a setting, the agent reads the current profile, shows you the current value, asks for the new one, explains which other tools in the plugin will be affected, and then writes the change to the config. It edits configuration only and does not verify legal conclusions.

What you need before installing

The skill assumes you already work with the claude-for-legal ip-legal plugin and have finished its cold-start setup. If you have not, the skill stops and asks you to run the cold-start interview first.

The profile lives in local plugin config files under ~/.claude/plugins/config/claude-for-legal/. The skill runs no scripts and uses no network access.

• The claude-for-legal ip-legal plugin, with cold-start setup completed
• Local config files under ~/.claude/plugins/config/claude-for-legal/

Install the customize skill

Download the ZIP file for this skill from this page. Then install it using one of the two methods below.

For Claude Code, unzip the file into ~/.claude/skills/ for your personal use, or into a project's .claude/skills/ folder to share it with that project. In the Claude apps, open Settings, go to Capabilities, and upload the ZIP under Skills.

• Personal install: unzip into ~/.claude/skills/
• Project install: unzip into the project's .claude/skills/ folder
• Claude apps: Settings → Capabilities → Skills, then upload the ZIP

How to trigger the skill with natural requests

You can ask for a change in your own words. The skill is designed to respond to requests like 'change my risk posture', 'update my profile', 'edit my config' or 'customize'. You can also name a section directly, such as escalation contacts or OSS review rules.

The skill also accepts the slash form /ip-legal:customize, with an optional section name or a description of what you want to change.

• 'Change my risk posture to middle.'
• 'Update my escalation contacts.'
• 'Add class 25 to my trademark watch classes.'
• 'Customize my OSS review rules.'

Examples of changes and their effects

The skill explains downstream effects before it writes anything. These examples come from the skill's own guidance.

Adding a trademark watch class means /portfolio will include that class in watch reports, and /infringement-triage will route findings in that class accordingly. Moving enforcement posture from aggressive to middle means /cease-desist will offer cure-letter drafts first for ambiguous cases instead of going straight to a cease-and-desist. Adding a new ship-blocker OSS license means /oss-review will fail reviews that include it rather than warning.

Safety notes and guardrails

The skill never deletes a section. To remove an IP type from scope, it sets that type to [Not currently in scope] and explains what drops out. It also flags inconsistencies, such as trademark marked out of scope while a trademark watch service is still configured.

Review tags are protected. The [review] flag, source attribution tags and [verify] tags on cited authorities should not be removed, and clearance confidence on /clearance output should not be suppressed. Company-wide changes such as company name or jurisdictions are written to company-profile.md and affect all 12 plugins.

• Changes to company-wide fields affect all 12 plugins
• One change is handled at a time; the skill does not re-run the whole interview
• A wrong profile setting could change how other tools advise, so check the downstream explanation before confirming