Skip to content
Get packs

Customize AI Governance Profile

Lets the agent adjust one part of your AI governance practice profile without re-running setup

Source Download skill
Repository
anthropics/claude-for-legal
Stars
9,870
Licence
Apache-2.0
Files
1 file

What it does

This skill lets you change one setting in an existing AI governance profile, such as risk posture, escalation contacts, use-case registry entries, vendor AI positions, or workspace paths, without repeating the full setup interview or editing config files by hand. The agent reads your saved profile, shows you a grouped map of current values, asks what to change, explains what the change affects in other skills, and then writes the update. It also refuses to silently delete settings and warns you when a change would conflict with other settings or switch off a safety guardrail.

Great for

  • Legal or governance teams that already completed the cold-start setup and need to tweak one setting
  • Users of the claude-for-legal AI governance plugin who want to update escalation contacts or risk posture
  • People who want guided edits to a config file instead of hand-editing YAML or Markdown

Skip it if

  • Users who have not yet run the setup interview; the skill stops and tells them to run it first because it only adjusts an existing profile
  • Anyone wanting legal advice from this file alone; it only edits configuration and does not assess any AI system
  • Users trying to disable review flags or verification tags for legal judgment; the skill warns these safeguards are load-bearing and should not be removed

Try asking

  • “/ai-governance-legal:customize change my risk posture to conservative”
  • “/ai-governance-legal:customize add a new escalation contact for the GC office”
  • “update my profile: add an approved entry to the use case registry for our support chatbot”
  • “customize my impact assessment house style to use a different section order”
Step-by-step guide: how to use Customize AI Governance ProfileInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    customize.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip customize.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip customize.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the section you want to change (for example, risk posture or escalation chain) to skip the menu and get to the change faster
  • Changes to company name, industry, jurisdictions, or stage affect all 12 plugins, so review the downstream note carefully before confirming
  • Existing assessments are not rewritten after a change; re-run them if you want the new posture reflected

What's inside

  • SKILL.md

Redistributed unmodified from anthropics/claude-for-legal under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.