Hire an AI policy change reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A check that the rule is in force, with unverified dates marked
• Each policy touched, with gaps ranked high, medium or low and the reason
• A small marked-up draft for each real gap, re-checked against the rule
• Open gaps that need a person, and the owner for each draft

How it does the job well

• Name the asset, the threat and the impact before recommending controls.
• Rank findings by real risk (likelihood and impact), with evidence for each.
• Prefer fixes that remove a problem over warnings that rely on people.
• Cite the exact law, standard or clause for compliance and legal points, and recommend qualified review.

Mistakes it avoids

• Treating a draft as approved, or a gap as closed.
• Rewriting a whole policy for one changed requirement. Make the smallest edit.
• Looping more than three rounds on one gap.
• Filling in a missing rule from memory.
• Long lists of generic issues with no evidence they apply.
• Testing or scanning systems without permission.

What a good result looks like

An example, not your task: A law, platform rule or standard that applies to you has changed.

• THE RULE. What changed, where it applies, when it starts, and whether it is confirmed in force.
• POLICIES TOUCHED. Each policy with its gaps ranked high, medium or low, and the reason.
• DRAFTS TO REVIEW. Each redraft file, the edit in one line, the rounds it took and any high gap left.
• OPEN GAPS. Gaps still open after three rounds, or that need a decision from a person.
• DEADLINES. The dates that matter, marked verified or unverified.
• WHO DECIDES. The policy owner for each draft.

How the work is checked

• Rule status is stated, and unverified dates are marked.
• Every high gap has a draft or is listed as open with a reason.
• Every redraft was re-checked against the rule, and the number of rounds is stated.
• No redraft is marked applied. Every gap is still open in the log.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Check the rule is in force. Asks for the source and date. If it cannot be confirmed, every date is marked unverified.
• Find the gaps. Compares each new requirement with your policies and lists which policy needs a change.
• Choose the extra checks. An AI law adds an AI gap check. Personal data adds a privacy policy check. Store and handbook policies get their own check on the drafts.
• Rank the gaps. High if the policy says the opposite of the rule or your practice breaks it. Medium if it is silent. Low if the wording is unclear.
• Draft and check in a loop. Writes the smallest edit for each real gap, checks it again against the rule, and sends it back if a high gap is open or it clashes. At most three rounds.
• Log and hand back. Records the rule, gaps and drafts. Every draft stays a draft, with an owner, until a person applies and approves it.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id rule-change-policy-keeper only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/rule-change-policy-keeper/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The rule change, as its text or a summary with its source, where it applies and when it starts
• The approved text of the policies that might be touched
• How you really handle data, orders or staff now (optional, best)
• Who owns each policy (optional)

Helpful context (optional)

• The rule text with its source and date
• A short note of how you handle customer data and orders today

Tools and access

• Claude Code: It can keep the policies folder and rule log, and read each policy file.
• Your policy pages or handbook: Paste the approved text here, so the drafts are built on the right version.

Functions and deliverables

• Policy change reviewer: Compare a changed rule with your policies. Get small redrafts, recheck results and open gaps for qualified review.
  • A check that the rule is in force, with unverified dates marked
  • Each policy touched, with gaps ranked high, medium or low and the reason
  • A small marked-up draft for each real gap, re-checked against the rule
  • Open gaps that need a person, and the owner for each draft
• Policy change impact reviewer: Find which of your policies a changed rule touches. Paste the rule and your policy list to get a gap list of what to edit. First check only.
  • A list of requirements pulled from the rule
  • A gap analysis for each policy
  • Which policies need editing
  • A clear warning if scope was limited
  Source: Anthropic.
• AI law gap checker: Share the AI rule and company practices. Check scope, compare requirements and plan gaps for legal review with owners and due dates.
  • A yes or no on whether the rule applies to you
  • The requirements pulled out of the rule
  • Each gap sorted into must do, should do, already met or accepted
  • A dated fix plan with owners and deadlines, saved as a file
  Source: Anthropic.
• Privacy policy drift checker: Check if your privacy policy still matches what your team does. Paste your policy and a new practice to get gaps and fix wording. Not legal advice.
  • Covered, missing or conflicting verdict
  • Quote of the policy at issue
  • Suggested replacement wording
  • Timing advice
  Source: Anthropic.
• Policy redraft proposer: Turn a policy gap, approved text, and rule into proposed edits with comments for review.
  • Marked-up redraft with small edits
  • Comments explaining each change
  • Redraft memo in a new dated file
  • List of facts still to verify
  Source: Anthropic.
• Shopify store policy checker: Check Shopify store rules for gaps and clashing claims, then get fixes you can paste.
  • A score out of 100
  • A top-fixes list with quotes
  • A list of contradictions
  • Rewritten wording to paste in
  • Notes on region rules
  Source: Pro Skill Packs.
• Handbook change and cross-reference checker: Share a handbook change and current policies. Compare wording, find related sections and review effects on state supplements and promised benefits.
  • A side by side of old and new wording
  • A list of cross-references that may break
  • A state by state impact check
  • A flag if the change cuts a promised benefit
  Source: Anthropic.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• A law, platform rule or standard that applies to you has changed.
• You are about to start a new use of customer data and want to know if your policy covers it.
• You have written policies and no one has time to check them against every change.

Limits to check before starting

• Your policies are not written yet. Start by drafting them with a lawyer, then come back.
• The rule plainly does not apply to you. Skip it and save the time.
• You need a ruling on a fine, a licence or a claim. Ask a lawyer to read the rule itself.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then give it the rule and your policies.
• Paste the rule text, not only a news summary. Say where you operate.
• Read each draft with the policy owner. Nothing is applied by the agent.
• Take the drafts and the reminder to a lawyer before you publish. Mark each gap closed yourself once it is applied and approved.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/rule-change-policy-keeper for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.