Hire an AI feature specification and legal-risk reviewer

Everything it can hand back

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

• A spec with goals, non-goals, success measures and acceptance checks
• A legal risk memo rated by area, with what to fix and who should sign off
• A go, wait or no-go call with the reason, based on the memo and your plan

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

• Long lists of generic issues with no evidence they apply.
• Testing or scanning systems without permission.
• Presenting a legal opinion as final.

What a good result looks like

An example, not your task: You are about to build a feature that uses personal data, new vendors, AI or public claims.

• Step 1: Feature spec. Problem, users, goals, non-goals, requirements with acceptance checks, success measures and open questions.
• Step 2: Legal risk memo. What is launching, AI and data flags, risk rated by area, what to fix and who signs off.
• Step 3: Launch call. Your plan quoted, six common faults, three readiness checks and a go, wait or no-go with the reason.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Sun Tzu would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Write the spec. Pins down the feature, the user problem and the success measures, then lists requirements with acceptance checks and open questions.
• Check the legal risks. Reads the spec to see what is launching and who uses it. Flags AI use, new data, vendors and claims. Rates each legal area and lists what to fix first.
• Pause and fix. You fix the flagged items, or ask a lawyer about the high-rated ones, then update your launch plan to match.
• Make the launch call. Quotes your plan and tests it against six common faults and three readiness checks. Asks whether pride or anger is driving it. Gives a go, wait or no-go.

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 spec-a-feature-and-make-a-legal-checked-launch-call 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/spec-a-feature-and-make-a-legal-checked-launch-call/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 feature idea, who it is for and the problem it solves
• Any limits you know, such as timing, rules and dependencies
• Your launch date and where you will launch
• Your launch plan, after you have fixed what the memo flags

Tools and access

• Any good chat AI: Checking a plan against a fixed list of faults is text work any strong chat AI does well with this skill.

Functions and deliverables

• Feature specification and legal-risk reviewer: Share the feature idea, data use and launch plan. Get a specification, first-pass legal questions and a proceed-or-wait review.
  • A spec with goals, non-goals, success measures and acceptance checks
  • A legal risk memo rated by area, with what to fix and who should sign off
  • A go, wait or no-go call with the reason, based on the memo and your plan
• Feature spec writer: Describe a feature idea. Get a spec with goals, non-goals, success measures and acceptance checks.
  • A full spec document
  • Goals and non-goals
  • Acceptance criteria
  • Success metrics
  • A list of open questions
  Source: Anthropic.
• Launch legal reviewer: Check a product plan against each legal area before you ship. Get a launch legal review memo plus a safe note for your ticket. Not legal advice.
  • A category by category review memo
  • Each finding rated for risk
  • Flags on new or unclear issues
  • A summary for the ticket
  Source: Anthropic.
• Go or no-go launch checker: Check a launch plan against six faults and three readiness checks. Get a go, wait or no verdict and a fix list before you spend.
  • Each of six faults marked present, absent or missing, with a reason from your plan
  • Three halfway checks answered yes, no or missing
  • One verdict, go, wait or no, with the single reason that decided it
  • A fix list for each fault found, and what would turn a wait into a go
• 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
• Sun Tzu: Plan a competitive move using The Art of War. Compare both sides, check costs and ask whether a fight can be avoided.
  • Your problem worked on the way Sun Tzu would: their questions, their method, their push-back
  • The answer or the work, in Sun Tzu's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You are about to build a feature that uses personal data, new vendors, AI or public claims.
• A launch date is set and nobody has read the spec for risk.
• You need a clear go, wait or no-go before telling customers.

Limits to check before starting

• Your feature uses no personal data, claims, new vendors or AI: use the Feature spec writer on its own.
• You need legal advice or a signed opinion: ask a lawyer. This memo is a first check only.
• The feature is already live and you want to test the money side: use the Bad-year break-even tester.

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.

• Download the handoff pack. It's a zip with HANDOFF.md and three skill files, in the order they run: Feature spec writer, Launch legal reviewer and Go or no-go launch checker.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Describe the feature and answer the questions it asks about users and data.
• Stop after step 2. Fix the flagged items or take the high ones to a lawyer.
• Update your launch plan, then run step 3 for the call. A go call is not legal sign-off. A lawyer still clears every high-rated item before launch.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/spec-a-feature-and-make-a-legal-checked-launch-call 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.