Skip to content
Get packs

Feature Risk Assessment

Produces a structured deep-dive on one risky feature: scenarios, likelihood, impact, mitigations, options.

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

What it does

When a product launch review turns up a risk that needs more than a single checklist line, this skill guides the agent to write a standalone decision document. It walks through what could go wrong, how likely and how severe each risk is, what already mitigates it, which regulators might care, and compares a few realistic options with a recommendation. It is written for in-house legal teams in a product-legal context, and it is meant to be used only for the small share of launches that need this level of scrutiny.

Great for

  • In-house legal teams reviewing a novel or high-scrutiny product feature
  • Product counsel preparing a decision document for a general counsel or leadership
  • Teams that have already been flagged by a launch review for an AI, children's, biometric or health feature

Skip it if

  • Routine launches that a standard launch review already covers, since the skill itself says most launches do not need it
  • Anyone seeking a verified legal opinion: the skill says its citations are AI-generated and must be checked against primary sources before use
  • Users outside a legal function who expect a finished compliance sign-off

Try asking

  • “Deep dive on this risk: our new AI recommendation feature may surface sensitive interests”
  • “Risk assessment for our children's onboarding flow”
  • “What could go wrong with using biometric login in the mobile app?”
Step-by-step guide: how to use Feature Risk AssessmentInstall, 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.

    feature-risk-assessment.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip feature-risk-assessment.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip feature-risk-assessment.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

  • Populate the product-legal CLAUDE.md profile (risk calibration, outputs header, launch review location) first, so the assessment is calibrated to your company rather than generic.
  • Treat every case, statute and enforcement action in the output as unverified until checked against a primary source.
  • Run the companion AI governance or privacy skills mentioned in the handoffs section so overlapping risk content is flagged rather than duplicated.

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.