Skip to content
Get packs

AI Impact Assessment Generator

Runs a structured AI impact assessment with regulatory classification, policy diff, and conditions

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

What it does

When installed, the agent walks a user through a conversational intake about an AI system (what it does, who it affects, what oversight exists), then classifies it against the AI regulations in the company's configured regulatory footprint and checks it against the company's AI policy. The output is a written assessment in the team's house format, with a list of conditions and flags for related reviews such as a privacy impact assessment or vendor review. The skill is a legal-team workflow tool and relies on the practice's configured settings and research tools, so the lawyer still makes the final decision.

Great for

  • In-house legal or governance teams documenting a new AI use case such as hiring screening or customer-facing decisions
  • Compliance staff who need a consistent, citation-tagged assessment format
  • Lawyers who want a first draft that they then verify against primary sources

Skip it if

  • Final legal sign-off: the skill's citations are partly from model knowledge and are tagged for verification, so a qualified lawyer must check them (risk of relying on outdated or wrong law)
  • Organisations without a configured practice CLAUDE.md or regulatory footprint: the skill depends on those files and will not produce a jurisdiction-accurate result without them
  • Deployments outside the configured jurisdictions or choice-of-law questions: the skill itself warns the analysis may not apply

Try asking

  • “Run an AI impact assessment for our AI résumé screening tool”
  • “Assess this AI use case for customer credit pricing and tell me the risk track”
  • “We need to document this AI system for our governance file”
  • “Generate an AIA from this triage result”
Step-by-step guide: how to use AI Impact Assessment GeneratorInstall, 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.

    aia-generation.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip aia-generation.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 house style and regulatory footprint in the practice CLAUDE.md before running, otherwise the output will not match your team's format or jurisdictions.
  • Check every citation tagged [verify] or [verify-pinpoint] against the official source before relying on it.
  • Answer the intake questions fully about who is affected and what human oversight exists; these drive the risk track and conditions.

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.