AI Governance Reviewer Carl Ditzler
Intake-first AI governance, privacy, and vendor-risk reviews with a fixed scorecard template
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 5f4ce59
Fetched SKILL.md, README, output-template.md; spot-checked 4 referenced files (output-template.md, frameworks.md, scenarios-product.md, EU AI ACT.pdf) — all HTTP 200. Frontmatter parses with name+description; no security smells (no curl|sh, base64, or injection; includes explicit not-legal-advice disclaimer). Ran output-vs-baseline on an HR Azure-OpenAI use case: wrote a baseline review (4 ad-hoc risk bullets + recs) and a strict skill-followed turn-1 response. Concrete difference observed: the skill withholds any report and asks a scoped 4-question Core Use Case intake block, and its report template mandates a fixed 10-category two-table scorecard (Inherent/Residual Risk, Missing Evidence, Confidence, Owner) plus EU AI Act tier and prohibited-use screening — categories absent from the free-form baseline.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 5/5
What AI Governance Reviewer Carl Ditzler does
Runs a structured intake-first workflow to review internal AI use cases, AI product features, LLM workflows, or third-party AI vendors, then produces a governance review with a two-table scorecard, findings, owners, remediation checklist, and follow-up questions. Triggers when the user asks for an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an AI system. Ships bundled EU AI Act, GDPR, NIST AI RMF, and OECD reference sources.
How to install AI Governance Reviewer Carl Ditzler
git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git /tmp/ai-governance-reviewer-carl-ditzler-src
mkdir -p ~/.claude/skills
cp -R "/tmp/ai-governance-reviewer-carl-ditzler-src/skills/ai-governance-reviewer-carl-ditzler" ~/.claude/skills/ai-governance-reviewer-carl-ditzler
# No external deps. Skill bundles reference PDFs/markdown (EU AI Act, GDPR, NIST AI RMF 100-1, OECD, EU GPAI Code of Practice) plus scenario + output-template files it reads at runtime.
# Pure prompt/reference skill — Claude produces the review in-context; no CLI, API key, or MCP server required.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger AI Governance Reviewer Carl Ditzler
-
/ai-governance-reviewer-carl-ditzlerIntake-first AI governance, privacy, and vendor-risk reviews with a fixed scorecard template
It also activates on plain-language prompts like these:
-
Review this AI vendor for procurement risk -
Assess our LLM workflow for governance compliance -
Score this AI feature against governance frameworks
Frequently asked questions
- Is the AI Governance Reviewer Carl Ditzler skill free?
- Yes. The skill itself is free from lawve-ai/awesome-legal-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does AI Governance Reviewer Carl Ditzler work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md, README, output-template.md; spot-checked 4 referenced files (output-template.md, frameworks.md, scenarios-product.md, EU AI ACT.pdf) — all HTTP 200. Frontmatter parses with name+description; no security smells (no curl|sh, base64, or injection; includes explicit not-legal-advice disclaimer). Ran output-vs-baseline on an HR Azure-OpenAI use case: wrote a baseline review (4 ad-hoc risk bullets + recs) and a strict skill-followed turn-1 response. Concrete difference observed: the skill withholds any report and asks a scoped 4-question Core Use Case intake block, and its report template mandates a fixed 10-category two-table scorecard (Inherent/Residual Risk, Missing Evidence, Confidence, Owner) plus EU AI Act tier and prohibited-use screening — categories absent from the free-form baseline.
- What is the AI Governance Reviewer Carl Ditzler SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
- How do I install AI Governance Reviewer Carl Ditzler?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use AI Governance Reviewer Carl Ditzler with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.