Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

AI Governance Reviewer Skill · lawve-ai | DecimalAI

legalby lawve-ai

AI Governance Reviewer Skill

lawve-ai/ai-governance-reviewer-carl-ditzler

Source lawve-ai/awesome-legal-skills ↗License NOASSERTION

Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an internal AI use case, an AI product feature, an LLM workflow, or a third-party AI vendor. The skill asks intake and clarifying questions first when facts or evidence are missing, identifies required documentation and missing evidence, maps the use case to AI governance frameworks and applicable legal domains, and produces a preliminary or final governance review with sco

SkillScore82Maintained

Automatic

Legal & Contracts pack

Last verified 8/16/2026

What it changes

Passed 18 of 22 test cases with the skill, and 11 of 22 without it.

Without skill50%

With skill82%

Checks it passed that the model alone missed

The response classifies the system as a Hybrid or Multiple scenario deployment.
The response contains a legal disclaimer stating that the guidance is not legal advice.
The response asks between 3 and 5 direct core use case intake questions on the first turn.

and 10 more in the full report

10 fixed8 passed either way1 still failing3 broke

Pass-rate lift: +32 pp
Tokens: +128%
Agent turns: 0%
Response time: -38%

Model gemini-3.6-flashMeasured 8/16/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/lawve-ai-ai-governance-reviewer-carl-ditzler/SKILL.md https://app.decimal.ai/s/lawve-ai-ai-governance-reviewer-carl-ditzler/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add lawve-ai-ai-governance-reviewer-carl-ditzler, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/lawve-ai-ai-governance-reviewer-carl-ditzler/ and pins it in .decimal/skills.lock

decimalai skills add lawve-ai-ai-governance-reviewer-carl-ditzler

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/lawve-ai-ai-governance-reviewer-carl-ditzler/SKILL.md https://app.decimal.ai/s/lawve-ai-ai-governance-reviewer-carl-ditzler/SKILL.md

Raw file: /s/lawve-ai-ai-governance-reviewer-carl-ditzler/SKILL.md ↗ · machine-readable summary at /s/lawve-ai-ai-governance-reviewer-carl-ditzler.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 10

Prompt

We are considering rolling out a third-party AI coding assistant tool to our 200 software engineers to accelerate internal development workflows. Before we sign the enterprise agreement, I need an AI governance evaluation covering risk classification, data privacy considerations, vendor risk, and compliance obligations. Please analyze this deployment and furnish a complete risk assessment breakdown.

What was checked, without and with the skill
Checked	Without skill	With skill
The response asks intake questions regarding the use case, data types, or controls before producing a complete risk assessment.	Missed	Passed
The response includes a legal disclaimer noting that the review is a draft and not formal legal representation.	Missed	Passed

case-02 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md273 lines8 files

AI Governance Reviewer Skill

Use this skill for draft AI governance reviews involving:

Internal AI use by employees or contractors
AI-enabled product features or AI system deployments
Third-party AI vendors, subprocessors, or embedded AI services

This skill supports governance, privacy, security, procurement, and legal preparation. It does not provide legal advice.

LEGAL DISCLAIMER Always include this disclaimer in the response:

This review assists with AI governance processes and does not replace a formal AI Governance, legal review or professional legal representation. This output is a draft and may contain errors or omissions. Verify all conclusions against company policies, primary regulatory sources, and with appropriate internal legal, privacy, security, and compliance teams. This is not legal advice.

Load These References

Read references/frameworks.md when making regulatory, governance, or source-citation claims.
Read references/responsible-ai-practice.md for operational responsible-AI best practices, escalation triggers, confidence discipline, and governance-program design guidance.
For legal frameworks, use the bundled files described in references/frameworks.md rather than relying on external URLs.
For ISO/IEC 23894:2023, do not use bundled local files. Use the ISO and iTeh URLs listed in references/frameworks.md.
Read exactly one or more scenario files based on the use case:
- references/scenarios-internal.md
- references/scenarios-product.md
- references/scenarios-vendor.md
Read references/output-template.md before drafting the scorecard or remediation output.
Read references/example-outputs.md when you need a model for an intake-only response, a preliminary review, or a final review.

Source And Document Priority

Use sources in this order:

User-provided facts, documents, contracts, screenshots, policies, technical materials, uploads, and answers
Bundled references/official/ legal source files
Bundled references/working/ legal source files
Bundled governance guidance in references/frameworks.md, references/responsible-ai-practice.md, and the scenario files
General best-practice reasoning only when the above do not fully answer the point

Do not let a lower-priority source override a higher-priority one.

Workflow

Conversation Control Rules

Track record

Benchmark

18 / 22

test cases passed, vs 11 / 22 without

Adoption

Users: 4
Times used: 176

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

lawve-ai / awesome-legal-skills

skills/ai-governance-reviewer-carl-ditzler/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 7 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

AI Governance Reviewer Skill

Load These References

Source And Document Priority

Workflow

Conversation Control Rules

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills