aia-generation

Run an AI impact assessment — structured intake, risk analysis, regulatory classification per regime in scope, policy consistency diff, and recommendation with conditions. Uses the house-style structure learned from the seed impact assessment in `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`. Use when user says "impact assessment for", "assess this AI use case", "run an AIA", "generate an AIA", "we need to document this AI system", "AI risk assessment for X", or follows a conditional triage result.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with strong workflow sequencing and validation gates, but it is token-inefficient due to repeated full paths and conceptual prose, and it does not practice progressive disclosure — all material lives in one large inline file rather than being split across reference files.

Suggestions

Define the CLAUDE.md path once at the top and refer to it by a short alias thereafter, eliminating the dozens of full-path repetitions that inflate token cost.

Move the ~120-line default assessment template and the intake question banks into reference files under references/ (e.g. references/assessment-template.md, references/intake-questions.md) and link to them from the body, practicing one-level-deep progressive disclosure.

Trim the conceptual framing in the 'Purpose' and house-style sections to the minimum needed to distinguish an AIA from a PIA, relying on Claude's existing knowledge of impact-assessment concepts.

Dimension	Reasoning	Score
Conciseness	Mostly specific and actionable, but verbose: the full path ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md is repeated dozens of times instead of being defined once and abbreviated, and conceptual framing prose ('An AI impact assessment is a documented decision, not a form...') could be tightened.	2 / 3
Actionability	Provides copy-paste-ready templates (the full default assessment markdown), exact user-facing phrasings in blockquotes, concrete intake question lists, and bad/better risk tables — fully executable guidance.	3 / 3
Workflow Clarity	Steps 0–4 are clearly sequenced with explicit validation gates: the Step 0 need-check, Step 3 footprint-freshness pre-check, the no-silent-supplement stop condition, and the certification gate ('Do not proceed past this gate without an explicit yes').	3 / 3
Progressive Disclosure	Well organized into clear sections, but the ~400-line body is monolithic with no bundle reference files — the ~120-line default assessment template and intake question banks are inline content that could be split into separate reference files. No references/, scripts/, or assets/ bundle files exist.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all dimensions: concrete actions, natural trigger phrasings, explicit what-and-when guidance, and a distinctive niche. It uses third-person voice and avoids fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'structured intake, risk analysis, regulatory classification per regime in scope, policy consistency diff, and recommendation with conditions' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Run an AI impact assessment — ...') and when (an explicit 'Use when user says ...' clause with multiple triggers).	3 / 3
Trigger Term Quality	Provides natural phrasings a user would actually say — 'run an AIA', 'generate an AIA', 'AI risk assessment for X', 'we need to document this AI system' — with good variation coverage.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (AI impact assessments) with distinct, specialized triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-for-legal
Path: ai-governance-legal/skills/aia-generation/SKILL.md
Commit: 4a6c651

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.