use-case-triage

Classify a proposed AI use case against your registry — approved, conditional, or not approved — and produce required conditions and next steps. Flags cross-plugin handoffs to privacy or product counsel. Use when user says "triage this use case", "can we use AI for X", "is this approved", "what do we need to do to use AI for X".

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.

A thorough, highly actionable legal-triage workflow with clear sequencing and validation gates, but it is token-heavy: the authoritative-CLAUDE.md path is repeated ~10 times and the single 319-line file does not progressively disclose detail into reference files. Tightening the repeated path and splitting the stable reference material would lift both conciseness and progressive disclosure.

Suggestions

Define the governance CLAUDE.md path once (e.g., 'the plugin's CLAUDE.md at ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md, referred to below as the playbook') and reuse the short alias to remove ~9 redundant full-path repetitions.

Move the stable source-attribution tiering rules and the APPROVED/NOT APPROVED gate scripts into a referenced file (e.g., GATES.md / ATTRIBUTION.md) so SKILL.md stays a lean overview with one-level-deep links.

Trim or factor the long placeholder-bounce and provisional-mode blockquotes into a short inline summary plus a pointer, keeping only what the model needs at decision time inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-appropriate, but the full path "~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md" is repeated ~10 times verbatim instead of being aliased once, and several long blockquote scripts (placeholder bounce, gate prompts) could be tightened — fitting the 'mostly efficient but could be tightened' anchor rather than level 3.	2 / 3
Actionability	Provides copy-paste-ready output templates — the triage output header, the conditions table, the APPROVED/NOT APPROVED gate scripts, the batch summary table — giving fully concrete, executable guidance; per the code-vs-instruction scoring note, absence of code in this instruction-only skill is not penalized because the guidance is highly actionable.	3 / 3
Workflow Clarity	Steps 1–6 are explicitly sequenced with validation checkpoints: confirm registry populated (else stop), red-line check before classifying, and explicit yes-gates before issuing APPROVED or NOT APPROVED classifications, plus feedback loops for error recovery (PLACEHOLDER bounce, retroactive-triage drift handling).	3 / 3
Progressive Disclosure	Well-sectioned but monolithic — ~319 lines all inline in SKILL.md with no external reference files, and the under-50-line simple-skill exception does not apply; content like the source-attribution tiering and the detailed gate scripts could be split into referenced files, fitting the 'content that should be separate is inline' anchor.	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.

A strong description: it states concrete capabilities, gives explicit natural-language triggers for when to use it, and carves out a distinctive legal-governance niche. The only nit is the second-person "your registry" phrasing, but it does not undermine the predominantly third-person imperative voice.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Classify a proposed AI use case against your registry — approved, conditional, or not approved", "produce required conditions and next steps", "Flags cross-plugin handoffs to privacy or product counsel" — matching the multiple-specific-actions anchor; the second-person possessive "your registry" is a modifier, not a "you can use this" instruction, so no specificity deduction.	3 / 3
Completeness	Clearly answers both what (classify, produce conditions/next steps, flag handoffs) and when (an explicit "Use when..." trigger clause), satisfying the both-what-AND-when anchor.	3 / 3
Trigger Term Quality	The "Use when user says" clause lists four natural phrases a user would actually say — "triage this use case", "can we use AI for X", "is this approved", "what do we need to do to use AI for X" — giving strong coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — AI governance/legal use-case triage against a registry — with distinct, domain-specific triggers unlikely to fire for other 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/use-case-triage/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.