launch-review

Full launch review against your framework and risk calibration. Use when the user says "review this launch", "legal review for [feature]", "can we ship this", "what are the legal issues with [product]", or references a launch tracker ticket or PRD that needs a category-by-category review memo.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 highly actionable, well-sequenced legal review workflow with strong validation gates, but it is verbose and inlines large reference tables that belong in the existing (currently orphaned) bundle file. Tightening the repeated config paths and externalizing the framework/sector tables would lift both conciseness and progressive disclosure.

Suggestions

Link the existing references/seven-category-framework.md from the body and move the 8-category framework table and sector-hints matrix into it (or a second reference file) so the inline body stays an overview.

Replace the repeatedly spelled-out ~/.claude/plugins/config/claude-for-legal/product-legal/CLAUDE.md path with a short alias defined once (e.g. "the practice CLAUDE.md") to cut token cost and repetition.

Condense the longer admonition blocks (e.g. the no-silent-supplement and source-tiering notes) into tight bullets while preserving the gating rules.

Dimension	Reasoning	Score
Conciseness	The body is long (~260 lines) with the full config path repeated verbatim many times and large inline tables (the 8-category framework and the sector-hints matrix) that could be tightened or externalized. Not a 1 because it does not explain basic concepts Claude already knows — it is dense domain-specific workflow guidance; not a 3 because of the repeated paths and verbosity in several admonition blocks.	2 / 3
Actionability	Provides concrete executable guidance: exact memo output templates with placeholders, specific skill invocations (e.g. "/ai-governance-legal:use-case-triage [feature]"), and a copy-ready redacted ticket-comment block. Not a 2 because the instructions are complete and copy-paste ready rather than pseudocode or abstract direction.	3 / 3
Workflow Clarity	A clearly sequenced six-step workflow with explicit validation gates ("Stop if placeholders", "Auto-skip honestly", the non-lawyer clearance gate before a "Clear to ship" call) and feedback loops. Not a 2 because checkpoints are explicit and error-recovery is addressed; this is a review (not a destructive/batch) operation so the destructive-cap guideline does not apply.	3 / 3
Progressive Disclosure	A bundle file references/seven-category-framework.md exists but is never linked from the body, while the 8-category framework and the sector-hints tables are inlined as large reference blocks that should live in separate files. Not a 1 because sections are well-organized and one-level-deep; not a 3 because the orphaned reference and inlined reference material mean content that should be split is inline.	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, third-person description that pairs concrete deliverables with explicit, naturally-worded triggers and a clearly bounded launch-review niche. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Full launch review against your framework and risk calibration" and a "category-by-category review memo" — rather than vague language. Not below 3 because it lists several specific deliverables; not a 2 because it goes beyond naming just the domain.	3 / 3
Completeness	Explicitly answers both what (launch review against framework and risk calibration producing a category-by-category memo) and when ("Use when the user says..."). Not a 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Quotes exact phrases users would naturally say ("review this launch", "can we ship this", "what are the legal issues with [product]") plus PRD/tracker-ticket references. Not a 2 because it covers common natural variations directly rather than just naming the file type.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear product-legal launch-review niche with triggers tied to launch/ship decisions and tracker tickets, unlikely to fire for unrelated skills. Not a 2 because the triggers are specific to launch review rather than generic legal work.	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: product-legal/skills/launch-review/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.