closing-checklist

What's blocking close — maintain the closing checklist with status, critical path, and days to close. Self-updating: ingests new items from diligence findings and schedule builds, tracks status, surfaces what's blocking. Use when user says "closing checklist", "what's left to close", "checklist status", "add to the checklist", or on a scheduled status pull.

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 well-structured, highly actionable body with clear mode sequencing and explicit validation checkpoints, including a strong consequential-action gate. Its main weakness is monolithic inline content with no progressive disclosure into separate reference files.

Suggestions

Move the closing-checklist YAML structure and the Mode 4 status-report template into separate reference files (e.g. references/checklist-schema.md and references/status-report-template.md) linked from SKILL.md, so the overview stays lean and detail is one level deep.

Tighten the consequential-action gate brief and consolidate repeated CLAUDE.md cross-references to a single pointer, reducing token weight without losing the gate's protective intent.

Add an explicit 'See <reference>' signal wherever a long inline block currently lives, so the reader knows the detail has been progressively disclosed.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes domain competence (it directs research rather than explaining HSR/CFIUS/MAC basics), but the ~190-line body has density that could be tightened — e.g. the lengthy gate brief and repeated cross-references to CLAUDE.md — so not every token earns its place.	2 / 3
Actionability	Provides concrete executable guidance throughout: exact file paths, a fully populated example YAML schema, the handoff schema, a sample status-update command, and a copy-paste-ready Mode 4 markdown report template with table structure.	3 / 3
Workflow Clarity	Opens with an explicit numbered sequence and branches by mode; the consequential-action gate is a clear validate/yes-no checkpoint with a feedback loop, and Mode 2's de-dupe rule is a concrete validation step for the self-updating ingestion.	3 / 3
Progressive Disclosure	Well-organized with clear section headers, but monolithic — the YAML schema and the Mode 4 template are inline content that could be split into one-level-deep reference files, and no bundle reference files exist or are signaled.	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 names concrete capabilities, gives natural trigger phrasings, and explicitly covers both what the skill does and when to invoke it. It occupies a clear niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "maintain the closing checklist with status, critical path, and days to close", "ingests new items from diligence findings and schedule builds, tracks status, surfaces what's blocking" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (maintain/ingest/track/surface the closing checklist) and when via a clear "Use when..." clause with concrete triggers, satisfying the explicit-trigger requirement for a top score.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would actually say ("closing checklist", "what's left to close", "checklist status", "add to the checklist") plus a scheduled-pull trigger; good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche (deal closing checklist) with distinct transaction-specific triggers unlikely to fire for unrelated skills; it would not naturally overlap with generic checklist 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: corporate-legal/skills/closing-checklist/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.