legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legal_hold fields in _log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

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-hold workflow with strong sequencing and validation gates. Its main weaknesses are repeated boilerplate and a monolithic structure that keeps large templates inline instead of factoring them into reference files.

Suggestions

Deduplicate the non-lawyer 'find a licensed attorney' block: state it once and reference it from both --issue and --release to recover tokens.

Factor the ~50-line default hold-notice template and the status-report template into reference files under references/ and link to them one level deep, improving progressive_disclosure.

Collapse the opening 6-step routing list or the duplicated high-level summary now that each mode is fully detailed below, to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Most content is domain-specific and earns its place, but the 'find a licensed attorney...' boilerplate is repeated near-verbatim in both --issue and --release, and the opening routing list (steps 1-6) duplicates the detailed Modes section. Not score 3 due to this redundancy and the long inline template; not score 1 because it avoids generic concept explanations.	2 / 3
Actionability	Provides concrete file paths, _log.yaml field schemas, docx output names, copy-paste hold-notice and status-report templates with placeholders, and history.md entry formats — fully executable guidance rather than vague direction.	3 / 3
Workflow Clarity	Each mode is clearly sequenced with explicit validation checkpoints: the unbypassable conflicts gate, 'Confirm before writing', the send gate, SME VERIFY markers, and the non-lawyer gate. Validation is present for the consequential acts, so workflow_clarity is not capped at 2.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single ~230-line file with large inline templates (default hold notice, status report) that could be split into reference files, and there are no skill-internal one-level-deep references. Matches the 'content that should be separate is inline' anchor rather than the 'appropriately split' 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, third-person description that names concrete actions and artifacts and gives explicit natural-language triggers for all four modes. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions tied to concrete artifacts: 'Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legal_hold fields in _log.yaml, and calendars the next refresh.' This matches the 'lists multiple specific concrete actions' anchor and is more comprehensive than the score-2 example.	3 / 3
Completeness	Explicitly answers both 'what' (issue/refresh/release/report + .docx + _log.yaml fields + next refresh) and 'when' ('Use when the user says...'), matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Provides natural user phrasings covering all four modes: '"issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.' These are terms a user would naturally say, satisfying the 'good coverage of natural terms' anchor; not score 2 because common variations are not missing.	3 / 3
Distinctiveness Conflict Risk	A clear niche (legal holds) with mode-specific triggers unlikely to collide with other skills, matching the 'clear niche with distinct triggers' anchor; not score 2 because it is not merely 'somewhat specific'.	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: litigation-legal/skills/legal-hold/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.