privilege-log-review

First-pass privilege log review — make the obvious privilege calls and flag the hard ones for attorney review without making close calls. Use when the user says "review the privilege log", "priv log", "check privilege on these docs", or has a log to QA before production.

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 body is highly actionable and workflow-clear with strong validation gates appropriate to a consequential legal task, but it is a long monolithic file with some redundancy that limits conciseness and progressive disclosure. Splitting jurisdictional/citation detail into reference files and de-duplicating repeated load/first-pass statements would lift the weaker dimensions.

Suggestions

Split the jurisdictional in-house counsel section and the citation-coverage protocol into separate reference files (e.g. references/in-house-privilege.md, references/citation-check.md) and link to them from SKILL.md to improve progressive disclosure.

De-duplicate repeated instructions: the CLAUDE.md load appears both in the top numbered list and the "Load context" section, and the "first pass / attorney reviews every flag" point is restated several times — consolidate to one canonical statement.

Tighten verbose passages like the disclosed-document restrictions and the no-silent-supplement block to their load-bearing requirements so every token earns its place.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but carries redundancy — loading CLAUDE.md is stated at the top and again in "Load context", and the "first pass / attorney reviews every flag" point is restated several times — so it could be tightened rather than earning the lean level-3 anchor.	2 / 3
Actionability	Provides highly concrete, copy-ready guidance: a three-state classification rule, exact marker tags ([VERIFY], [UNCERTAIN], [CITE NEEDED]), verbatim refusal/report phrasings, and a full markdown output template — meeting the fully-executable anchor for an instruction-heavy skill.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 0 research → Step 1 format check → Step 2 entry-by-entry → Step 3 pattern flags) with explicit validation checkpoints and feedback loops (conflicts gate, no-silent-supplement stop-and-ask, citation coverage passes, attorney-must-review gate before service), matching the level-3 anchor.	3 / 3
Progressive Disclosure	Well-organized with clear headers, but it is a monolithic single SKILL.md (~230 lines) with no bundle reference files, and content like the jurisdictional in-house counsel detail or citation-coverage protocol is inline that could be split out; not level 1 because organization is good and references are clearly signaled, not level 3 because no one-level-deep reference files structure the content.	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: it states concrete actions, gives natural trigger phrases, answers both what and when, and carves out a distinctive niche. It uses third-person/infinitive voice as the guidelines require, with no verbosity or over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "make the obvious privilege calls", "flag the hard ones for attorney review", "without making close calls" — matching the multi-action anchor rather than the single-action level 2.	3 / 3
Completeness	Explicitly answers both what (first-pass review, make calls, flag hard ones) and when (an explicit "Use when..." clause with concrete triggers), which is the level-3 anchor; not level 2 because the when clause is present and explicit.	3 / 3
Trigger Term Quality	Quotes natural user phrasings ("review the privilege log", "priv log", "check privilege on these docs", "log to QA before production") giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (privilege log first-pass triage) with distinct, domain-specific triggers unlikely to fire for unrelated skills; not level 2 because the scope is unambiguously narrow.	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/privilege-log-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.