policy-monitor

Keep the privacy policy current with practice. Two modes: weekly sweep of saved PIAs, DPA reviews, and triage results to find policy drift; or direct query for a proposed new practice. Use when the user asks "does our policy cover this", "we want to start doing X — does the policy need updating", "run the policy monitor", "policy sweep", or wants to find where the privacy policy no longer matches what the team actually does.

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 with clear, sequenced workflows and concrete output templates for an instruction-only legal skill. Its main weaknesses are conciseness redundancy and a single large file that could offload some reference material into bundle files for better progressive disclosure.

Suggestions

Trim the redundant opening summary block (lines 13-33) and the conceptual Purpose restatement, since the frontmatter and the Mode sections already cover this — every token should earn its place.

Move the large sectoral-notices table and/or the full sweep and direct-query output templates into separate reference files (e.g., references/sectoral-notices.md, references/output-templates.md) and link to them one level deep, improving progressive disclosure and shrinking the SKILL.md overview.

If a bundle directory is intended to exist, add it; otherwise confirm the single-file design is deliberate so reviewers can score progressive_disclosure against the actual bundle structure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific, but the ~350-line body carries redundancy — the opening summary block repeats the frontmatter modes, and the Purpose section restates drift conceptually — so it could be tightened rather than being fully lean.	2 / 3
Actionability	Although it is instruction-only with no executable code (appropriate for a legal-policy workflow), the guidance is highly concrete: exact config paths to read, per-output-type extraction lists, full markdown output templates, and a structured diff table.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit checkpoints — empty-folder handling, placeholder detection, REQUIRED vs ADVISABLE classification with examples, and an ask-user-if-ambiguous feedback loop before proceeding.	3 / 3
Progressive Disclosure	No bundle files exist and the file is monolithic at ~350 lines; while it is well-organized with clear section headers, large reference blocks such as the sectoral-notices table and full output templates are inline where they could be split into separate files.	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 across both modes, gives explicit natural-language triggers, and answers both 'what' and 'when' clearly. No voice or over-claim issues are present.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — 'weekly sweep of saved PIAs, DPA reviews, and triage results to find policy drift' and 'direct query for a proposed new practice' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It explicitly answers both what (keep the privacy policy current with practice; two modes) and when, via an explicit 'Use when...' clause with concrete triggers, matching the top anchor exactly.	3 / 3
Trigger Term Quality	It includes natural phrases users would say — 'does our policy cover this', 'we want to start doing X — does the policy need updating', 'run the policy monitor', 'policy sweep' — giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche — privacy policy drift monitoring — is specific and the triggers are distinctive enough that it is unlikely to fire for unrelated 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: privacy-legal/skills/policy-monitor/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.