dpa-review

Review a Data Processing Agreement against your DPA playbook — auto-detects whether you're processor or controller and applies the right half of the playbook. Use when the user says "review this DPA", "check this data processing addendum", "customer sent their DPA", "is this DPA okay", or attaches a DPA.

Quality

83%

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 richly actionable legal-review skill with a clear sequenced workflow and strong validation gates. It loses points on conciseness (editorial prose) and progressive disclosure (monolithic single file with no reference bundle).

Suggestions

Trim rhetorical/editorial passages (e.g. the 'A client who receives a surgical redline...' sentences) to the operational rule, keeping conciseness without losing the redline-granularity guidance.

Split the large federal sectoral overlay block and/or the output template into reference files under ./references/ and link to them from the body, moving progressive disclosure from a monolith toward appropriately split content.

Consider extracting the term-by-term and direction-specific tables into a reference doc so SKILL.md reads as an overview pointing to detail one level deep.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but carries notable editorial/rhetorical prose ('A client who receives a surgical redline trusts that you read carefully. A client who receives a wholesale replacement wonders whether you read at all.') and justificatory passages that could be tightened without losing the operational point.	2 / 3
Actionability	Provides concrete, specific guidance: term-by-term tables mapping each clause to a named playbook field, exact redline examples ('twelve (12)' → 'twenty-four (24)'), citation tiers ([settled]/[verify]/[verify-pinpoint]), and a copy-paste output template. Absence of code is appropriate for an instruction-only legal skill.	3 / 3
Workflow Clarity	Opens with a numbered 5-step sequence and embeds explicit validation checkpoints: the 'ask first' federal overlay gate, the 'no silent supplement' stop-and-ask protocol, and the signing gate that requires an explicit yes before proceeding.	3 / 3
Progressive Disclosure	References to the playbook CLAUDE.md are one-level-deep and well-signaled by section, but the skill is a single ~240-line monolith with substantial inline content (the federal overlay block, the full output template) that could be split into reference files; no bundle files are present to offload detail.	2 / 3
	Total	10 / 12 Passed

Description

90%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, well-targeted description with concrete actions and explicit, natural-sounding trigger phrases. The main weakness is second-person voice ('your', 'you're'), which costs it a specificity point under the rubric.

Suggestions

Rewrite in third person to match the rubric's voice requirement, e.g. 'Reviews a Data Processing Agreement against the DPA playbook — auto-detects whether the user is processor or controller and applies the matching half of the playbook.'

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Review a Data Processing Agreement against your DPA playbook', 'auto-detects whether you're processor or controller', 'applies the right half of the playbook'), which would anchor at 3, but it is written in second person ('your DPA playbook', 'you're processor or controller'), which the rubric penalizes by one point.	2 / 3
Completeness	Explicitly answers what it does and when to use it via an explicit 'Use when the user says...' trigger clause, matching the anchor for clearly answering both.	3 / 3
Trigger Term Quality	Quotes literal natural phrasings a user would say ('review this DPA', 'check this data processing addendum', 'customer sent their DPA', 'is this DPA okay') with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche (DPA review with processor/controller direction detection) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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/dpa-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.