dsar-response

Walk through a Data Subject Access Request (or deletion, portability, correction request) and draft the response — verify identity, locate data system-by-system, assess exemptions, draft the acknowledgment and substantive response letters. Use when a DSAR comes in, the user pastes an access/deletion/portability/correction request, or says "DSAR came in", "access request", "right to be forgotten", or "someone wants their data".

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 thorough, well-sequenced DSAR workflow with concrete templates and strong validation gates. Its weaknesses are verbosity in the prose and a monolithic single-file structure that would benefit from one-level-deep reference files.

Suggestions

Tighten the prose throughout — several cautions, rationales, and asides can be condensed to bullet points without losing the legal nuance, improving conciseness.

Split the letter templates (acknowledgment / access / deletion) and the exemption-analysis guidance into separate reference files under references/, linked from the body, to improve progressive disclosure.

Consider moving the source-attribution tiering and research-connector notes into a references/research.md to reduce inline bulk while keeping them discoverable.

Dimension	Reasoning	Score
Conciseness	Domain guidance is specific rather than re-explaining concepts Claude knows, so it is not a 1, but the ~290-line body is prose-heavy with passages (rationales, cautions, asides) that could be tightened; verbosity is penalized even when accurate, capping it at 2.	2 / 3
Actionability	Provides concrete, fill-in-the-blank letter templates (acknowledgment, access, deletion) plus a systems-walk table and explicit escalation triggers — copy-paste-ready guidance rather than vague direction, matching the score-3 anchor.	3 / 3
Workflow Clarity	A clearly sequenced six-step workflow with explicit validation gates (identity verification, attorney-review gate, "Before sending either letter", research-connector pre-flight) and feedback loops, matching the score-3 checklist/checkpoint anchor.	3 / 3
Progressive Disclosure	Well-organized into sections, but it is a single ~290-line file with no bundle reference files (references/scripts/assets are empty), so letter templates and exemption guidance that should be split out remain inline; the simple-skill allowance does not apply given the length, so it cannot reach 3.	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: concrete capabilities, natural trigger phrasings, and an explicit Use-when clause, all in third-person voice. It cleanly answers what the skill does and when to invoke it with minimal fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "verify identity, locate data system-by-system, assess exemptions, draft the acknowledgment and substantive response letters" — matching the score-3 anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (walk through verify/locate/assess/draft) and when via a clear "Use when a DSAR comes in..." clause, matching the score-3 what-and-when anchor.	3 / 3
Trigger Term Quality	Natural phrasings a user would actually say are present — "DSAR came in", "access request", "right to be forgotten", "someone wants their data" — giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear DSAR/privacy-legal niche with distinct triggers unlikely to fire for unrelated skills; not below 3 because the scope is unmistakable, not above because 3 is the cap.	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/dsar-response/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.