customize

Guided customization of your privacy practice profile — change one thing without re-running the whole cold-start interview. Adjust risk posture, escalation contacts, DPA playbook, privacy policy commitments, PIA house style, DSAR process, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my playbook", or "customize".

Quality

92%

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

85%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 well-structured, highly actionable instruction skill with clear sequencing and explicit guardrails. The only weakness is mild token redundancy where the opening section re-enumerates domains already present elsewhere.

Suggestions

Tighten the "When this runs" section: drop the re-listing of domains (risk posture, escalation contact, DPA position, PIA section, DSAR timeline) since they already appear in the description and the customizable map; keep only the intent and the two constraints (no full re-interview, no hand-editing YAML).

Consider collapsing the customizable-map category descriptions into shorter one-liners, since several sub-bullets restate info implied by the category name, trimming tokens without losing clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows (DPA, PIA, DSAR are used without definition), but the "When this runs" section re-lists domains already covered by both the description and the customizable map, which could be tightened; not 3 because of this redundant re-enumeration.	2 / 3
Actionability	Gives concrete file paths (e.g. "…/privacy-legal/CLAUDE.md", "company-profile.md"), placeholder detection ("[PLACEHOLDER]"), copy-paste-ready quoted prompts, and specific change examples with their downstream effects, matching the fully-actionable anchor; not 2 because guidance is concrete and complete rather than pseudocode-like.	3 / 3
Workflow Clarity	A clear six-step sequence with explicit validation/refusal checkpoints — refuse if config missing or placeholder-filled, show-current-then-confirm-before-write, flag inconsistency, and refuse sub-minimum statutory DSAR timelines — matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is single-purpose, organized into clean When-this-runs / What-to-do / Guardrails sections with no nested references; per the simple-skills note, well-organized single-purpose content can score 3 without external file references.	3 / 3
	Total	11 / 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, well-scoped description that names concrete capabilities, gives natural trigger phrases, and explicitly covers both what and when. It is clearly distinguishable within the privacy-legal plugin set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete adjustment areas — "risk posture, escalation contacts, DPA playbook, privacy policy commitments, PIA house style, DSAR process, or matter workspace paths" — matching the anchor for enumerating several specific actions, not merely naming a domain.	3 / 3
Completeness	Explicitly answers both what (guided one-thing customization of the privacy profile with enumerated areas) and when (an explicit "Use when the user says…" clause), satisfying the top anchor; not 2 because the when-trigger is explicit rather than implied.	3 / 3
Trigger Term Quality	Provides natural user phrasings — "change my [thing]", "update my profile", "edit my playbook", or "customize" — covering terms a user would actually say, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear privacy-legal profile-customization niche with distinct triggers, making conflict with unrelated skills unlikely; the mild "your privacy practice profile" is a possessive over the profile object rather than instructional second-person address.	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/customize/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.