configuring-privacy-policies

Select and customize OpenMed's seven bundled privacy policy profiles for de-identification, and build custom surrogate generators. Use when the user asks which policy fits HIPAA Safe Harbor vs Expert Determination vs GDPR vs PIPEDA vs a research limited dataset vs strict no-leak, wants to pass policy= to deidentify(), needs to keep quasi-identifiers for research, or must register a custom MRN/name/address surrogate provider. Covers the profile-to-use-case map, AnonymizerConfig/Anonymizer for fine control, and register_clinical_provider / register_label_generator. Pairs with OpenMed deidentifying-clinical-text and generating-synthetic-surrogates.

Quality

91%

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

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, executable reference that leads with working code, gives a decision map for profile selection, and documents customization with concrete examples and edge cases. It is efficient and actionable, with only minor redundancy and no need for the missing bundle files.

Suggestions

Drop or trim the 'When to use this skill' section — its triggers already appear in the frontmatter description, so it mostly restates them.

Consider moving the seven-profile table and 'Key dimensions to reason about' bullets into a references/ file (e.g. PROFILES.md) to keep SKILL.md an overview, since no bundle files currently exist.

Add a one-line validation/verification pointer for custom surrogates (e.g. checking collision against real ID space) as an explicit checkpoint in the Customizing section, beyond the CANONICAL_LABELS note.

Dimension	Reasoning	Score
Conciseness	Mostly lean and information-dense — the profile table, key-dimension bullets, and edge cases all earn their place — with only minor redundancy (the 'When to use this skill' section restates triggers already in the description).	4 / 5
Actionability	Copy-paste-ready, executable code in both Quick start (three policy calls) and Customizing (Anonymizer, register_label_generator with a concrete hospital_mrn generator, register_clinical_provider), covering the common cases.	5 / 5
Workflow Clarity	Clear decision logic ('map regulation → profile') and numbered customization steps with a validation checkpoint ('Validate custom labels against openmed.CANONICAL_LABELS'), though it is a selection/reference skill rather than a strict multi-step workflow with feedback loops.	4 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with one-level references to sibling skills and source paths and no nested refs; the dense profile table and config-dimension bullets could arguably live in a separate reference file, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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, third-person description that concretely states capabilities and gives explicit, varied 'Use when' triggers tied to named regulations and API calls. It is comprehensive, distinct, and free of fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Select and customize ... privacy policy profiles', 'build custom surrogate generators', 'register a custom MRN/name/address surrogate provider', 'pass policy= to deidentify()' — with comprehensive coverage of the skill's domain.	5 / 5
Completeness	Explicitly answers both what ('Select and customize ... profiles ... build custom surrogate generators') and when ('Use when the user asks which policy fits ... wants to pass policy= ... needs to keep quasi-identifiers ... or must register a custom ... surrogate provider') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Surfaces natural user phrasing across regulatory regimes — 'HIPAA Safe Harbor vs Expert Determination vs GDPR vs PIPEDA', 'research limited dataset', 'strict no-leak', 'quasi-identifiers', 'register a custom ... surrogate provider' — covering synonyms and variants a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (OpenMed de-identification policy selection) with triggers tied to specific regulatory regimes and API surfaces, and explicitly pairs with adjacent skills, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: maziyarpanahi/openmed
Path: skills/configuring-privacy-policies/SKILL.md
Commit: 80da98c

Reviewed: about 23 hours 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.