CtrlK
BlogDocsLog inGet started
Tessl Logo

pseudonymizing-for-gdpr

Apply GDPR-grade pseudonymization to clinical or personal text with OpenMed, keeping a separately-held re-linkage key so the data can be controlled-re-linked later. Use when the user must process EU personal/health data under GDPR, asks for pseudonymization vs anonymization, needs Art. 4(5) / Art. 9 / Recital 26 alignment, wants a reversible mapping/key vault held apart from the data, or needs controlled re-linkage. Covers openmed.deidentify(policy="gdpr_pseudonymization", keep_mapping=True), storing the mapping in a separate key vault, reidentify() for authorized re-linkage, and retention. Pairs after extracting-pii-entities and configuring-privacy-policies.

74

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 strong, actionable body with executable code and a clear sequenced workflow. It is largely concise and well-structured, with minor room to tighten repeated guidance and add an inline validation checkpoint.

Suggestions

Consolidate the 'pseudonymized ≠ anonymized' point, which is stated in both the intro and the Edge cases section, to reduce redundancy.

Add an inline validation checkpoint in the workflow (e.g. verify detector recall or scan deidentified_text for residual identifiers before splitting key from data) rather than only delegating verification to sibling skills.

Trim the opening GDPR article exposition to the minimum needed to justify the reversible-key approach, trusting Claude's existing knowledge of GDPR.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence, though the opening GDPR article exposition and some restated gotchas (e.g. pseudonymized≠anonymized appears twice) could be trimmed slightly. Efficient but not perfectly tight.

4 / 5

Actionability

Fully executable copy-paste Python with specific parameters (policy, keep_mapping, consistent, seed), the reidentify() re-linkage call, and concrete hand-off commands; common cases are covered.

5 / 5

Workflow Clarity

A clear 5-step sequence with explicit separation and logging/destruction checkpoints, but it lacks an explicit validate→fix→retry feedback loop; verification is delegated to a sibling skill rather than an inline checkpoint.

4 / 5

Progressive Disclosure

Well-organized sections (Quick start, Workflow, Hand-off, Edge cases, References) with clearly signaled hand-offs to sibling skills; no bundle files exist, so content is appropriately self-contained, though sibling references are skill names rather than file paths.

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.

An exemplary description: concrete actions, natural trigger terms, explicit what/when coverage, and a distinct niche with sibling-skill pairing. It is comprehensive without resorting to vague fluff or buzzwords.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — pseudonymize text, keep a separately-held re-linkage key, store the mapping in a key vault, reidentify() for authorized re-linkage, and retention — covering the capability comprehensively.

5 / 5

Completeness

Explicitly answers 'what' (apply GDPR-grade pseudonymization with a separately-held re-linkage key) and 'when' via a concrete 'Use when...' clause enumerating multiple trigger scenarios.

5 / 5

Trigger Term Quality

Natural user-facing terms abound — 'pseudonymization vs anonymization', 'GDPR', 'EU personal/health data', 'Art. 4(5) / Art. 9 / Recital 26', 'reversible mapping/key vault', 'controlled re-linkage' — matching phrases a user would actually say.

5 / 5

Distinctiveness Conflict Risk

A clear niche (GDPR reversible pseudonymization with key vault) with distinct triggers and explicit pairing with sibling skills, minimizing overlap with other de-identification skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
maziyarpanahi/openmed
Reviewed

Table of Contents

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.