reidentifying-text

Reversibly de-identify clinical text with OpenMed and later restore the original PHI from a saved mapping. Use when the user needs pseudonymization rather than permanent anonymization, wants to mask PHI now and re-link it later under authorization (e.g. recontact, adjudication, GDPR pseudonymization), asks about deidentify keep_mapping, reidentify, or how to store and protect the re-identification mapping. Covers when reversibility is and is not appropriate (pseudonymization vs HIPAA Safe Harbor anonymization). Pairs after extracting-pii-entities and deidentifying-clinical-text.

Quality

93%

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

86%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, actionable skill body with copy-paste-ready examples and clear sequencing for the reversible de-identification round-trip; minor conciseness gains and an explicit error-recovery loop would lift it further.

Suggestions

De-duplicate the 'do not anonymize-and-keep-mapping' guidance so it appears once (either 'When to use' or 'Edge cases') rather than restated near-verbatim in both.

Add an explicit validate/fix/retry checkpoint around mapping storage (e.g., verify the vault write succeeded and the mapping round-trips before discarding in-memory copies) to strengthen the workflow for this security-sensitive path.

Tighten framing sentences like 'The mapping is the re-identification key. Treat it like a secret:' into the bullet list that follows, since the bullets already convey the same guidance.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence (no explaining what PHI/HIPAA/dict are), but the 'Never anonymize-and-keep-mapping' point is restated across 'When to use' and 'Edge cases', and a few framing sentences could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready code blocks cover the common cases — quick-start round-trip, consistent surrogates, secure separate mapping storage, and later re-identification load — each with specific calls and the assert verification.	5 / 5
Workflow Clarity	Clear sequence (de-identify with keep_mapping → store mapping separately encrypted → later re-identify under authorization) with an `assert restored == note` checkpoint and an edge-cases checklist, but lacks an explicit validate/fix/retry feedback loop for the security-sensitive storage step.	4 / 5
Progressive Disclosure	No bundle files exist; the single self-contained SKILL.md is well-organized into purposeful sections (When to use, Quick start, secure storage, reversible-vs-irreversible table, hand-off, edge cases, references), which is appropriate for a skill of this size.	5 / 5
	Total	18 / 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, provides rich natural trigger terms, and explicitly addresses both what the skill does and when to use it while distinguishing it from sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reversibly de-identify clinical text', 'restore the original PHI from a saved mapping', 'mask PHI now and re-link it later', 'store and protect the re-identification mapping' — giving comprehensive coverage rather than just naming the domain.	5 / 5
Completeness	Explicitly answers both 'what' ('Reversibly de-identify clinical text... restore the original PHI from a saved mapping') and 'when' (a clear 'Use when the user needs...' clause with concrete trigger conditions).	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms and tool-specific tokens: 'pseudonymization', 'anonymization', 'deidentify keep_mapping', 'reidentify', 're-identification mapping', 'GDPR pseudonymization', 'recontact', 'adjudication' — phrases users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (reversible re-identification round-trip) with distinct triggers, and explicitly carves out adjacent skills via 'Pairs after extracting-pii-entities and deidentifying-clinical-text', 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/reidentifying-text/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.