reviewing-reidentification-risk

Run expert-determination-style quasi-identifier risk scoring (k-anonymity, l-diversity) plus OpenMed's empirical re-identification attack on a de-identified dataset, then document residual risk in a defensible memo. Use when the user needs HIPAA Expert Determination (45 CFR 164.514(b)(1)) support, asks whether a dataset is safe to release, worries about singling-out via age/ZIP/dates, or wants a statistical "very small risk" determination. Covers identifying quasi-identifiers, computing k-anonymity / l-diversity, running openmed.eval.attacks.reid (run_reid_attack / run_reid_benchmark) as the adversarial attack, and writing the risk memo. Pairs after deidentifying-clinical-text and auditing-deid-leakage.

Quality

98%

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

96%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 high-quality, action-oriented skill body: executable code, a sequenced workflow with a real validation/re-score loop, and disciplined conciseness without over-explanation. Only mild room to split long sections into reference files, but the self-contained structure is well-judged for this domain.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence — no tutorializing of what HIPAA or k-anonymity is, tight code with only need-to-know comments, and dense workflow steps; every token earns its place.	5 / 5
Actionability	Fully executable Quick start with the real import path, function calls, and metric keys, plus concrete thresholds (k ≥ 5/11) and specific generalization recipes (age→band, ZIP5→ZIP3) throughout the workflow.	5 / 5
Workflow Clarity	Six clearly sequenced steps with an explicit validation feedback loop in step 5 ('re-run until k_min and linkage rate meet your documented threshold') for a release-grade operation, matching the anchor with checkpoints and a retry loop.	5 / 5
Progressive Disclosure	Well-organized into clear sections (When to use, Quick start, Workflow, Hand-off, Edge cases, Standards) with no nested references and no bundle files to navigate, though the ~130-line body is longer than the simple-skill 50-line carve-out that would guarantee a 5.	4 / 5
	Total	19 / 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 exceptionally well-crafted description: specific, trigger-rich, complete on both what and when, and clearly distinct from neighboring de-identification skills. Voice is consistently third person with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — quasi-identifier risk scoring (k-anonymity, l-diversity), the empirical re-identification attack, and writing a defensible residual-risk memo — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (run QI risk scoring, the empirical attack, write the memo) and 'when' ('Use when the user needs HIPAA Expert Determination...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including 'HIPAA Expert Determination', 'safe to release', 'singling-out via age/ZIP/dates', 'very small risk', k-anonymity, and l-diversity, plus the regulatory citation.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear HIPAA Expert Determination / re-identification niche with named module APIs and explicit pairing with sibling de-id 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/reviewing-reidentification-risk/SKILL.md
Commit: 80da98c

Reviewed: about 24 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.