CtrlK
BlogDocsLog inGet started
Tessl Logo

auditing-safe-harbor-checklist

Verify OpenMed de-identified output against all 18 HIPAA Safe Harbor identifier categories and report residual re-identification risk. Use when the user must confirm a note meets HIPAA Safe Harbor (45 CFR 164.514(b)(2)), needs a coverage checklist mapping detected entities to the 18 categories, wants to flag gaps like ages over 89, rare geography, fax vs phone, or biometrics, or asks whether masking was complete. Maps OpenMed CANONICAL_LABELS to the 18 HIPAA classes and uses extract_pii / deidentify to check coverage. Pairs with OpenMed deidentifying-clinical-text and auditing-deidentification-runs.

77

Quality

96%

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

92%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 auditing skill: executable Quick start code, a sequenced workflow with validation and human sign-off, concrete edge cases, and a single one-level-deep reference holding the mapping table. Only minor conciseness trims would be needed to reach the top anchor.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — executable code, named APIs, and tight edge-case bullets with little padding. A few framing sentences in the opening paragraph ('This skill turns that legal checklist into a concrete coverage check over OpenMed output...') could be trimmed without loss, keeping it just below the lean 5 anchor.

4 / 5

Actionability

The Quick start gives copy-paste-ready, executable code using real OpenMed APIs (extract_pii, normalize_label, LABEL_TO_HIPAA, HIPAA_SAFE_HARBOR_CLASSES), and the Workflow and Edge cases sections give specific commands and concrete rules (age > 89 → '90+', 3-digit ZIP gating, audit=True for residual_risk).

5 / 5

Workflow Clarity

A clear 5-step sequence (de-identify → map spans to classes → walk checklist → assess residual risk via audit=True → record human 'no actual knowledge' sign-off) with explicit validation checkpoints: non-zero residual_risk triggers review and a mandatory human sign-off step closes the loop.

5 / 5

Progressive Disclosure

SKILL.md is an overview that clearly signals one-level-deep references to references/safe-harbor-identifiers.md (the authoritative 18-category mapping table), which is a real bundle file; the bulk detail lives in the reference and navigation to it is repeated and unambiguous.

5 / 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.

A strong, specific description that clearly states what the skill does and gives multiple natural 'Use when' triggers, with concrete HIPAA categories and OpenMed APIs. It is distinct from neighboring skills via explicit pairing boundaries.

DimensionReasoningScore

Specificity

Multiple concrete actions are named — 'Verify OpenMed de-identified output against all 18 HIPAA Safe Harbor identifier categories', 'report residual re-identification risk', 'Maps OpenMed CANONICAL_LABELS to the 18 HIPAA classes', and 'uses extract_pii / deidentify to check coverage' — giving comprehensive, specific coverage rather than generic verbs.

5 / 5

Completeness

Both 'what' (verify against 18 categories, report residual risk, map labels) and 'when' (explicit 'Use when...' with multiple concrete trigger phrases) are clearly and explicitly answered.

5 / 5

Trigger Term Quality

The 'Use when...' clause enumerates natural user phrasings — 'confirm a note meets HIPAA Safe Harbor', 'needs a coverage checklist', 'wants to flag gaps like ages over 89, rare geography, fax vs phone, or biometrics', and 'asks whether masking was complete' — covering synonyms and concrete gap signals a user would actually say.

5 / 5

Distinctiveness Conflict Risk

A clear niche — OpenMed-specific HIPAA Safe Harbor coverage auditing — with distinct triggers and explicit 'Pairs with' boundaries to deidentifying-clinical-text and auditing-deidentification-runs, minimizing overlap with adjacent 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.