shifting-clinical-dates

Apply consistent per-patient date shifting in OpenMed that preserves intervals between events while satisfying HIPAA Safe Harbor's date rule. Use when the user needs to de-identify dates but keep temporal structure for research, shift all dates by the same offset per patient, preserve days-between-events for survival or longitudinal analysis, cap ages over 89, or strip everything but the year. Covers deidentify(method="shift_dates", date_shift_days=..., keep_year=...) and per-patient reproducible offsets via consistent=True, seed=.... Pairs with OpenMed deidentifying-clinical-text and auditing-safe-harbor-checklist.

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, actionable skill body with executable code and a sensible workflow including verification. The main weaknesses are mild conceptual over-explanation and a missing explicit retry loop on audit failure.

Suggestions

Tighten the 'How interval preservation works' section — the ASCII diagram restates a mechanic the one-line 'identical offset → intervals unchanged' already conveys; consider trimming to one sentence.

Add an explicit feedback loop to the workflow's Verify step: 'If audit=True reports a leaked calendar date or broken interval, adjust keep_year/offset and re-run.'

Consider moving the 'Edge cases & gotchas' or 'Standards & references' block into a references/ file so SKILL.md stays a lean overview that points one level deep.

Dimension	Reasoning	Score
Conciseness	Largely lean with each section earning its place, but the conceptual intro and the 'How interval preservation works' ASCII diagram mildly re-explain date-shifting mechanics Claude could largely infer.	4 / 5
Actionability	Quick-start and per-patient seed-derivation code are fully executable and copy-paste ready, and the workflow gives concrete parameter guidance covering the common cases.	5 / 5
Workflow Clarity	A clear 5-step sequence with an explicit 'Verify' (audit=True) checkpoint avoids the destructive/batch cap, but it lacks a validate→fix→retry feedback loop for audit failure.	4 / 5
Progressive Disclosure	No bundle files exist, yet the self-contained ~125-line body is well-sectioned with clear one-level pointers to sibling skills and external standards; minor room to split edge cases or standards into references.	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: third-person voice, concrete capabilities, explicit trigger guidance, and clear delineation from sibling de-identification skills. It names the API surface (method, key params) without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — per-patient date shifting, preserving intervals, capping ages over 89, stripping to year — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both 'what' (apply per-patient shifting preserving intervals, satisfying HIPAA) and 'when' via a concrete 'Use when the user needs to de-identify dates…' trigger clause.	5 / 5
Trigger Term Quality	Natural clinical-research phrasings a user would actually say ('de-identify dates but keep temporal structure', 'survival or longitudinal analysis', 'cap ages over 89') with synonyms covered.	5 / 5
Distinctiveness Conflict Risk	Pinned to method="shift_dates" with a clear niche (date de-identification), and explicitly distinguishes itself by naming sibling skills it 'Pairs with' rather than overlapping them.	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/shifting-clinical-dates/SKILL.md
Commit: 80da98c

Reviewed: 1 day 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.