Shifting Clinical Dates

What it does

When your agent uses it

• 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
• Longitudinal analysis

Example prompts

• “shiftdates”
• “/shifting-clinical-dates”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Decide the offset policy. Per-patient is standard for clinical research.
2. 2Set keep_year=False for Safe Harbor. (keep_year=True retains the year,
3. 3Cap ages over 89 separately. Date shifting moves dates; it does not
4. 4Keep names/IDs handled too. shift_dates only touches dates. Run a normal
5. 5Verify intervals are preserved and no calendar leaked via audit=True.

What it can do on your machine

Read from SKILL.md and the folder at commit 34d7b8c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • ecfr.gov
  • hhs.gov

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Shifting Clinical Dates loads about 1.7k tokens when it runs. Until then it costs about 162 tokens; SKILL.md has 592 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~162

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 34d7b8c, republished under its Apache-2.0 licence (© maziyarpanahi). 592 words, ~1,652 tokens.

name

shifting-clinical-dates

description

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.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

de-identification

metadata.pairs

after

metadata.version

1.0

import openmed

note = (
    "Admitted 2024-03-02, started antibiotics 2024-03-04, discharged 2024-03-09. "
    "Follow-up scheduled 2024-04-02."
)

# Shift every date by the SAME offset -> intervals preserved, dates obscured.
result = openmed.deidentify(
    note,
    method="shift_dates",
    consistent=True,        # one stable offset for this run
    seed=20240519,          # reproducible per-patient offset (use a per-patient key)
    keep_year=False,        # do NOT retain the year (Safe Harbor: year-only is the max)
)
print(result.deidentified_text)
# Admit -> antibiotics is still 2 days; admit -> discharge still 7 days; etc.

real:    Mar 2  ──2d──▶ Mar 4  ──5d──▶ Mar 9
shifted: Jul 18 ──2d──▶ Jul 20 ──5d──▶ Jul 25     (offset = +138 days, intervals intact)

def patient_offset_seed(patient_key: str) -> int:
    import hashlib, hmac
    # keyed so the mapping from patient -> offset is itself a secret
    digest = hmac.new(b"<vault-secret>", patient_key.encode(), hashlib.sha256).digest()
    return int.from_bytes(digest[:8], "big")

for doc in patient_documents:
    openmed.deidentify(
        doc, method="shift_dates",
        consistent=True, seed=patient_offset_seed(patient_id),
        keep_year=False,
    )

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/shifting-clinical-dates of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c