Deidentifying Clinical Text

What it does

When your agent uses it

• The user needs to de-identify medical notes
• Strip patient identifiers
• Redact PHI before sharing
• Anonymize discharge summaries

Example prompts

• “/deidentifying-clinical-text”

Requirements

• Python 3

Workflow steps

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

1. 1Pick a method and a policy. Start from a bundled policy= profile
2. 2Set confidence_threshold deliberately. Default is 0.7. For de-id,
3. 3Run deidentify. Inspect result.pii_entities by offset and label,
4. 4For stable surrogates, pass consistent=True, seed= so the same
5. 5For reversibility, pass keep_mapping=True and store result.mapping
6. 6Verify, don't assume. Check residual risk with 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):

  • 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

Deidentifying Clinical Text loads about 1.8k tokens when it runs. Until then it costs about 163 tokens; SKILL.md has 602 words of instructions outside code blocks.

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

~163

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

~1.8k

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). 602 words, ~1,835 tokens.

name

deidentifying-clinical-text

description

Remove, mask, or replace PHI/PII in clinical free text on-device with OpenMed's deidentify(). Use when the user needs to de-identify medical notes, strip patient identifiers, redact PHI before sharing or analysis, anonymize discharge summaries, or pick a de-id method (mask vs remove vs replace vs hash vs shift_dates). Covers confidence_threshold for safety, consistent+seed for stable surrogates, keep_mapping for reversible de-id, policy= profiles, and the DeidentificationResult fields. Pairs with OpenMed extract_pii (detect spans), reidentify (restore), configuring-privacy-policies, and auditing-deidentification-runs.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

openmed-core

metadata.pairs

adjacent

metadata.version

1.0

import openmed

note = (
    "Patient John Doe (MRN 1234567) was seen on 2024-03-02 by Dr. Alice Reed. "
    "Contact: john.doe@example.com, 617-555-0142."
)

result = openmed.deidentify(
    note,
    method="mask",                 # mask | remove | replace | hash | shift_dates
    confidence_threshold=0.7,      # safety default; raise to reduce false negatives' impact
    policy="hipaa_safe_harbor",    # optional bundled profile (see below)
)

print(result.deidentified_text)
# Patient [NAME] (MRN [ID_NUM]) was seen on [DATE] by Dr. [NAME]. ...

for e in result.pii_entities:
    # NEVER log e.text / e.original_text — those are raw PHI. Use offsets + label.
    print(e.canonical_label, e.start, e.end, round(e.confidence, 3))

# Same fake identity for every mention of the same person, reproducibly:
r = openmed.deidentify(note, method="replace", consistent=True, seed=42)

# Reversible de-id (keep the mapping secret and separate from output):
r = openmed.deidentify(note, method="mask", keep_mapping=True)
restored = openmed.reidentify(r.deidentified_text, r.mapping)
assert restored == note

© 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/deidentifying-clinical-text of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c