Generating Synthetic Surrogates

What it does

When your agent uses it

• The user wants surrogate names
• Dates rather than opaque masks
• Needs consistent fake identities across a document
• Must keep notes natural for downstream NLP

Example prompts

• “replace”
• “/generating-synthetic-surrogates”

Requirements

• Python 3

Workflow steps

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

1. 1Choose method="replace" (or a profile like gdpr_pseudonymization /
2. 2Enable consistency with consistent=True and a seed= so repeated
3. 3Set locale= so surrogates look native (pt_BR, de_DE, …); it
4. 4Register custom generators for any house-specific formats (MRN, account,
5. 5If reversibility is needed, add keep_mapping=True and store
6. 6Verify no surrogate collides with a real value and residual risk is low

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):

  • eur-lex.europa.eu
  • 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

Generating Synthetic Surrogates loads about 1.8k tokens when it runs. Until then it costs about 171 tokens; SKILL.md has 542 words of instructions outside code blocks.

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

~171

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). 542 words, ~1,779 tokens.

name

generating-synthetic-surrogates

description

Replace detected PHI with realistic, type-matched fake values in OpenMed so clinical notes stay readable and parseable instead of full of [REDACTED] markers. Use when the user wants surrogate names, MRNs, addresses, or dates rather than opaque masks, needs consistent fake identities across a document, must keep notes natural for downstream NLP, or wants to register a custom surrogate generator or provider. Covers deidentify(method="replace", consistent=True, seed=..., locale=...), register_label_generator, register_clinical_provider, and Anonymizer/AnonymizerConfig. Pairs with OpenMed deidentifying-clinical-text and configuring-privacy-policies.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

de-identification

metadata.pairs

after

metadata.version

1.0

import openmed

note = (
    "Patient John Doe (MRN 1234567) saw Dr. John Doe's colleague on 2024-03-02. "
    "Reach John Doe at 617-555-0142."
)

result = openmed.deidentify(
    note,
    method="replace",
    consistent=True,     # every "John Doe" -> the SAME surrogate within this call
    seed=42,             # reproducible across runs
    locale="en_US",      # shapes the fakes; defaults from lang via LANG_TO_LOCALE
)
print(result.deidentified_text)
# Patient Mark Lee (MRN 8830127) saw Dr. Mark Lee's colleague on 2024-07-18. ...

from openmed import (
    register_label_generator, register_clinical_provider,
    Anonymizer, AnonymizerConfig,
)

# Override the surrogate for one canonical label. Signature: (faker, original, *, locale)
def hospital_mrn(faker, original, *, locale):
    return f"H{faker.numerify('#######')}"

register_label_generator("ID_NUM", hospital_mrn)   # global, all new Anonymizers

# Add a whole custom Faker provider (e.g. proprietary identifier formats):
register_clinical_provider(MyClinicalProvider)     # a faker BaseProvider subclass

# Per-instance control (preferred for isolation): pass providers via config,
# and pull a single surrogate directly when you need one.
anon = Anonymizer(AnonymizerConfig(
    lang="en", consistent=True, seed=7, custom_providers=[MyClinicalProvider],
))
fake = anon.surrogate("1234567", "ID_NUM")

© 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/generating-synthetic-surrogates of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c