Clinical anonymization
Skill elisaterumi-ai/agent-skills-in-practice/examples/clinical-anonymization
Removes sensitive data from clinical text while preserving meaning. Use for healthcare data.From its SKILL.md
npx -y skills add elisaterumi-ai/agent-skills-in-practice --skill clinical-anonymizationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
0.4 KB, 68 tokens by cl100k_base, as published. Nobody here has run it
Instructions
-
Identify sensitive data:
- Names
- Dates
- Locations
- IDs
-
Replace with placeholders:
- [NAME]
- [DATE]
- [LOCATION]
- [ID]
-
Preserve clinical meaning
Output Format
- Anonymized text
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most healthcare skills give in 68 tokens
Counted across 147 of the 152 authors here whose files we hold, read 2026-08-07
- Export trial data to CSV formatin 11 of 147, across 2 files
- Retrieve trial details using an NCT IDin 11 of 147, across 2 files
- Split clinical datasets strictly by patientin 11 of 147, across 3 files
- Use the ClinicalTrials.gov API v2in 10 of 147, across 1 file
- Search trials by condition, drug, location, status or phasein 10 of 147, across 1 file
- Use maximum page size for bulk data retrievalin 10 of 147, across 1 file
- Extract and summarize key study informationin 10 of 147, across 1 file
- Combine multiple filters for targeted searchesin 10 of 147, across 1 file
- Print and review dataset statistics before modelingin 8 of 147, across 1 file
- Start model development with simple baselinesin 8 of 147, across 1 file
- Match preprocessing processors directly to data typesin 8 of 147, across 1 file
- Monitor validation metrics for task type and class imbalancein 8 of 147, across 1 file
Said here and by no other author read
- Identify names
- Identify dates
- Identify locations
- Replace names with [NAME]
- Replace dates with [DATE]
- Replace locations with [LOCATION]
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.