Plugins
Browse, filter, and install DeepSeek-Harness plugins.
4 plugins found
dsh-medical-anonymizer
wld007/dsh-medical-anonymizer
Batch pseudonymization for medical text, CSV, JSON, and XLSX in DeepSeek Harness. Deterministic identifier rules run first; an optional OpenAI-compatible model pass adds discovery and verification. Exact-span replacement preserves file structure, tokens stay stable per value, and each batch produces an audit report plus a re-identification vault. DICOM images get header-only de-identification based on PS3.15 Annex E, with pixel data left byte-identical.
dsh-medseek
mr-neutr0n/dsh-medseek
Clinical documentation and reference bundle for healthcare professionals: SOAP/APSO progress notes, admission H&P, SBAR/I-PASS handover, discharge summaries, Safe Harbor de-identification, patient-instruction readability, completeness checks, and cited lookups against FDA labels, MedlinePlus, PubMed, and ClinicalTrials.gov. Draft-only with a PHI egress guard; not a medical device.
dsh-patient-education
liuhange789/dsh-patient-education
Turns decisions a doctor has already made into a patient-readable after-visit guide: one-sentence diagnosis, medication table (name / how to take / for how long / caution), diet & activity, follow-up, and when to seek urgent care. A hard-coded template filled with the input verbatim: no model-written medical text, no advice, no diagnosis, no medication recommendation; a doctor must review the output before it reaches a patient.
dsh-clinic-intake
liuhange789/dsh-clinic-intake
Pre-visit intake structuring for clinics: six patient questions become a structured intake summary (chief complaint location / character / duration, medications with frequency, allergies, past history, reason-category tag) capped at 300 Chinese characters. Rule-based and local-only, it redacts phone numbers, ID numbers, emails and name labels, and never suggests a diagnosis, triage decision or medication. Ships two host tools, a web-UI intake wizard in the session header, and an offline single-file HTML form for the waiting room.