一键在 Manus 中运行任何 Skill

transcribing-medical

星标0

分支0

更新时间2026年6月19日 19:51

Transcribes clinical audio (consults, dictations, rounds) preserving exact medical terminology, drug names, dosages, and speaker attribution without adding interpretation. Use when expected_format is "medical" or the audio is a doctor-patient encounter, clinical dictation, or discusses medication, diagnosis, or pharmacology.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

cyanxxy

cyanxxy/transcription-agent-go

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Medical Transcription Guidance

Preserve exact medical terminology and speaker attribution without adding interpretation. Do not turn the audio into a different document type; keep the output transcript-first and faithful to the spoken content.

Rules

Spell drug names and dosages exactly as spoken; use [inaudible] rather than guessing a dose.
Preserve clinician vs patient speaker labels when distinguishable.
Never paraphrase symptoms, measurements, or instructions.

References

Extended brand/generic and controlled-substance glossary: references/drug-names.md

同仓库更多 Skills

同仓库

dual-gemini

cyanxxy/transcription-agent-go

Generates two Gemini candidates (primary plus an automatically chosen secondary model) so the judge can cross-check disagreements. Use when accuracy matters more than latency or cost.

2026-06-190

gemini-plus-parakeet

cyanxxy/transcription-agent-go

Runs a primary Gemini candidate alongside a Parakeet ASR candidate so the judge can cross-check timing-sensitive transcripts. Use when word-level timestamp precision matters or Gemini timestamps alone are unreliable.

2026-06-190

single-gemini

cyanxxy/transcription-agent-go

Generates a single Gemini transcription candidate. Use as the fastest, lowest-cost strategy when one strong model pass is sufficient.

2026-06-190

transcribing-interview

cyanxxy/transcription-agent-go

Transcribes interviews and Q&A sessions faithfully with speaker turns exactly as spoken. Use when expected_format is "interview" or the audio is a one-on-one interview, journalist Q&A, or research session.

2026-06-190

transcribing-lecture

cyanxxy/transcription-agent-go

Transcribes lectures, talks, and presentations faithfully, surfacing main points only when clearly spoken. Use when expected_format is "lecture" or the audio is a class, keynote, seminar, or single-presenter talk.

2026-06-190

transcribing-legal

cyanxxy/transcription-agent-go

Transcribes legal proceedings, depositions, and hearings preserving exact wording, legal terminology, and attribution. Use when expected_format is "legal" or the audio is a deposition, court hearing, or legal consultation.

2026-06-190

name	transcribing-medical
description	Transcribes clinical audio (consults, dictations, rounds) preserving exact medical terminology, drug names, dosages, and speaker attribution without adding interpretation. Use when expected_format is "medical" or the audio is a doctor-patient encounter, clinical dictation, or discusses medication, diagnosis, or pharmacology.
license	Proprietary
compatibility	Uses Gemini structured output; optional Parakeet sidecar for word-level timing.
metadata	{"kind":"format","formats":"medical","version":"1.0.0","references":"references/drug-names.md"}

Medical Transcription Guidance

Rules

Spell drug names and dosages exactly as spoken; use [inaudible] rather than guessing a dose.
Preserve clinician vs patient speaker labels when distinguishable.
Never paraphrase symptoms, measurements, or instructions.

References

Extended brand/generic and controlled-substance glossary: references/drug-names.md