unisound-operation-record根据手术相关病历素材生成规范的手术记录。输入术前小结、术中记录、术后记录等,调用内部医疗大模型,输出结构化手术记录(含手术日期、时间、地点、医生、手术名称、指征、诊断、经过、异常情况、术后情况、签名等 14 个字段)。
Install via ClawdBot CLI:
clawdbot install unisound-llm/unisound-operation-recordGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://maas-api.hivoice.cn/v1`。Audited May 20, 2026 · audit v1.0
Generated Aug 11, 2026
Hospitals need to generate standardized surgical records after each operation. This skill processes pre-op, intra-op, and post-op notes to produce a structured record, saving time for medical staff and ensuring consistency.
Medical transcription companies can use this skill to convert dictated or documented surgical procedures into structured records for clinics that lack in-house systems.
Healthcare quality teams can use the generated records to audit surgical practices, check completeness, and identify deviations from standard procedures.
For legal purposes, complete and accurate surgical records are critical. This skill helps produce comprehensive documentation that can be used in malpractice cases or medical dispute resolution.
Researchers can use the structured surgical records to extract data for clinical studies, including surgical techniques, outcomes, and complications.
Offer the skill as a cloud-based service to hospitals and clinics, charging a monthly subscription per user or per hospital bed. Includes regular updates and support.
Expose the skill as an API for integration into existing EHR systems. Charge per surgical record generated, allowing variable usage without long-term contracts.
Bundle the skill with medical coding, billing, or analytics services. Generate additional revenue by offering insights derived from the surgical records, such as complication rates or cost analysis.
💬 Integration Tip
Ensure input files are de-identified before sending to the model, and configure a stable appkey for authentication.
Scored Aug 11, 2026
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.