ClawHub

研究生组会录音智能总结助手。和老师讨论/组会汇报的录音,调用skill可以有针对性的识别出学生和老师的内容,同时以老师的内容为重点进行内容总结,根据用户指令,自定义选择以文本展示或者音频展示。

v1.0.1

Use when: 用户要把研究生组会、与导师讨论论文修改、技术方案推敲等小规模学术讨论录音转成纪要，并提取老师意见、学生回应、待修改事项和后续动作时触发。 适用于 2 到 3 人、以老师和学生为主的学术讨论场景。Skill 会优先使用 SenseAudio ASR 的说话人分离能力，再结合 Agent 的大模型...

⭐ 0· 119·0 current·0 all-time
by@xinhao-96
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name/description (academic discussion ASR/TTS and LLM-assisted summarization) match the declared requirements: python3 and a single SENSEAUDIO_API_KEY for the SenseAudio service. The script calls SenseAudio ASR and TTS endpoints and produces the stated artifacts.
✓
Instruction Scope
SKILL.md and scripts/main.py focus on transcribing, diarizing, building LLM input, and synthesizing summary audio. They only reference SENSEAUDIO_API_KEY and optional SENSEAUDIO_API_BASE, operate on user-supplied audio files, and write outputs under ./outputs. The instructions explicitly prohibit using other TTS services and require returning MEDIA: lines — this is consistent with the skill purpose.
ℹ
Install Mechanism
There is no formal install spec, but scripts/main.py will attempt to auto-install the 'requests' package via pip at runtime if missing (subprocess run of pip). Auto-installing packages at runtime is functional but increases runtime network activity and may modify the environment; review this behavior if you prefer no runtime package installs.
✓
Credentials
Only one required env var (SENSEAUDIO_API_KEY) and an optional SENSEAUDIO_API_BASE are declared and used. This is proportionate to the skill's purpose. No unrelated credentials or config paths are requested.
✓
Persistence & Privilege
Skill is not always-enabled and does not request persistent elevated privileges. It writes output files under a local ./outputs directory (normal for a CLI utility) and does not modify other skills or system-wide agent settings.
Assessment
This skill appears internally consistent for converting small advisor-student meeting recordings into transcriptions, structured summaries, and a TTS audio summary. Before installing or running it: 1) Verify you trust the SenseAudio provider (default API base is https://api.senseaudio.cn) because the script will send audio and use your SENSEAUDIO_API_KEY. 2) Only provide an API key with minimal/appropriate permissions; rotate or revoke the key if you later stop using the skill. 3) Be aware the script may auto-install the Python 'requests' package at runtime (network download via pip). If you prefer, pre-install dependencies in a controlled environment. 4) Audio files may contain sensitive content (student/advisor conversations); ensure you are allowed to upload/process them by the external service. 5) Check generated outputs under ./outputs and confirm the MEDIA: behavior works with your target channel before relying on automated delivery. If you need higher assurance, request a vendor/homepage or code provenance (signed release, repository) before trusting the skill in production.

Like a lobster shell, security has layers — review code before you run it.

latestvk977e85szzyppjsstg1heyw3m9832chg

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

📝 Clawdis
Binspython3
EnvSENSEAUDIO_API_KEY
Primary envSENSEAUDIO_API_KEY

Comments