sunflowermm/office-transcribe
skills/standard/office-transcribe/SKILL.md
音频/视频转文字、字幕时间轴、说话人分段；Whisper/faster-whisper，转写后接纪要
$ install --global
skillsauthnpx skillsauth add sunflowermm/XRK-AGT office-transcribeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 10, 2026, 4:36 AM13.4s1 file scanned
SKILL.md
- name:
- office-transcribe
- description:
- 音频/视频转文字、字幕时间轴、说话人分段；Whisper/faster-whisper，转写后接纪要
何时使用
会议录音、语音备忘、采访、.mp3 .wav .m4a 转文字、要 SRT 字幕。
流程
- 音频放入工作区（或用户提供路径）
run执行转写脚本，输出.txt/.srt/.json- 长音频：按
office-meeting出纪要；短备忘：摘要 5 条
推荐：faster-whisper（本地）
from faster_whisper import WhisperModel
model = WhisperModel("large-v3", device="cpu", compute_type="int8")
segments, info = model.transcribe("meeting.mp3", language="zh", vad_filter=True)
lines = []
for seg in segments:
lines.append(f"[{seg.start:.1f}s-{seg.end:.1f}s] {seg.text.strip()}")
open("transcript.txt", "w", encoding="utf-8").write("\n".join(lines))
pip install faster-whisper
# 可选 GPU：device=cuda
说话人分段
Whisper 原生无 diarization；需 pyannote 等额外模型时先说明环境与授权。
SRT 字幕
def fmt(t):
h, r = divmod(int(t), 3600); m, s = divmod(r, 60); ms = int((t % 1) * 1000)
return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}"
# 每 segment 写一条 SRT 块
禁止
- 不声称已转写除非输出文件存在
- 敏感录音提醒用户脱敏后再写入
memory/
缺环境
无 faster-whisper / 无 run → 请用户提供文字稿或外部转写结果；见 office-env-setup
Related Skills
sunflowermm/answer-format
development
VerifiedTrustedCommunity
统一回复版式：短、结构化、可复制；减少空话
145SKILL.mdUpdated Jun 12, 2026
sunflowermm/agent-tools
tools
VerifiedTrustedCommunity
MCP 工具地图：默认工作流、web_search、何时启用 desktop/browser/memory
145SKILL.mdUpdated Jun 12, 2026
sunflowermm/agent-search
development
VerifiedTrustedCommunity
检索栈：web_search（13 提供商 + parallel-free 免费通道）、web_fetch、与 office-research 分工
145SKILL.mdUpdated Jun 12, 2026
sunflowermm/agent-memory
data-ai
VerifiedTrustedCommunity
工作区 Markdown 记忆 + memory 工作流向量记忆的使用边界
145SKILL.mdUpdated Jun 12, 2026