メニュー
Export a transcript (or any pipeline output) by emailing it, uploading to Google Drive, or copying to clipboard. Use when the user asks to send, email, upload, save to Drive, or copy a transcript.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Transcribe a podcast episode and produce two outputs in one pass — (1) the raw API transcript exactly as the provider returned it, and (2) a podcast-formatted reading version with filler words removed, section headers added, and speaker labels preserved. Use whenever the user provides a podcast audio file or says "transcribe this podcast".
Diagnose-and-treat workflow for very messy recordings where the standard preprocessor isn't enough. Generates a spectrogram, identifies problematic frequency bands (AC hum, rumble, narrow-band whines, broadband hiss, clipping), and proposes targeted ffmpeg filters. ONLY use when the user explicitly invokes it — the normal pipeline runs `preprocess-for-transcription` directly and skips diagnostic work. Trigger phrases the user might use — "this audio is messy", "transcription failed because of noise", "fix this rough recording", "the audio is bad and the transcript is garbage".
Remove background noise from an audio file. Cloud providers (Auphonic default, ElevenLabs, Dolby.io) or local (DeepFilterNet ML, ffmpeg afftdn non-ML). Use when the user asks to denoise, clean up noise, remove hum/hiss, or enhance speech audio before transcription.
Prepare audio for transcription — format normalise (mono/16kHz/opus), loudness normalise (EBU R128), and collapse long silences (silero-vad). Optional denoise pass. Use before sending to AssemblyAI or any ASR for cleaner results, smaller uploads, and lower cost. Use when the user asks to "preprocess audio", "prep for transcription", "clean up a recording before sending it", or just hands over a raw voice memo to be transcribed.
Apply a stylistic / formatting transformation to a transcript using a named prompt from the user's Text-Transformation-Prompt-Library (206 transformations covering blog outlines, briefs, business correspondence, analysis documents, meeting notes, and more). Use when the user asks to "convert this to <style>", "format like a <type>", or names a specific transformation. Fetches the catalog on demand and caches it; never commits the prompts into this plugin.
Mine a transcript for durable personal context — facts about the speaker (location, role, projects, preferences, relationships, ongoing work) — and write them to a context file for later reuse. De-duplicates against existing context so the same facts aren't re-extracted on every memo. Use when the user wants to build a knowledge base from voice memos, or asks to "pull out context from this".
| name | export-transcript |
| description | Export a transcript (or any pipeline output) by emailing it, uploading to Google Drive, or copying to clipboard. Use when the user asks to send, email, upload, save to Drive, or copy a transcript. |
Send a transcript file (or post-processed variant) to a destination.
Use the email-skills skill set (send-personal-email or send-business-email).
Prompt user for:
When attaching the transcript file, the same staging rule as Drive applies — the GWS MCP runs on ubuntuvm and can't read workstation paths. Stage via MinIO (python3 ~/.claude/lib/minio-stage.py …) and pass the presigned URL as the attachment's sourceUrl. The send-* email skills cover this.
Use the gws-personal MCP. The GWS MCP runs on ubuntuvm — it cannot read workstation paths like /home/daniel/.... The canonical upload path is MinIO staging + sourceUrl:
python3 ~/.claude/lib/minio-stage.py /path/to/transcript.md --expires 3600
# → {"url":"http://10.0.0.4:9100/mcp-staging/<uuid>/transcript.md?X-Amz-...",...}
create_folder if the user specified a new folder name (or reuse an existing one via search).mcp__jungle-personal__gws-personal__upload_file with sourceUrl: <presigned URL> and parents: [<folder-id>]. Do not pass a workstation file_path/sourcePath — that param is ubuntuvm-local only.create_google_doc with the content inline instead.share_file if the user wants a shareable link.Report back the Drive webViewLink.
Do NOT reach for rclone, scp, gcloud, gdrive, direct Drive API curl, or any other workaround. MinIO staging + sourceUrl is the only supported route from this workstation; the staging bucket (mcp-staging on 10.0.0.4:9100) self-cleans after 1 day.
Copy file contents to clipboard: wl-copy < FILE (Wayland) or xclip -selection clipboard < FILE (X11). Detect which is available.
For PDF or binary, warn that clipboard export isn't meaningful and suggest email/Drive instead.
Any file produced by this plugin: .raw.txt, .cleaned.md, .structured.md, .blog.md, .summary.md, .notes.md, .combined.md, .combined.pdf.
Also accept arbitrary paths the user supplies.
Allow chaining: "email it and upload to Drive" should do both.