Help us improve
Share bugs, ideas, or general feedback.
From plaud
Guide for finding and browsing Plaud recordings using metadata filters. Use when the user asks to list, find, filter, or browse their recordings by date, source type, title, or transcription status.
npx claudepluginhub harshav167/plaud-plugin --plugin plaudHow this skill is triggered — by the user, by Claude, or both
Slash command
/plaud:recording-searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Find and browse Plaud AI recordings by metadata: title, date, source type, and transcription status.
Lists recent meetings and voice memos from local files, sorted newest-first. Supports filtering by type and custom limits.
Searches and retrieves meeting transcripts from Fireflies.ai and Google Drive with full text, speaker labels, timestamps, summaries, keywords, and action items. Triggers on transcript search, meeting history, call recordings, or Fireflies queries.
Queries Fireflies.ai for meeting transcripts from Zoom, Teams, Google Meet; searches by keyword/date, extracts action items, and retrieves summaries.
Share bugs, ideas, or general feedback.
Find and browse Plaud AI recordings by metadata: title, date, source type, and transcription status.
find_recordingsBrowse and filter recordings. Returns a list with metadata previews.
| Parameter | Type | Default | Description |
|---|---|---|---|
query | string | null | Partial title match (case-insensitive) |
source | "call" | "meeting" | "desktop" | null | Filter by recording type |
transcribed | bool | null | Filter by transcript availability |
since | string | null | Relative ("7d", "30d") or absolute ("2026-01-15") |
until | string | null | Same format as since |
limit | int | 20 | Max results (capped at 100) |
Response fields per recording:
| Field | Description |
|---|---|
id | 32-char hex file ID (use for all other tools) |
title | Recording title |
source | call, meeting, or desktop |
duration | Human-readable ("1h 52m") |
recorded | Human-readable date |
has_transcript | Whether transcript exists |
has_summary | Whether AI summary exists |
get_recordingFull metadata for a single recording.
| Parameter | Type | Description |
|---|---|---|
file_ref | string | Required. File ID, short prefix, or row number |
Returns all find_recordings fields plus available_content, transcript_cached, audio_cached, indexed status, ai_headline, and ai_keywords.
get_audio_urlGet a presigned download URL for the recording audio.
| Parameter | Type | Description |
|---|---|---|
file_ref | string | Required. File ID, short prefix, or row number |
Returns a presigned S3 URL valid ~5 minutes. Present to user immediately -- it expires fast.
All tools accepting file_ref support three formats:
| Format | Example | Description |
|---|---|---|
| Full ID | 4f757af256ecba4fab502739c122dc78 | Exact 32-char hex match |
| Short prefix | 4f75 | Unambiguous prefix of any file ID |
| Row number | 3 | 1-based index from most recent find_recordings |
Best practice: Call find_recordings first, then use the id field directly.
Browse recent recordings:
find_recordings(limit=10)
Find meetings from the last week:
find_recordings(source="meeting", since="7d")
Find untranscribed recordings:
find_recordings(transcribed=false)
Search by title keyword:
find_recordings(query="standup")
Check a recording's full status (cached, indexed):
get_recording(file_ref="4f75")
Get audio download link:
get_audio_url(file_ref="4f75")
find_recordings(limit=10)find_recordings(source="meeting", since="7d")get_recording(file_ref="<id>") for full detailsget_audio_url(file_ref="<id>")source="call" + since="30d" + query="client"get_recording to check transcript_cached and indexed status before transcribing or searchingnext_steps field guiding your next action -- follow it