cleanexpo/pi-dev-ops/plaud-read
Claude Code and agent skill by cleanexpo/pi-dev-ops
- community
Checking that the SKILL.md file is still in the repository.
Read the transcript, AI summary, notes, or download audio for a specific Plaud recording. Use when the user says 'show the transcript', 'summarize this', 'what was said', 'get audio', 'the notes from', or names a specific recording to dig into. Also covers extracting structured fields from a recording.
Install
npx vskill@latest install cleanexpo/pi-dev-ops/plaud-readSKILL.md
The same SKILL.md was published earlier as cleanexpo/pi-dev-ops/plaud-read.
plaud-read
Read [`plaud-shared`](../plaud-shared/SKILL.md) first.
When to use
- User names a specific recording (by name or ID) and wants to read its content.
- User asks for "transcript", "summary", "action items", "audio", "who said what", or a structured extraction ("action items, decisions, attendees").
- If the user did not specify a recording, hand off to
plaud-find(by topic) orplaud-browse(by recency) first.
Tool selection matrix
| User wants | Tool | Notes | |
|---|---|---|---|
| AI summary, TL;DR, action items | get_note | Returns Markdown; usually enough — try this before get_transcript | |
| Verbatim quotes, full dialogue | get_transcript | Timestamped; larger | |
| Audio download link | get_file then use presigned_url | Link expires in 24h | |
| Full metadata + availability flags | get_file | Check source_list / note_list populated before claiming content exists |
Structured extraction workflow
If the user provides a schema (e.g., {"action_items": [], "decisions": [], "attendees": []}):
- Call
get_notefirst — the AI summary usually already contains these fields. - Only call
get_transcriptif the summary is missing a required field. - Return JSON matching the user's schema. Mark any missing field with
nulland note why.
Common schemas:
- Sales:
{ "pain_points": [], "follow_ups": [], "deal_stage": "" } - Clinical:
{ "diagnoses": [], "medications": [], "next_appointment": "" } - Project:
{ "action_items": [], "decisions": [], "attendees": [] }
Output
- Transcripts: preserve
[MM:SS - MM:SS] Speaker: content. Do not reformat timestamps. - Summaries: render Markdown directly in the reply.
- Audio: print the URL and mention "expires in 24h".
Anti-patterns
- Do not call
get_transcriptspeculatively — it's the largest payload. - Do not paraphrase the AI summary unless the user asked; quote it verbatim.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills-library/skills/plaud-read/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/cleanexpo/pi-dev-ops/plaud-read)