Documents

plaud-spoken-field-notes-to-a-structured-sheet

Try it

Plaud Spoken Field Notes to a Structured Sheet: Turns a spoken site visit into a filled-in spreadsheet row, so measurements and specs never get typed up twice. Built for anyone who dictates structured details on the job rather than writing them down: window and flooring measurements, equipment specs, inspection findings, punch lists, service call notes. Say the details out loud in the same order each visit (client, room, width, drop, colour, notes) and the workflow reads each new Plaud recordin.

What it does

Plaud Spoken Field Notes to a Structured Sheet: Turns a spoken site visit into a filled-in spreadsheet row, so measurements and specs never get typed up twice. Built for anyone who dictates structured details on the job rather than writing them down: window and flooring measurements, equipment specs, inspection findings, punch lists, service call notes. Say the details out loud in the same order each visit (client, room, width, drop, colour, notes) and the workflow reads each new Plaud recordin.

The skill document

Plaud Spoken Field Notes to a Structured Sheet

Freshness

Last updated: 2026-07-26.

If the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.

What This Workflow Does

Turns a spoken site visit into a filled-in spreadsheet row, so measurements and specs never get typed up twice. Built for anyone who dictates structured details on the job rather than writing them down: window and flooring measurements, equipment specs, inspection findings, punch lists, service call notes. Say the details out loud in the same order each visit (client, room, width, drop, colour, notes) and the workflow reads each new Plaud recording, pulls its transcript, extracts only the values actually spoken, and appends them as one row to your Google Sheet under whatever column headers you have already set up. Values are never inferred: if a measurement was not said, the cell is left empty and flagged in the run summary rather than guessed, because a fabricated number on a quote is worse than a blank one. Recordings that are not field dictations (meetings, personal memos, ambient audio) are logged as skipped and produce no row. A Processed tab records every recording id so the workflow can run on a schedule without duplicating rows. Pair it with your own quote template and the spreadsheet row becomes the quote.

Required Setup

  • AgentPMT overview: ../what-is-agentpmt.
  • Account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup.

Core AgentPMT setup skills:

  • What AgentPMT is: ../what-is-agentpmt
  • AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup

skills.sh install script:

npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup

Workflow Session Management

Call AgentPMT-Workflow-Skills with start_workflow before the first step and end_workflow after the final step.

{"action":"start_workflow","skill_id":"plaud-spoken-field-notes-to-a-structured-sheet"}

{"action":"end_workflow","skill_id":"plaud-spoken-field-notes-to-a-structured-sheet","rating":5,"comment":"completed"}

Workflow Process

  1. Get User Timezone and Date
    • Tool product: Get Users Current Time / Date.
    • Tool skill: ../get-users-current-time-date.
    • ClawHub page: https://clawhub.ai/agentpmt/get-users-current-time-date.
    • skills.sh install: npx skills add AgentPMT/agent-skills --skill get-users-current-time-date.
    • Marketplace: https://www.agentpmt.com/marketplace/user-timezone-datetime.
    • Tool instructions: Get the user's current local date, time, timezone and UTC offset. Everything downstream, the requested window, the recording timestamps and any spoken relative date, is resolved against this and never against the server clock.
  2. Ask for the Recording Window
    • Prompt: Establish the exact window of recordings this run covers, in the user's own timezone.
  3. List Plaud Recordings
    • Tool product: Plaud.
    • Tool skill: ../plaud.
    • ClawHub page: https://clawhub.ai/agentpmt/plaud.
    • skills.sh install: npx skills add AgentPMT/agent-skills --skill plaud.
    • Marketplace: https://www.agentpmt.com/marketplace/plaud.
    • Tool instructions: Call list_files with the widened UTC date_from and date_to from the previous step. Plaud's timestamps are inconsistent and must be handled deliberately: the name field carries the recording's LOCAL time (for example '2026-07-25 19:53:50') while start_at and created_at are UTC written as naive strings with no Z and no offset (the same recording reads '2026-07-25T23:53:50'). Treat start_at as UTC, convert it into the user's timezone, and only then decide whether the recording falls inside the requested local window. An evening local recording carries the next day's UTC date, so comparing the raw string silently misfiles it. Display and log times in the user's local timezone. Then drop any recording id already in the Processed tab so a scheduled run never repeats work.
  4. Each New Recording
    • Iterate over the configured collection, then continue through the connected workflow path.
  5. Fetch Transcript
  6. Summarize the Run
    • Prompt: Report what was captured this run so the user can spot a bad extraction before acting on it.
  7. Extract Spoken Fields
    • Prompt: Turn a spoken site-visit dictation into one structured row matching the column headers of the target sheet.
  8. Append Row to Sheet
    • Tool product: Google Sheets.
    • Tool skill: ../google-sheets.
    • ClawHub page: https://clawhub.ai/agentpmt/google-sheets.
    • skills.sh install: npx skills add AgentPMT/agent-skills --skill google-sheets.
    • Marketplace: https://www.agentpmt.com/marketplace/google-sheets-api.
    • Tool instructions: Append the extracted row to the data tab at the true table end, writing any timestamp in the user's local timezone. Then log the recording id to the Processed tab so it is never handled twice. Skipped recordings are logged to Processed with their reason and no data row.

Tool Skill Links

AgentPMT Reference

Related skills

plaud-recordings-to-google-drive-sync

Plaud Recordings to Google Drive Sync: Automatically backs up your Plaud recordings to Google Drive and keeps a tracking spreadsheet in Google Sheets. Each time you run this workflow, it downloads any new recordings from your Plaud account to a "Plaud Recordings" folder in Drive, creates a transcript for each recording (using Plaud's built-in transcripts when available, or automatic speech-to-text otherwise), saves the transcript alongside the audio file, identifies what each recording is about.

plaud-recordings-to-google-calendar-events

Plaud Recordings to Google Calendar Events: Puts the meetings you agree to out loud straight onto your Google Calendar, without Zapier in the middle. Plaud's own app has no Calendar integration, so this closes that gap directly: each new recording is scanned, the transcript pulled, and any genuine scheduling commitment spoken in it ("let's do Tuesday at 3", "I'll come back out Thursday morning") is extracted with the relative date resolved against the recording's own date and your timezone. Eac.

1 installs

one-plaud-recording-several-differently-formatted-summaries

One Plaud Recording, Several Differently Formatted Summaries: Gets you past the one-template-per-recording ceiling. The Plaud app applies a single AutoFlow template to a recording, so if you want a short recap for yourself, a decisions-only version for the people who missed it, and a clean action list for your task manager, you are re-running or rewriting by hand. This workflow reads the transcript once and produces every format you have defined in a single pass: you list the output formats you.

1 installs

plaud-transcripts-corrected-with-your-own-terminology-glossary

Plaud Transcripts Corrected With Your Own Terminology Glossary: Fixes the words your transcription keeps getting wrong, by giving the pipeline your vocabulary instead of hoping a bigger model guesses right. Every speech model mangles terms it has never seen: cell line and reagent names, drug and device names, case and matter numbers, part numbers, local spelling and number conventions, team and client names. Swapping to a different model does not fix this, because none of them have your terms e.

1 installs

narrated-walkthrough-to-a-numbered-sop-document

Narrated Walkthrough to a Numbered SOP Document: Turns talking through a job out loud into a written, numbered standard operating procedure. Built for the people who actually know the equipment and have no time to write documentation: maintenance and facilities teams, field service, manufacturing, labs, franchise operations, and any owner trying to get a process out of their own head before handing it over. Walk the machine or the task and narrate it, saying the step number out loud as you go.

1 installs

Speak AI

Connect an agent to the Speak AI MCP server with 113 tools, 5 resources, and 3 prompts for transcription and analysis.

32 installs