Features
Use your connected model to extract summaries, decisions, actions and open questions from meeting text. The script checks source quotes, owners and dates, then exports meeting.md, meeting.json and tasks.csv. Unstated owners or dates remain marked unknown.
Usage examples
After installation, send any example below to your AI. Include the files or URLs it refers to.
Turn this meeting text into a summary, decisions and actions, each with source quotations.
Extract owners and deadlines from the meeting notes, marking unspecified values for confirmation.
Export this meeting's actions as tasks.csv and save Markdown minutes.
Advanced usage: run in a terminal
These commands are for manual execution in the terminal on the computer or server running OpenClaw. For everyday use, send one of the chat examples above.
Replace these placeholders with actual paths before running:
SKILL_DIRECTORY: the installed Skill folder.NEW_REPORT_DIRECTORY: a new report directory.TRANSCRIPT.txt: the meeting transcript file.NEW_EVIDENCE_DIRECTORY: a new source-evidence directory.EVIDENCE_FILE: the evidence-file path returned by the previous step.EXTRACTION_JSON: the extraction JSON completed from the template.
Prepare numbered evidence:
node "SKILL_DIRECTORY/scripts/meeting.mjs" prepare --input "TRANSCRIPT.txt" --out "NEW_EVIDENCE_DIRECTORY"
Have OpenClaw fill the returned extraction template, then export:
node "SKILL_DIRECTORY/scripts/meeting.mjs" render --evidence "EVIDENCE_FILE" --draft "EXTRACTION_JSON" --out "NEW_REPORT_DIRECTORY"
Use actual input paths and new output folders. Try samples/sample-input.txt first.