OneResearchClaw: Skill for Cursor

Meeting Audio Grounding

Convert a meeting audio file into structured meeting grounding outputs by:

1. reusing the existing audio_structuring skill to produce meeting_transcript.txt
2. reusing the existing meeting-grounding skill to turn that transcript into meeting grounding outputs

This skill is for meeting audio inputs where the primary information comes from speech. It is intentionally transcript-first.

When to Use

Use this skill when:

• the input is a meeting recording or discussion audio file
• the main information is expected to come from spoken content
• you want to reuse the existing audio transcription and meeting grounding workflow

Do not use this skill when:

• the task is only to produce a transcript without meeting grounding
• the task is to write a polished final report directly from raw audio
• the input is not a meeting/discussion recording

Input

A single meeting audio file.

Typical examples:

• .mp3
• .wav
• .m4a
• .webm
• .aac
• .ogg

All these formats are supported via WhisperX's ffmpeg backend.

Optional input:

• transcription_language: language code such as en or zh

Output Bundle

For each input audio file, create one bundle directory:

data/grounded_notes/<ground_id>/

Inside that bundle, the expected outputs are always:

<bundle_dir>/
├─ extracted.md
├─ extracted_meta.json
├─ grounded.md
├─ audio/
│  └─ meeting_audio<original_ext>
└─ transcript/
   └─ meeting_transcript.txt

If the meeting contains multiple independent topics that should be researched separately downstream, the bundle may also contain:

<bundle_dir>/
├─ topic_manifest.json
└─ child_outputs/
   ├─ topic_01/
   │  └─ grounded.md
   ├─ topic_02/
   │  └─ grounded.md
   └─ ...

Important separation of responsibilities

• scripts/run.sh is responsible for:
  • preparing the bundle directory
  • ensuring the input audio is present under audio/
  • calling the existing audio_structuring skill
  • creating the bundle files:
    • audio/meeting_audio<original_ext>
    • transcript/meeting_transcript.txt
    • extracted.md
    • extracted_meta.json
• The agent is responsible for:
  • reading the transcript bundle
  • applying the existing meeting-grounding skill
  • always writing the meeting-level:
    • grounded.md
  • and, when appropriate, also writing:
    • topic_manifest.json
    • child_outputs/topic_xx/grounded.md