agentleFS
gaotiexinqugaotiexinqu/OneResearchClaw/.cursor/skills/meeting-audio-grounding/SKILL.md

meeting-audio-grounding

Skill444 starsChanged 7 months agoMITView on GitHub

Convert a meeting audio file into a transcript bundle, then use meeting-grounding to produce structured meeting grounding outputs.

The file

Show its rules and text

We split this skill into the rules it gives an agent

20 rules. About 0 are common, 15 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈15

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 19
  2. Distinctive:

    Do not use this skill when:

    line 25
  3. Distinctive:

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

    line 44
  4. Distinctive:

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

    line 71
  5. Distinctive:

    always writing the meeting-level:

    line 98
  6. Very specific:

    Run the existing scripts/run.sh entrypoint for this skill.

    line 109
  7. Very specific:

    Read transcript/meeting_transcript.txt as the primary grounding evidence.

    line 115
  8. Very specific:

    Always save the meeting-level structured note to grounded.md inside the same bundle directory.

    line 117
  9. Distinctive:

    If the transcript clearly contains multiple independent topics, also save:

    line 118
  10. Distinctive:

    Do not stop after confirming that the transcript bundle exists.

    line 121
  11. Very specific:

    If topic children are created, each child grounded note must also follow the same meeting-grounding schema.

    line 127
  12. Distinctive:

    Do not invent a new schema here.

    line 129
  13. Distinctive:

    Do not implement a new ASR pipeline.

    line 133
  14. Distinctive:

    Do not implement a new meeting summarizer.

    line 134
  15. Distinctive:

    Do not directly summarize the raw audio without first running the existing workflow.

    line 135
  16. Distinctive:

    Treat the transcript as the primary evidence.

    line 138
  17. Distinctive:

    Keep the workflow simple and stable.

    line 139
  18. Distinctive:

    If the input audio file does not exist, fail clearly.

    line 143
  19. Very specific:

    If meeting_transcript.txt is not produced, fail clearly.

    line 144
  20. Distinctive:

    Do not pretend the task succeeded if only part of the workflow completed.

    line 145

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

grounded.md must be a real grounding note. It must not remain a placeholder scaffold.

Required Agent Workflow

  1. Run the existing scripts/run.sh entrypoint for this skill.
  2. Confirm that the bundle exists and that these files are present:
    • extracted.md
    • extracted_meta.json
    • audio/
    • transcript/meeting_transcript.txt
  3. Read transcript/meeting_transcript.txt as the primary grounding evidence.
  4. Reuse the existing meeting-grounding skill on that transcript.
  5. Always save the meeting-level structured note to grounded.md inside the same bundle directory.
  6. If the transcript clearly contains multiple independent topics, also save:
    • topic_manifest.json
    • child_outputs/topic_xx/grounded.md
  7. Do not stop after confirming that the transcript bundle exists.

Output Format

The final grounded.md must follow the existing meeting-grounding schema exactly.

If topic children are created, each child grounded note must also follow the same meeting-grounding schema.

Do not invent a new schema here.

Instructions

  • Do not implement a new ASR pipeline.
  • Do not implement a new meeting summarizer.
  • Do not directly summarize the raw audio without first running the existing workflow.
  • Reuse the existing audio_structuring skill for transcription.
  • Reuse the existing meeting-grounding skill for transcript grounding.
  • Treat the transcript as the primary evidence.
  • Keep the workflow simple and stable.

Failure Handling

  • If the input audio file does not exist, fail clearly.
  • If meeting_transcript.txt is not produced, fail clearly.
  • Do not pretend the task succeeded if only part of the workflow completed.

Example Invocation

/meeting-audio-grounding

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.