agentleFS
Sign inStart free
DeiblerDeibler/edmund-harness/skills/voice-memo/SKILL.md

voice-memo

Skill24 starsChanged 2 months agoMITView on GitHub

Reply with a spoken audio clip, or transcribe incoming voice notes.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the user asks for a voice memo, wants to hear something, or the moment calls for tone.

    line 13
  2. Very specific:

    When the user sends an audio attachment, check the envelope's Attachments line first — voice notes usually arrive pre-transcribed ([voice …

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

voice-memo

Reply with audio

  1. generate_audio(text, voice?, async: true) — TTS speech (always pass async: true); the file AUTO-DELIVERS to the user, no follow-up send_attachment.
  2. Voices: alloy / echo / fable / onyx / nova / shimmer (model-dependent). list_audio_models() if the user wants a specific style.

Use when the user asks for a voice memo, wants to hear something, or the moment calls for tone. Keep the spoken text shorter than you would a typed reply — people listen impatiently.

Handle incoming voice notes

When the user sends an audio attachment, check the envelope's Attachments line first — voice notes usually arrive pre-transcribed ([voice transcript: "…"]). If not, call transcribe_audio(file_path=<path from the attachment list>) before responding. Treat the transcript as the user's message. (Videos get the same treatment automatically; for everything else video, read_skill("video").)

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.

Check your setup, free