voice-fetch
Skill2 starsChanged 58 days agoLicence not identifiedView on GitHub
Front door for local audio going into the wiki: whenever a voice memo or audio file (m4a, mp3, wav, …) should be ingested, this transcribes it on-device via WhisperKit (CoreML/Neural Engine — no cloud, no credentials), lands a wiki-ingest-ready doc (source_type: transcript) in .raw/audio/, then hands off to ingest. An audio file has no text for ingest to read, so a bare ingest of the path would miss everything — route ANY audio-file path aimed at ingest here first, including audio the user dropped into .raw/ directly. Triggers on: voice-fetch, /voice-fetch, transcribe this, transcribe <path>, ingest this audio, ingest <anything>.m4a/.mp3/.wav, add this voice memo to my wiki, ingest this recording, voice memo to wiki, transcribe and ingest, add this m4a, an audio file path to add/ingest, save this recording to the wiki, there's an audio file in .raw.
- Installs packages
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/techtrip-secondbrain.mdcCursor rule
- brain-dumpSkill
- code-fetchSkill
- mode-fitSkill
- new-ideaSkill
- notebooklm-ingestSkill
- secondbrain-doctorSkill
- secondbrainSkill
- x-fetchSkill
- yt-fetchSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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
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.