agentleFS
iwesysiwesys/IWE/.claude/skills/transcribe/SKILL.md

transcribe

Skill0 starsChanged 25 days agoMITView on GitHub

Transcribe audio/video files via MLX Whisper (Apple Silicon). Usage: /transcribe path/to/file.mp3

  • Deletes or force-pushes
  • Installs packages

49 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use spreadsheet, done and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JetBrainsSkill

    spreadsheet

    Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) with formula-aware workflows, cached recalculation, and visual review.

    Also in 3 projects that use this

  • robzolkosSkill

    done

    Reset the working directory for the next task by ensuring no uncommitted changes exist, then switching to the main branch and pulling latest.

    Also in 3 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 3 projects that use this

  • AnthropicSkill

    onboarding

    Generate an onboarding checklist and first-week plan for a new hire. Use when someone has a start date coming up, building the pre-start task list (accounts, equipment, buddy), scheduling Day 1 and Week 1, or setting 30/60/90-day goals for a new team member.

    Also in 3 projects that use this

  • NVIDIASkill

    deep-research

    Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.

    Also in 3 projects that use this

  • MicrosoftSkill

    mcp-builder

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If this fails (broken or missing), recreate it:

    line 37
  2. Very specific:

    Use large-v3: the script selects the model source (see "Locations").

    line 47
  3. Distinctive:

    If the language is not English, the user will specify it, or the script will detect it automatically.

    line 55
  4. Very specific:

    If the user requests saving, write the output to a file alongside the source: <filename>.txt.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “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

Audio/Video Transcription

Transcription via MLX Whisper on Apple Silicon. Runs locally, no cloud required.

Locations

  • Local model (optional): ~/.local/share/mlx-whisper/mlx_models/large-v3 — the Skill and its installation do not create this directory; it is used only when a model is present there (i.e., config.json exists)
  • Venv: ~/.local/share/mlx-whisper/.venv-whisper/
  • Model: large-v3 (high accuracy, ~3 GB). The script selects the source in the following order: (1) the environment variable IWE_WHISPER_MODEL (a directory path or Hugging Face repository ID), if set and non-empty (a whitespace-only value is treated as empty; the value is passed through without validation — this is an explicit user choice); (2) the local directory from the first line above, if a model is present there (config.json exists); (3) otherwise the Hugging Face repository mlx-community/whisper-large-v3-mlx — mlx_whisper downloads it on the first transcription run into ~/.cache/huggingface/hub/ (network required, ~3 GB) and uses the cache on subsequent runs

Instructions for Claude

Step 1: Check the venv

~/.local/share/mlx-whisper/.venv-whisper/bin/python -c "import mlx_whisper; print('ok')" 2>/dev/null

If this fails (broken or missing), recreate it:

rm -rf ~/.local/share/mlx-whisper/.venv-whisper
python3 -m venv ~/.local/share/mlx-whisper/.venv-whisper
~/.local/share/mlx-whisper/.venv-whisper/bin/pip install mlx-whisper

Step 2: Determine the file and model

  • The Skill argument is the path to the file. If not provided, ask the user.
  • Use large-v3: the script selects the model source (see "Locations"). Only the user may override this via IWE_WHISPER_MODEL — do not change it on your own.

Step 3: Transcription

bash "$IWE_SCRIPTS/route-task.sh" --skill transcribe --args "<path_to_file>"

If the language is not English, the user will specify it, or the script will detect it automatically.

Step 4: Result

  • Display the text to the user.
  • If the user requests saving, write the output to a file alongside the source: <filename>.txt.
  • For long files (>30 min), warn the user that transcription may take several minutes.

Supported formats

mp3, m4a, wav, flac, ogg, mp4, mkv, webm — any format supported by ffmpeg.

<!-- USER-SPACE --><!-- /USER-SPACE -->

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.