Agent skill

Transcribe

by badlogic in badlogic/pi-skills

Local speech-to-text transcription on Apple Silicon macOS. An agent skill from badlogic/pi-skills.

MITAuto-check passedMedia & Creative

Install Transcribe

skills CLI
$ npx skills add badlogic/pi-skills --skill transcribe -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install badlogic/pi-skills transcribe --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/badlogic/pi-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/transcribe .claude/skills/transcribe && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
transcribe
GitHub stars
2.6k
Token cost
~264 tokens
SKILL.md length
87 words
Files
3
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Local speech-to-text transcription on Apple Silicon macOS. An agent skill from badlogic/pi-skills.

  • Tasks that involve Transcription
  • SKILL.md covers Usage, Output and Requirements
  • Runs Shell scripts from its folder; calls brew
  • Tasks that involve Video production

What it does

Transcribe is an agent skill from badlogic/pi-skills. Local speech-to-text transcription on Apple Silicon macOS. Supports wav directly and other audio formats via ffmpeg.

Its SKILL.md is about 260 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `transcribe.sh`).

It sits in Media & Creative, covering Transcription and Video production. It works with macOS and FFmpeg. The repository describes itself as: Skills for pi coding agent (compatible with Claude Code and Codex CLI). The licence is MIT.

When your agent uses it

  • Tasks that involve Transcription
  • Tasks that involve Video production

Example prompts

  • “/transcribe”

Requirements

  • A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit 90bb51c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • brew

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Transcribe loads about 264 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 87 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~264

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from badlogic/pi-skills at commit 90bb51c, republished under its MIT licence (© badlogic). 87 words, ~264 tokens.

Download SKILL.mdSave it as .claude/skills/transcribe/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
transcribe
description
Local speech-to-text transcription on Apple Silicon macOS. Supports wav directly and other audio formats via ffmpeg.

Transcribe

Local speech-to-text using parakeet-cpp-transcribe on Apple Silicon macOS.

Usage

bash
{baseDir}/transcribe.sh <audio-file>

The first run downloads the macOS arm64 binary from the latest badlogic/pibot GitHub release into the extension's ignored bin directory:

text
{extensionDir}/bin/parakeet-cpp-transcribe

({extensionDir} is the parent directory of this skill's {baseDir}.) The binary downloads its GGUF model automatically if missing.

Output

Plain text timestamped in 15 second chunks is written to stdout:

text
[00:00-00:15] transcript text
[00:15-00:30] more transcript text

Model/GGML diagnostic logs are written to stderr. Redirect stderr to hide them:

bash
{baseDir}/transcribe.sh <audio-file> 2>/dev/null

Requirements

  • Apple Silicon macOS only
  • curl and tar
  • ffmpeg for non-WAV input: brew install ffmpeg

© badlogic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in transcribe of badlogic/pi-skills.

  • SKILL.md
  • .gitignore
  • transcribe.sh

Open the folder on GitHubat commit 90bb51c

Compare with similar skills

Transcribe next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Transcribe compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Transcribe this skillbadlogic/pi-skills2.6k—~264Automated safety check: PassMIT
Video Clipping ReferenceRightNow-AI/openfang18k—~4.1kAutomated safety check: WarnApache-2.0
Open Editveedstudio/open-edit1.6k—~1.8kAutomated safety check: PassApache-2.0
Ffmpeg Skillkajisho5/ffmpeg-skill1.9k—~7.4kAutomated safety check: PassMIT
ShortsAgriciDaniel/claude-shorts218—~3.2kAutomated safety check: NotesMIT
Explain Videolimin112/min-skill362—~2.4kAutomated safety check: PassNone

Similar skills

  • Video Clipping Reference

    RightNow-AI/openfang

    Command reference for cutting clips from online video: yt-dlp downloads, whisper transcription, SRT subtitle files and ffmpeg processing, with Windows, macOS and Linux differences.

    18k GitHub stars~4.1k tokensUpdated 3 mo ago
    Media & CreativeAuto-check: warnings
  • Open Edit

    veedstudio/open-edit

    Video work with VEED's hosted services and a CLI toolkit — word-timed transcription, cutting, background removal, AI presenters, lipsync, any fal model, sound mixing, and a Chrome renderer for HTML…

    1.6k GitHub stars~1.8k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Ffmpeg Skill

    kajisho5/ffmpeg-skill

    Edit video and audio with local FFmpeg from natural-language requests: cut, trim, join, resize/reframe (9:16, 1:1), speed change, captions and subtitles (SRT/ASS, animated, karaoke), logos and text…

    1.9k GitHub stars~7.4k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • Shorts

    AgriciDaniel/claude-shorts

    Interactive longform-to-shortform video creator. An agent skill from AgriciDaniel/claude-shorts.

    218 GitHub stars~3.2k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Explain Video

    limin112/min-skill

    Build a narrated explainer video from a concept — discussion → structure → HTML slide deck → narration script → TTS voice → subtitles → background music → Playwright screen recording → ffmpeg…

    362 GitHub stars~2.4k tokensUpdated 15 days ago
    Media & CreativeAuto-check passed
  • Cassette Video Edit

    Cassette-Editor/oh-my-cassette

    Edit, trim, cut, caption, subtitle, reframe, combine, add background music to, or export video, audio, and image files through Cassette.

    157 GitHub starsUsed in 1 repo~3.4k tokens
    Media & CreativeAuto-check passed

More from badlogic/pi-skills

  • Brave Search

    badlogic/pi-skills

    Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.

    2.6k GitHub starsUsed in 6 repos~592 tokens
    Auto-check passed
  • Gccli

    badlogic/pi-skills

    Google Calendar CLI for listing calendars, viewing/creating/updating events, and checking availability.

    2.6k GitHub starsUsed in 1 repo~530 tokens
    Auto-check passed
  • Gdcli

    badlogic/pi-skills

    Google Drive CLI for listing, searching, uploading, downloading, and sharing files and folders.

    2.6k GitHub starsUsed in 1 repo~759 tokens
    Auto-check passed
  • Gmcli

    badlogic/pi-skills

    Gmail CLI for searching emails, reading threads, sending messages, managing drafts, and handling labels/attachments.

    2.6k GitHub starsUsed in 1 repo~470 tokens
    Auto-check passed
  • Youtube Transcript

    badlogic/pi-skills

    Fetch transcripts from YouTube videos for summarization and analysis.

    2.6k GitHub starsUsed in 1 repo~179 tokens
    Auto-check passed

Works with

Questions about Transcribe

What does Transcribe do?

Local speech-to-text transcription on Apple Silicon macOS. An agent skill from badlogic/pi-skills. Transcribe is an agent skill from badlogic/pi-skills. Local speech-to-text transcription on Apple Silicon macOS.

When should I use Transcribe?

Transcribe fits situations like: tasks that involve Transcription; tasks that involve Video production.

How do I install Transcribe in Claude Code?

Run `npx skills add badlogic/pi-skills --skill transcribe -a claude-code`. Or copy the skill folder (transcribe in badlogic/pi-skills) into .claude/skills/transcribe in your project. Claude Code loads it when a task matches its description.

How do I install Transcribe in Codex?

Run `npx skills add badlogic/pi-skills --skill transcribe -a codex`. Or copy the skill folder (transcribe in badlogic/pi-skills) into .agents/skills/transcribe in your project. Codex loads it when a task matches its description.

Can I use Transcribe in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add badlogic/pi-skills --skill transcribe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/transcribe, .gemini/skills/transcribe, .github/skills/transcribe and .opencode/skills/transcribe in your project.

What does Transcribe need to run?

Going by SKILL.md and its folder, Transcribe needs a shell for the scripts in its folder and the command-line tools its instructions call (brew). Our summary lists: A Bash shell.

Does Transcribe access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Transcribe safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Transcribe use?

Transcribe is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Transcribe use?

About 264 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Transcribe?

Skills that share tags, products or a category with Transcribe: Video Clipping Reference (RightNow-AI/openfang, 18k stars), Open Edit (veedstudio/open-edit, 1.6k stars), Ffmpeg Skill (kajisho5/ffmpeg-skill, 1.9k stars) and Shorts (AgriciDaniel/claude-shorts, 218 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Transcribe?

badlogic (a GitHub user) maintains it in badlogic/pi-skills, which has 2,592 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 6, 2026.

Source: badlogic/pi-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.