MatClaw: Skill for Claude Code

.claude/skills/use-local-whisper/SKILL.md

use-local-whisper is a skill for Claude Code from DingyangLyu/MatClaw. It costs 46 tokens per session (1,184 once invoked), scanned A, a copy of use-local-whisper, Apache-2.0.

Instructions for switching WhatsApp voice transcription from OpenAI's Whisper service to whisper.cpp running locally on Apple Silicon. Transcription converts spoken audio into text.

In plain words
What is it for?
Use it to configure local WhatsApp audio transcription with whisper.cpp, ffmpeg, and a downloaded speech model. It currently covers WhatsApp only and requires the voice-transcription setup first.
Why use it?
It keeps transcription on the device, so this setup does not need an API key, network access, or per-use service costs.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is DingyangLyu/MatClaw's own configuration. It tells Claude Code how to work on MatClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MatClaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DingyangLyu/MatClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DingyangLyu/MatClaw/main/.claude/skills/use-local-whisper/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/DingyangLyu/MatClaw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for use-local-whisper

README.md
[![agentmods](https://agentmods.dev/badge/skills/dingyanglyu/matclaw/use-local-whisper/github.svg)](https://agentmods.dev/skills/dingyanglyu/matclaw/use-local-whisper)
Your own site
<a href="https://agentmods.dev/skills/dingyanglyu/matclaw/use-local-whisper"><img src="https://agentmods.dev/badge/skills/dingyanglyu/matclaw/use-local-whisper/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for use-local-whisper

Your own site · 80×15
<a href="https://agentmods.dev/skills/dingyanglyu/matclaw/use-local-whisper"><img src="https://agentmods.dev/badge/skills/dingyanglyu/matclaw/use-local-whisper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 84% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.01184
Opus 5 $0.00023 $0.00592
Sonnet 5 $0.00009 $0.00237
Haiku 4.5 $0.00005 $0.00118

Measured 10d ago against content hash e3a08f4ae15a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

use-local-whisper scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (modify/src/transcription.ts, tests/use-local-whisper.test.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -L -o data/models/ggml-base.bin "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin"
Origin

This is a copy

84% identical to use-local-whisper — 44 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/use-local-whisper/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Local Whisper

Switches voice transcription from OpenAI's Whisper API to local whisper.cpp. Runs entirely on-device — no API key, no network, no cost.

Channel support: Currently WhatsApp only. The transcription module (src/transcription.ts) uses Baileys types for audio download. Other channels (Telegram, Discord, etc.) would need their own audio-download logic before this skill can serve them.

Note: The Homebrew package is whisper-cpp, but the CLI binary it installs is whisper-cli.

Prerequisites

  • voice-transcription skill must be applied first (WhatsApp channel)
  • macOS with Apple Silicon (M1+) recommended
  • whisper-cpp installed: brew install whisper-cpp (provides the whisper-cli binary)
  • ffmpeg installed: brew install ffmpeg
  • A GGML model file downloaded to data/models/

Phase 1: Pre-flight

Check if already applied

Read .matclaw/state.yaml. If use-local-whisper is in applied_skills, skip to Phase 3 (Verify).

Check dependencies are installed

whisper-cli --help >/dev/null 2>&1 && echo "WHISPER_OK" || echo "WHISPER_MISSING"
ffmpeg -version >/dev/null 2>&1 && echo "FFMPEG_OK" || echo "FFMPEG_MISSING"

If missing, install via Homebrew:

brew install whisper-cpp ffmpeg

Check for model file

ls data/models/ggml-*.bin 2>/dev/null || echo "NO_MODEL"

If no model exists, download the base model (148MB, good balance of speed and accuracy):

mkdir -p data/models
curl -L -o data/models/ggml-base.bin "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin"

For better accuracy at the cost of speed, use ggml-small.bin (466MB) or ggml-medium.bin (1.5GB).

Phase 2: Apply Code Changes

npx tsx scripts/apply-skill.ts .claude/skills/use-local-whisper

This modifies src/transcription.ts to use the whisper-cli binary instead of the OpenAI API.

Validate

npm test
npm run build

Phase 3: Verify

Ensure launchd PATH includes Homebrew

Read the full file on GitHub · 129 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 129 lines · 46 tokens per session scan A e3a08f4ae15a

Subscribe to this mod's changes

use-local-whisper is a skill published in the GitHub repository DingyangLyu/MatClaw (90 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,184 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 84% identical to use-local-whisper, differing in 44 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens