← Back to Skills Marketplace
toniaczlog

Voice Notes Pro

by toniaczlog · GitHub ↗ · v2.0.1
cross-platform ⚠ suspicious
1353
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install voice-notes-pro
Description
Automatyczna transkrypcja i kategoryzacja notatek głosowych z WhatsApp do plików Markdown w 6 kategoriach, w tym zadania i lista zakupów.
Usage Guidance
What to check before installing: - Expect to provide an OPENAI_API_KEY (the code throws if it's missing); the registry metadata currently omits that — ask the publisher to declare required env vars. - The skill writes files to disk. Confirm which directories it will use (SKILL.md shows ~/notes but code defaults to /root/notes). Adjust configuration to point to a safe, writable directory you control and verify file permissions. - SKILL.md tells you to run npm install in the skill folder; package.json depends on the public 'openai' package (common) but package.json's 'main' is 'skill.js' while included file is voice-notes-pro.js — this mismatch may prevent the skill from running; ask the author to fix packaging before installing. - SKILL.md includes a hard-coded phoneNumber in its example config — remove or replace with your own and confirm the skill only connects to your WhatsApp gateway. - Review the code (transcribeAudio and handlers) yourself or have a trusted developer review it: it reads audio files and sends them to OpenAI for transcription (expected), and only writes local Markdown files. There is no obvious network exfiltration beyond OpenAI API calls, but ensure you trust the OpenAI API key you provide. - If you need higher assurance: request the publisher to update registry metadata to list required env vars/config paths, fix package.json main/version mismatches, and provide a signed release or a vetted install instruction so you can audit the exact code that will be installed. Confidence note: medium — the code appears to implement the advertised functionality, but multiple metadata/instruction mismatches (undeclared OPENAI_API_KEY requirement, path inconsistencies, package.json main mismatch, example phone number) create ambiguity that prevents a clean 'benign' verdict. Additional metadata fixes or reproducible build instructions would raise confidence.
Capability Analysis
Type: OpenClaw Skill Name: voice-notes-pro Version: 2.0.1 The skill is suspicious due to its explicit configuration to write user-generated notes into the `/root/notes/` directory, as specified in both `SKILL.md` and `voice-notes-pro.js`. While the stated purpose is benign note-taking, targeting the `/root/` directory is a high-risk capability that implies an attempt to write to a highly privileged location, which is not aligned with typical user-level note management and could lead to unauthorized file modification if the agent runs with elevated privileges. There is no clear evidence of data exfiltration or malicious code execution.
Capability Assessment
Purpose & Capability
The stated purpose (transcribe WhatsApp voice notes, categorize and append to Markdown files) matches the code: it calls OpenAI Whisper, detects categories, and writes to local note files. However the registry metadata claims no required env vars or config paths while both SKILL.md and the code require an OpenAI API key and writable note directories — this is an inconsistency.
Instruction Scope
SKILL.md instructs npm install, restarting the OpenClaw gateway, requiring WhatsApp connection, and write permissions to ~/notes; the code will write to absolute paths under /root/notes by default. The instructions and code reference reading/writing local files and a WhatsApp gateway (expected), but the filesystem path mismatch (~/notes vs /root/notes) and a hard-coded phone number in SKILL.md are surprising and warrant validation.
Install Mechanism
There is no formal install spec in the registry, but SKILL.md tells the user to run npm install in the skill directory; package.json depends on the public 'openai' npm package (expected). This is moderate risk (npm pulls remote code) but uses a well-known package. Additional concerns: package.json's 'main' points at 'skill.js' while the repository file is voice-notes-pro.js (mismatch that may break installation/runtime).
Credentials
The code requires process.env.OPENAI_API_KEY for transcription, and SKILL.md lists 'OpenAI API key' and a WhatsApp connection as requirements, yet the registry metadata declares no required environment variables or primary credential. That omission is a meaningful mismatch — the skill needs a sensitive credential but the registry doesn't advertise it. Also SKILL.md contains a hard-coded phoneNumber in its example config which may leak or confuse.
Persistence & Privilege
The skill is not set to always:true and does not request to modify other skills or system-wide settings. It writes to its own configured note directories and requires restart of the OpenClaw gateway for activation (documented). Autonomous invocation is allowed by default (normal for skills) but does not by itself increase concern here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install voice-notes-pro
  3. After installation, invoke the skill by name or use /voice-notes-pro
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.1
No code or file changes detected in this version; only documentation updates. - SKILL.md rewritten for clarity and expanded detail - Added feature descriptions, keywords for each note category, and usage examples - Documented triggers that prompt skill activation - Expanded configuration and installation instructions - Stated system requirements and current production status
v2.0.0
Voice Notes Pro v2.0 brings expanded note categorization and people database. - Added support for 6 categories: song lyrics, tasks, shopping, ideas, people database, and watchlist. - Introduced a dedicated people database with add/check features. - Provided configuration options for category directories and WhatsApp integration. - Improved Polish-language instructions and usage examples. - Relies on Whisper (via Blew) for voice transcription.
Metadata
Slug voice-notes-pro
Version 2.0.1
License
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Voice Notes Pro?

Automatyczna transkrypcja i kategoryzacja notatek głosowych z WhatsApp do plików Markdown w 6 kategoriach, w tym zadania i lista zakupów. It is an AI Agent Skill for Claude Code / OpenClaw, with 1353 downloads so far.

How do I install Voice Notes Pro?

Run "/install voice-notes-pro" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Voice Notes Pro free?

Yes, Voice Notes Pro is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Voice Notes Pro support?

Voice Notes Pro is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Voice Notes Pro?

It is built and maintained by toniaczlog (@toniaczlog); the current version is v2.0.1.

💬 Comments