New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Voxclaw

by malpern in malpern/VoxClaw

Give your agent a voice. An agent skill from malpern/VoxClaw.

No licenceAuto-check passedMedia & Creative

Install Voxclaw

skills CLI
$ npx skills add malpern/VoxClaw --skill voxclaw -a claude-code

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

GitHub CLI
$ gh skill install malpern/VoxClaw voxclaw --agent claude-code

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

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

Facts

Skill name
voxclaw
GitHub stars
208
Token cost
~1.9k tokens
SKILL.md length
736 words
Files
302 (incl. scripts)
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Give your agent a voice. An agent skill from malpern/VoxClaw.

  • Works in 4 steps: Confirm on VoxClaw Mac: curl -sS… → Confirm from agent host: curl -sS… → Send all speech — including final… → …
  • Tasks that involve Text to speech and voice
  • SKILL.md covers How It Works, Fast Handoff (Human -> Agent), API and Setup, plus 3 more sections
  • Calls curl; reaches voxclaw.com

What it does

Voxclaw is an agent skill from malpern/VoxClaw. Give your agent a voice. Send text to a Mac running VoxClaw and hear it spoken aloud with OpenAI neural voices or Apple TTS.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 309 other files, including scripts (for example `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json` and `.claude/commands/voxclaw-failure.md`).

It sits in Media & Creative, covering Text to speech and voice. It works with OpenAI. The repository describes itself as: Give OpenClaw a voice — Let your agent speak from any Mac on your network.

When your agent uses it

  • Tasks that involve Text to speech and voice

Example prompts

  • “/voxclaw”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Confirm on VoxClaw Mac: curl -sS http://localhost:4140/status
  2. Confirm from agent host: curl -sS http://:4140/status
  3. Send all speech — including final summaries and failures — to :4140/read
  4. If step 1 passes but step 2 fails, treat as network/firewall issue (not app API issue).

What it can do on your machine

Read from SKILL.md and the folder at commit 0a1cb0f. 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 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • voxclaw.com

    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

Voxclaw loads about 1.9k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 736 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 736 words (~1,860 tokens).

“VoxClaw is a macOS app that speaks text aloud. It runs on the user's Mac as a menu bar app and listens for text over HTTP. Send text from any machine on the LAN and VoxClaw reads it using OpenAI…”

— opening of SKILL.md by malpern
name
voxclaw
homepage
https://github.com/malpern/VoxClaw

Read the full SKILL.md on GitHub

Files

SKILL.md and 301 other files (scripts) in the repository root of malpern/VoxClaw.

  • SKILL.md
  • .agents/plugins/marketplace.json
  • .claude-plugin/marketplace.json
  • .claude/commands/voxclaw-failure.md
  • .claude/commands/voxclaw-progress.md
  • .claude/commands/voxclaw-summary.md
  • .claude/settings.json
  • .github/workflows/ci.yml
  • .github/workflows/ios-release.yml
  • .github/workflows/release.yml
  • .gitignore
  • .vscode/launch.json
  • AGENTS.md
  • … and 289 more

Open the folder on GitHubat commit 0a1cb0f

Compare with similar skills

Voxclaw 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.

Voxclaw compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Voxclaw this skillmalpern/VoxClaw208—~1.9kAutomated safety check: PassNone
SpeechJetBrains/skills3663 repos~1.9kAutomated safety check: PassApache-2.0
Podcastteam-attention/plugins-for-claude-natives827—~1.5kAutomated safety check: PassMIT
Lessongug007/lpm152—~1.2kAutomated safety check: PassMIT
Speechdavila7/claude-code-templates32k—~2kAutomated safety check: PassApache-2.0
Speechnexu-io/open-design100k—~291Automated safety check: PassApache-2.0

Similar skills

  • Speech

    JetBrains/skills

    Official

    A skill your agent uses when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI…

    366 GitHub starsUsed in 3 repos~1.9k tokens
    Media & CreativeAuto-check passed

  • Podcast

    team-attention/plugins-for-claude-natives

    Generate Korean podcast episodes from any source (URLs, tweets, articles, PDFs) — analyzes content, writes a script, generates audio via OpenAI TTS, converts to MP4, and auto-uploads to YouTube.

    827 GitHub stars~1.5k tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed

  • Lesson

    gug007/lpm

    Make a narrated lesson video about lpm from the real desktop app, recorded on a pristine data directory.

    152 GitHub stars~1.2k tokensUpdated today
    Media & CreativeAuto-check passed

  • Speech

    davila7/claude-code-templates

    A skill your agent uses when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation.

    32k GitHub stars~2k tokensUpdated today
    Media & CreativeAuto-check passed

  • Speech

    nexu-io/open-design

    Generate spoken audio from text using OpenAI's API with built-in voices.

    100k GitHub stars~291 tokensUpdated today
    Media & CreativeAuto-check passed

  • Openai Tts

    benchflow-ai/skillsbench

    OpenAI Text-to-Speech API for high-quality speech synthesis.

    1.8k GitHub stars~946 tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed

More from malpern/VoxClaw

All 9 skills in this repo

  • Building Apple Platform Products

    malpern/VoxClaw

    Builds, tests, archives, and deploys Swift packages and Xcode projects for Apple platforms.

    208 GitHub stars~2.8k tokensUpdated 2 mo ago
    Auto-check: notes

  • Asc Screenshot Resize

    malpern/VoxClaw

    Resize and validate App Store screenshots for all device classes using macOS sips.

    208 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Asc Submission Health

    malpern/VoxClaw

    Preflight App Store submissions, submit builds, and monitor review status with asc.

    208 GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed

  • Asc Subscription Localization

    malpern/VoxClaw

    Bulk-localize subscription and in-app purchase display names across all App Store locales using asc.

    208 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed

  • Asc Workflow

    malpern/VoxClaw

    Define, validate, and run repo-local multi-step automations with asc workflow and .asc/workflow.json.

    208 GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed

  • Asc Xcode Build

    malpern/VoxClaw

    Build, archive, export, and manage Xcode version/build numbers with asc and xcodebuild before uploading to App Store Connect.

    208 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about Voxclaw

What does Voxclaw do?

Give your agent a voice. An agent skill from malpern/VoxClaw. Voxclaw is an agent skill from malpern/VoxClaw. Give your agent a voice.

When should I use Voxclaw?

Voxclaw fits situations like: tasks that involve Text to speech and voice.

How do I install Voxclaw in Claude Code?

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

How do I install Voxclaw in Codex?

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

Can I use Voxclaw 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 malpern/VoxClaw --skill voxclaw -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/voxclaw, .gemini/skills/voxclaw, .github/skills/voxclaw and .opencode/skills/voxclaw in your project.

What does Voxclaw need to run?

Going by SKILL.md and its folder, Voxclaw needs the command-line tools its instructions call (curl).

Does Voxclaw access the network?

SKILL.md names 1 domain. In commands or code: voxclaw.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Voxclaw 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Voxclaw use?

No licence was found for Voxclaw or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Voxclaw use?

About 1.9k tokens (SKILL.md is roughly 7.4k 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 Voxclaw?

Skills that share tags, products or a category with Voxclaw: Speech (JetBrains/skills, 366 stars), Podcast (team-attention/plugins-for-claude-natives, 827 stars), Lesson (gug007/lpm, 152 stars) and Speech (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Voxclaw?

malpern (a GitHub user) maintains it in malpern/VoxClaw, which has 208 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on July 25, 2026.

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