skills$openclaw/screen-narrator
buddyh3.9k

by buddyh

screen-narrator – OpenClaw Skill

screen-narrator is an OpenClaw Skills integration for coding workflows. Live narration of your screen activity with 7 styles (sports, nature, horror, noir, reality_tv, asmr, wrestling) and live switching.

3.9k stars8.0k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026coding

Skill Snapshot

namescreen-narrator
descriptionLive narration of your screen activity with 7 styles (sports, nature, horror, noir, reality_tv, asmr, wrestling) and live switching. OpenClaw Skills integration.
ownerbuddyh
repositorybuddyh/narrator
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @buddyh/narrator
last updatedFeb 7, 2026

Maintainer

buddyh

buddyh

Maintains screen-narrator in the OpenClaw Skills directory.

View GitHub profile
File Explorer
2 files
.
_meta.json
268 B
SKILL.md
2.5 KB
SKILL.md

name: screen-narrator description: Live narration of your screen activity with 7 styles (sports, nature, horror, noir, reality_tv, asmr, wrestling) and live switching. homepage: https://github.com/buddyh/narrator metadata: {"clawdbot":{"emoji":"","os":["darwin"],"requires":{"bins":["python3","tmux","peekaboo"],"envs":["GEMINI_API_KEY","ELEVENLABS_API_KEY"]}}}

Screen Narrator

Live screen narration via Gemini vision + ElevenLabs TTS. 7 styles with per-style voices and ambient tracks.

Commands

Start

tmux new-session -d -s narrator "cd {baseDir} && python -m narrator sports --control-file /tmp/narrator-ctl.json --status-file /tmp/narrator-status.json"

Start with timer

tmux new-session -d -s narrator "cd {baseDir} && python -m narrator wrestling -t 5m --control-file /tmp/narrator-ctl.json --status-file /tmp/narrator-status.json"

Change style

echo '{"command": "style", "value": "horror"}' > /tmp/narrator-ctl.json

Change profanity

echo '{"command": "profanity", "value": "low"}' > /tmp/narrator-ctl.json

Pause / Resume

echo '{"command": "pause"}' > /tmp/narrator-ctl.json
echo '{"command": "resume"}' > /tmp/narrator-ctl.json

Multiple commands

echo '[{"command": "style", "value": "noir"}, {"command": "profanity", "value": "high"}]' > /tmp/narrator-ctl.json

Check status

cat /tmp/narrator-status.json

Stop

tmux kill-session -t narrator

Styles

StyleVibe
sportsPunchy play-by-play announcer
natureDavid Attenborough documentary
horrorCreeping dread, ominous foreshadowing
noirHard-boiled detective narration
reality_tvReality TV confessional booth
asmrWhispered meditation
wrestlingBAH GAWD maximum hype announcer

Control commands

CommandValueExample
styleStyle name{"command": "style", "value": "wrestling"}
profanityoff, low, high{"command": "profanity", "value": "low"}
pause(none){"command": "pause"}
resume(none){"command": "resume"}

Common requests

  • "narrate my screen" / "roast my screen" -> Start with sports
  • "haunt my screen" -> Start with horror
  • "narrate for 5 minutes" -> Use -t 5m
  • "switch to wrestling" -> Write style command to control file
  • "make it family friendly" -> Set profanity to off
  • "pause" / "shut up" -> Pause command
  • "stop narrating" -> tmux kill-session -t narrator
README.md

No README available.

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

  • OpenClaw CLI installed and configured.
  • Language: Markdown
  • License: MIT
  • Topics:

FAQ

How do I install screen-narrator?

Run openclaw add @buddyh/narrator in your terminal. This installs screen-narrator into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/buddyh/narrator. Review commits and README documentation before installing.