AGENT SKILL

pocket-debater

PocketDebater — a debate practice app for the Rabbit R1. Generates opponent arguments, scores exchanges, and delivers a coaching debrief using the R1 built-in LLM.

License 许可
MIT
最近更新
2026-09-04
Stars
★ 0
Forks
0

01 前言 Front Matter

name
pocket-debater
author
rabbit-r1-skillz
version
1.1.0
description
PocketDebater — a debate practice app for the Rabbit R1. Generates opponent arguments, scores exchanges, and delivers a coaching debrief using the R1 built-in LLM.

02 资源文件 3

03 SKILL.md 正文

PocketDebater

PocketDebater is a self-contained debate practice app that runs entirely on the R1 device. All argument generation, scoring, and debrief analysis use the R1 built-in LLM via PluginMessageHandler. No local machine, bridge, or external service is required.


How it works

  1. The user picks a debate format (Socratic, Steel Man, Devil's Advocate, Cross Examination, or Street Fighter).
  2. The user speaks their argument via PTT. STT transcription arrives as sttEnded.
  3. The app builds a format-specific prompt and sends it to the R1 LLM (useLLM: true, wantsR1Response: false).
  4. The LLM response is spoken back using TTS and displayed in the debate bubble.
  5. If scoring is enabled, a second LLM call scores the exchange and returns JSON with humanScore, r1Score, and a rationale sentence.
  6. After all rounds complete, a third LLM call generates a structured debrief (strongest argument, weakest point, coach tip).

No external dependencies

PocketDebater has no OpenClaw dependency and no network calls beyond the R1 LLM API. All state is stored in creationStorage under the keys below.


Storage keys used

Key Purpose
pocketdebater:stats Lifetime debate statistics (debates, wins, losses, avg score)
pocketdebater:history Last 30 debate records (topic, format, scores, result)
pocketdebater:best-arg Best-scored argument saved for the stats screen

All storage uses creationStorage.plain (per-pluginId isolation).


Security notes

  • All prompts are constructed from the user's own spoken arguments and the app's built-in system prompts.
  • There is no web-fetch or external data ingestion, so the lethal-trifecta risk (private data + untrusted content + external comms) does not apply.
  • Do not log debate transcripts to external services without explicit user consent.

04 同仓库更多 Skills

ajohnsonnow
ajohnsonnow/r1-warren

whisper-quiz

WhisperQuiz — voice-answered trivia game for Rabbit R1. Generates questions via the R1's built-in LLM, captures spoken answers via STT, and evaluates correctness with flexible LLM-based matching.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

walk-cast

Walking podcast production skill. Receives raw audio metadata and transcript from the R1, removes long pauses, applies noise reduction and normalization, generates AI chapter titles and episode metadata via LLM, and uploads the final episode to your configured podcast RSS host (Spotify for Podcasters / Anchor, Podbean, Buzzsprout, RSS.com, or any FTP-accessible feed).

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

voice-novel

Local machine skill for VoiceNovel — handles story export to disk.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

voice-guide

Environment description and navigation assistant for blind and low-vision users. Analyzes camera frames via a vision LLM, reads visible text, identifies scene categories (people/vehicles/food/hazards/exits), performs 360° scans, retrieves GPS position, and sends emergency SMS alerts — all via audio feedback with zero screen dependency.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

voice-draft

Voice-driven document drafting for the Rabbit R1. Dictate stream-of-consciousness speech; the R1 formats it into Email, Blog Post, Report, Proposal, Meeting Notes, Creative Writing, Code Comments, Cover Letter, or Tweet Thread — then saves the result to a configured folder on your local machine via OpenClaw.

★ 0
ajohnsonnow
ajohnsonnow/r1-warren

voice-commit

Hands-free git and CI workflow voice controller for the Rabbit R1. Speak git/CI commands and hear results — commit, push, status, PR management, test runs, and deploy, all voice-driven via OpenClaw.

★ 0