hermes-desktop-preview
Hermes Desktop default preview tabs (YouTube, X).
- License 许可
- MIT
- 所属仓库
- zapabob/Skills
- 最近更新
- 2026-10-26
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- hermes-desktop-preview
- author
- Hermes Agent
- license
- MIT
- version
- 1.1.0
- metadata
- { "hermes": { "tags": [ "desktop", "preview", "tabs", "youtube", "x" ], "category": "desktop", "related_skills": [ "computer-use" ] } }
- platforms
- [ "windows" ]
- description
- Hermes Desktop default preview tabs (YouTube, X).
03 SKILL.md 正文
Hermes Desktop Preview Tabs Skill
This skill documents the default preview tabs feature in Hermes Desktop (Electron app).
When Hermes Desktop launches, the $previewTabs atom is initialized with DEFAULT_PREVIEW_TABS. This contains two pre-configured tabs: YouTube (url:https://www.youtube.com) and X (url:https://x.com). These appear in the right preview rail of the Hermes Desktop interface.
If tabs don't appear on launch:
- Ensure Hermes Desktop is fully running (the Electron app, not just the CLI)
- Restart Hermes Desktop if tabs are missing
- Feature only works when the app is running
Vertical Split Behavior
URL previews (YouTube, X) open side by side in a row split — equal height, sharing rail width. File/artifact previews dock as before.
See references/code-reference.md for implementation details and the 2026-08-18 change.
Code reference: apps/desktop/src/store/preview.ts, apps/desktop/src/app/chat/preview-tile.tsx.
04 同仓库更多 Skills
xurl
X/Twitter via xurl CLI: post, search, DM, media, v2 API.
writing-plans
Write implementation plans: bite-sized tasks, paths, code.
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
watchers
Poll RSS, JSON APIs, and GitHub with watermark dedup.
serving-llms-vllm
vLLM: high-throughput LLM serving, OpenAI API, quantization.