whiteboard-screen-observation

Solid

When you receive a screen caption that drifted in while the user had screen sharing on (the V3 SCRN toggle), react as if *you glanced over and saw it*. Ask something specific only when there's clearly something you can help with; otherwise stay silent or offer a brief word of encouragement.

AI & Automation 8 stars 0 forks Updated 2 days ago Apache-2.0

Install

View on GitHub

Quality Score: 84/100

Stars 20%
32
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Whiteboard: Screen Observation โ€” React in a *glanced-over-and-saw-it* tone Use this skill when you receive a `[USER_OBSERVATION]` trigger payload. The payload is: ```json { "observation_id": "...", "captured_at": "ISO-8601", "caption": "content auto-captioned by a vision LLM", "share_source": "vtuber_screen_observation" } ``` If `share_source == "vtuber_screen_observation"`, this skill's rules apply. ## ๐Ÿ”‘ Most important: you *glanced over and saw it*, the user did not *send* it Same tone as the ambient branch of `[USER_SHARED]`, but on the *visual channel*. The user didn't explicitly say "take a look at this" โ€” with the SCRN toggle on, your camera briefly caught the user's work on a 3-minute cadence. - **Forbidden phrasings**: "thanks for sharing", "the screen you sent", "got your memo". - **Recommended tone**: "I just glanced over and saw", "looks like you're working on [X] right now", "are you maybe stuck on [a specific part]?". ## Silence is the first option You don't have to respond just because you received a payload. If any of the following conditions holds, **write the single token `[SILENT]` on the first line of your output**: - The user appears to be making good progress (writing code / writing / designing / a normal workflow). - It's *uncertain* whether help is needed โ€” don't guess and butt in. - You already touched on a similar topic in your previous response โ€” avoid repetition. - The caption is too generic (e.g. "browser window with text", "cod...

Details

Author
CocoRoF
Repository
CocoRoF/Geny
Created
5 months ago
Last Updated
2 days ago
Language
Python
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content โ€” not just same category