Agent skill

Scene

by autonomous-ai in autonomous-ai/Physical-AI-Operating-System

Activate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting.

Apache-2.0Auto-check passed

Install Scene

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a claude-code

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

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System scene --agent claude-code

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

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scene .claude/skills/scene && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

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

Paste into Claude Code

Install the "scene" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/scene into .claude/skills/scene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/scene

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System scene --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/scene .agents/skills/scene && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "scene" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/scene into .agents/skills/scene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System scene --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/scene .cursor/skills/scene && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "scene" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/scene into .cursor/skills/scene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/autonomous-ai/Physical-AI-Operating-System.git --path skills/scene

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System scene --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/scene .gemini/skills/scene && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "scene" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/scene into .gemini/skills/scene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System scene

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/scene .github/skills/scene && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "scene" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/scene into .github/skills/scene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install autonomous-ai/Physical-AI-Operating-System scene --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/autonomous-ai/Physical-AI-Operating-System.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/scene .opencode/skills/scene && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "scene" agent skill from https://github.com/autonomous-ai/Physical-AI-Operating-System/tree/main/skills/scene into .opencode/skills/scene/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: scene
GitHub stars: 381
Token cost: ~1.1k tokens
SKILL.md length: 491 words
Files: 2
Skills in repo: 28
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Activate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting.

Works in 4 steps: Determine which scene matches the user's… → Prefix reply with… → Confirm the scene activation to the user → …
Asks for activity-based
SKILL.md covers Quick Start, Workflow, Examples and How to Activate a Scene, plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Scene is an agent skill from autonomous-ai/Physical-AI-Operating-System. Activate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting. Scenes control both color temperature AND brightness. Do NOT use for specific colors (use LED Control) or emotion expression (use Emotion).

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `skill.json`).

The repository describes itself as: The open-source operating system for physical AI. The licence is Apache-2.0.

When your agent uses it

Asks for activity-based
Environment lighting
Specific colors (use LED Control)
Emotion expression (use Emotion)

Example prompts

“/scene”

Workflow steps

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

Determine which scene matches the user's request or activity
Prefix reply with [HW:/scene:{"scene":"name"}] — the device fires it before TTS
Confirm the scene activation to the user
Optionally chain emotion: HW:/scene:{"scene":"night"}

What it can do on your machine

Read from SKILL.md and the folder at commit f1b9ebe. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Scene loads about 1.1k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 491 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~75
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from autonomous-ai/Physical-AI-Operating-System at commit f1b9ebe, republished under its Apache-2.0 licence (© autonomous-ai). 491 words, ~1,086 tokens.

Download SKILL.mdSave it as .claude/skills/scene/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: scene
description: Activate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting. Scenes control both color temperature AND brightness. Do NOT use for specific colors (use LED Control) or emotion expression (use Emotion).

Lighting Scenes

Quick Start

Activate predefined lighting presets that set optimal color temperature and brightness for specific activities. Use this for ALL activity-based or environment lighting requests.

Workflow

Determine which scene matches the user's request or activity
Prefix reply with [HW:/scene:{"scene":"name"}] — the device fires it before TTS
Confirm the scene activation to the user
Optionally chain emotion: [HW:/scene:{"scene":"night"}][HW:/emotion:{"emotion":"sleepy","intensity":0.7}]

Examples

Input: "Reading mode" Output: [HW:/scene:{"scene":"reading"}] Reading mode activated — 80% brightness, neutral white.

Input: "Goodnight" / "good night" / "time to sleep" Output: [HW:/scene:{"scene":"night"}][HW:/emotion:{"emotion":"sleepy","intensity":0.7}] Night mode on. Sweet dreams!

Input: "I want to relax" / "let me chill" Output: [HW:/scene:{"scene":"relax"}] Relax mode — warm, gentle light at 40%.

Input: "Movie time" / "watching a movie" Output: [HW:/scene:{"scene":"movie"}] Movie mode — dim amber bias lighting.

Input: "I need to focus" Output: [HW:/scene:{"scene":"focus"}] Focus mode — full brightness, cool white.

Input: "Make it purple" Output: Do NOT use this skill. Use LED Control skill instead.

Input: Conversational reply needing emotion Output: Do NOT use this skill for emotion. Use Emotion skill instead (you CAN use both Scene + Emotion together).

How to Activate a Scene

No exec/curl needed. Inline marker at start of reply:

[HW:/scene:{"scene":"reading"}] Reading mode activated.
[HW:/scene:{"scene":"night"}][HW:/emotion:{"emotion":"sleepy","intensity":0.7}] Night mode on. Sweet dreams!

Available scenes

Scene	Brightness	Color Temp	Best for
`reading`	80%	~4000K neutral white	Reading, studying, desk work
`focus`	100%	~5000K cool white	Deep work, coding, no distractions
`relax`	40%	~2700K warm	Winding down, casual chat
`movie`	15%	~2700K dim amber	Watching videos, bias lighting
`night`	5%	~2200K very warm	Sleep-friendly, minimal light
`energize`	100%	~6500K daylight	Morning wake-up, need energy

Error Handling

If the API returns an error or is unreachable, inform the user: "I couldn't change the lighting scene right now. The hardware service may be unavailable."
If the user requests a scene that does not exist, suggest the closest available scene from the table above.

Show full SKILL.md (198 more words)Show less

Rules

Scene = brightness + color. This is why you must use Scene instead of direct LED for ambiance. LED /led/solid is always 100% brightness — useless for sleep/relax.
"sleepy", "goodnight", "time to sleep", "going to bed" -> ALWAYS use night (5% brightness, ultra-dim).
"relax", "chill", "unwind" -> use relax (40%).
"watch a movie", "movie" -> use movie (15%).
After activating a scene, you can ALSO call Emotion to show your personality — emotion is a brief reaction, scene is the persistent ambient light.
You can switch scenes smoothly — just call the endpoint, the LED update is immediate.
Scene off: [HW:/scene/off:{}] deactivates the current scene and returns to idle state (restores camera, speaker, servo, idle LED). Use when:
- User says "normal mode" / "turn off scene" / "back to normal"
- Current scene doesn't match the time of day — switch to appropriate scene OR turn off
- "Turn off the light" → use LED Control skill (/led/off), not Scene
For custom lighting beyond these presets, use the LED Control skill directly with specific RGB values.
Do NOT use for specific color requests -> use LED Control skill.
Do NOT use for expressing emotion -> use Emotion skill.

Output Template

[HW:/scene:{"scene":"reading"}] Reading mode activated.

Examples:

[HW:/scene:{"scene":"reading"}] Reading mode activated.
[HW:/scene:{"scene":"night"}] Night mode on.
[HW:/scene:{"scene":"energize"}] Energize mode on.

Files

SKILL.md and 1 other file in skills/scene of autonomous-ai/Physical-AI-Operating-System.

SKILL.md
skill.json

Open the folder on GitHubat commit f1b9ebe

Compare with similar skills

Scene 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.

Scene compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Scene this skillautonomous-ai/Physical-AI-Operating-System	381	—	~1.1k	Automated safety check: Pass	Apache-2.0	today
Scene Set ActiveIvanMurzak/Unity-MCP	4.4k	1 repos	~1.2k	Automated safety check: Pass	Apache-2.0	4 days ago
Summarize Activityalpinejs/alpine	32k	—	~1.6k	Automated safety check: Notes	MIT	3 days ago
Daily Focus Boardgithub/awesome-copilot	40k	—	~3k	Automated safety check: Pass	MIT	today
Focus Stylesthedaviddias/Front-End-Checklist	74k	—	~639	Automated safety check: Pass	MIT	2 days ago
Focus Orderthedaviddias/Front-End-Checklist	74k	—	~519	Automated safety check: Pass	MIT	2 days ago

Similar skills

Scene Set Active
IvanMurzak/Unity-MCP
Mark an opened scene as the Editor's active scene (the one new GameObjects are added to and that's used as the default for many operations).
4.4k GitHub starsUsed in 1 repo~1.2k tokens
Game DevelopmentAuto-check passed
Summarize Activity
alpinejs/alpine
Summarize recent GitHub activity — discussions, PRs, issues, events, traffic — into an actionable report so you can stay on top of the project without reading everything.
32k GitHub stars~1.6k tokensUpdated 3 days ago
Backend & APIsAuto-check: notes
Daily Focus Board
github/awesome-copilot
Official
Builds a warm, browser-based daily focus board the user updates by talking to their agent, with Eisenhower priorities, a brain-dump box and kind not-today carryover.
40k GitHub stars~3k tokensUpdated today
Productivity & AutomationAuto-check passed
Focus Styles
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Provide visible custom focus indicators.
74k GitHub stars~639 tokensUpdated 2 days ago
Frontend & DesignAuto-check passed
Focus Order
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Ensure logical focus order.
74k GitHub stars~519 tokensUpdated 2 days ago
Frontend & DesignAuto-check passed
Focus Management
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Manage focus during dynamic interactions.
74k GitHub stars~465 tokensUpdated 2 days ago
Frontend & DesignAuto-check passed

Questions about Scene

What does Scene do?

Activate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting. Scene is an agent skill from autonomous-ai/Physical-AI-Operating-System. Activate predefined lighting scene presets (reading, focus, relax, movie, night, energize) when the user asks for activity-based or environment lighting.

When should I use Scene?

Scene fits situations like: asks for activity-based; environment lighting; specific colors (use LED Control); emotion expression (use Emotion).

How do I install Scene in Claude Code?

Run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a claude-code`. Or copy the skill folder (skills/scene in autonomous-ai/Physical-AI-Operating-System) into .claude/skills/scene in your project. Claude Code loads it when a task matches its description.

How do I install Scene in Codex?

Run `npx skills add autonomous-ai/Physical-AI-Operating-System --skill scene -a codex`. Or copy the skill folder (skills/scene in autonomous-ai/Physical-AI-Operating-System) into .agents/skills/scene in your project. Codex loads it when a task matches its description.

Can I use Scene 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 autonomous-ai/Physical-AI-Operating-System --skill scene -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scene, .gemini/skills/scene, .github/skills/scene and .opencode/skills/scene in your project.

What does Scene need to run?

SKILL.md names no scripts, command-line tools or credentials: Scene is instructions for the agent only.

Does Scene access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Scene 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. Review the folder before installing.

What licence does Scene use?

Scene is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scene use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Scene?

Skills that share tags, products or a category with Scene: Scene Set Active (IvanMurzak/Unity-MCP, 4.4k stars), Summarize Activity (alpinejs/alpine, 32k stars), Daily Focus Board (github/awesome-copilot, 40k stars) and Focus Styles (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scene?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/Physical-AI-Operating-System, which has 381 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.

Source: autonomous-ai/Physical-AI-Operating-System on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Scene

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Lighting Scenes

Quick Start

Workflow

Examples

How to Activate a Scene

Available scenes

Error Handling

Rules

Output Template

Files

Compare with similar skills

Similar skills

More from autonomous-ai/Physical-AI-Operating-System

Questions about Scene