Foundation Models On Device
affaan-m/ECC
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
Configure Mycodo environmental-control workflows using Inputs, Outputs, Functions, Actions, Widgets, Dashboards, PID, Conditional, Trigger, Methods, cameras, energy, and notes.
GPL-3.0Auto-check passed
Install Devices And Control
$ npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill devices-and-control --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control .claude/skills/devices-and-control && rm -rf skills-srcUse ~/.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/
Install the "devices-and-control" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control into .claude/skills/devices-and-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "devices-and-control", 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 install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-controlType 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.
$ npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill devices-and-control --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control .agents/skills/devices-and-control && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "devices-and-control" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control into .agents/skills/devices-and-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "devices-and-control", 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.
$ npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill devices-and-control --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control .cursor/skills/devices-and-control && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "devices-and-control" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control into .cursor/skills/devices-and-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "devices-and-control", 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 https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill devices-and-control --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control .gemini/skills/devices-and-control && rm -rf skills-srcUse ~/.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/
Install the "devices-and-control" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control into .gemini/skills/devices-and-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "devices-and-control", 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.
$ gh skill install VectorSpaceLab/AREX-Skill devices-and-controlInstalls 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).
$ npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control .github/skills/devices-and-control && rm -rf skills-srcUse ~/.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/
Install the "devices-and-control" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control into .github/skills/devices-and-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "devices-and-control", 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.
$ npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill devices-and-control --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control .opencode/skills/devices-and-control && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "devices-and-control" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control into .opencode/skills/devices-and-control/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "devices-and-control", 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
devices-and-control- GitHub stars
- 330
- Token cost
- ~2.3k tokens
- SKILL.md length
- 1,087 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
Configure Mycodo environmental-control workflows using Inputs, Outputs, Functions, Actions, Widgets, Dashboards, PID, Conditional, Trigger, Methods, cameras, energy, and notes.
- Works in 7 steps: Name the goal and risk: what condition… → Choose the measurement: add and activate… → Choose the actuator: add an Output with… → …
- SKILL.md covers What This Sub-skill Owns, Route Out Of This Sub-skill, Bundled Files and Start Here: Control Planning…, plus 4 more sections
- Runs Python scripts from its folder; calls python
What it does
Devices And Control is an agent skill from VectorSpaceLab/AREX-Skill. Configure Mycodo environmental-control workflows using Inputs, Outputs, Functions, Actions, Widgets, Dashboards, PID, Conditional, Trigger, Methods, cameras, energy, and notes.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/control-workflows.md`, `references/device-catalog.md` and `references/hardware-and-control-recipes.md`).
The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is GPL-3.0.
Example prompts
- “/devices-and-control”
Requirements
- Python 3
- Docker
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Name the goal and risk: what condition changes, which device can change
- Choose the measurement: add and activate the Input or Function that
- Choose the actuator: add an Output with the correct type (on_off,
- Pick the controller: PID for proportional feedback, Bang-Bang for simple
- Attach Actions: connect Input Actions, Conditional Actions, or Trigger
- Observe first: create Live Measurements, Dashboard Widgets, graphs, and
- Bound mutation: require explicit confirmation before changing Outputs,
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
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
Devices And Control loads about 2.3k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 1,087 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its GPL-3.0 licence (© VectorSpaceLab). 1,087 words, ~2,252 tokens.
Download SKILL.mdSave it as
.claude/skills/devices-and-control/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- devices-and-control
- description
- Configure Mycodo environmental-control workflows using Inputs, Outputs, Functions, Actions, Widgets, Dashboards, PID, Conditional, Trigger, Methods, cameras, energy, and notes.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- GPL 3.0
Mycodo Devices And Control
Use this sub-skill when a task asks how to configure Mycodo environmental control from the web UI: Inputs, Outputs, Functions, Actions, Widgets, Dashboards, measurements, PID, Conditional, Trigger, Methods, camera capture, energy accounting, notes, or hardware/module selection. This skill is self-contained; do not reopen repository docs, examples, or tests to use it at runtime.
What This Sub-skill Owns
- Planning measurement flows from an Input or Function into InfluxDB and then into Widgets, Dashboards, Functions, PID, Conditional, Trigger, energy usage, and notes.
- Choosing and configuring built-in Inputs, Outputs, Functions, Actions, and Widgets from Mycodo's module families.
- PID regulation, PID Autotune, Bang-Bang control, Conditional Python logic, Trigger events, Methods, and setpoint tracking.
- Output actuation choices: on/off duration, PWM duty cycle, volume/pump, value/DAC, MQTT, command, remote Mycodo, startup state, shutdown state, and Trigger at Startup.
- Input choices: sensor/system/weather/MQTT/TTN/command Inputs, measurement units, Period, Pre Output, Power Output power cycling, Input Commands, and Input Actions.
- Dashboard design with Widgets, graphs, camera widgets, PID/output controls, live measurements, energy reports, and timestamped notes.
- Hardware-aware safety triage for GPIO, I2C, UART, SPI, 1-Wire, Bluetooth, cameras, relays, pumps, fans, DACs, ADCs, and optional module dependencies.
Route Out Of This Sub-skill
- Source-level custom Input, Output, Function, Action, or Widget module authoring
belongs to
custom-modules. - REST API, local Pyro
DaemonControl,mycodo-client, external scripts, or remote automation belongs toapi-and-automation. - Full installation, upgrades, backup/restore operations, Docker, nginx,
systemd, InfluxDB service repair, or host service hardening belongs to
installation-operations. - Repository source-code development, database migrations, Flask routes, and upstream test execution are outside this runtime operating skill.
Bundled Files
Read or run these files instead of looking up upstream material:
- references/control-workflows.md — read when designing end-to-end Input → measurement → Output/Function/Action → Dashboard workflows, PID/Conditional/Trigger/Method logic, or measurement Max Age assumptions.
- references/hardware-and-control-recipes.md — read when selecting hardware patterns for chambers, fans, relays, pumps, pH/EC dosing, TTN/MQTT, cameras, energy usage, or safe dry-run procedures.
- references/device-catalog.md — read when choosing among built-in module families, interfaces, output types, Actions, and Widgets without source lookup.
- references/troubleshooting.md — read when an Input has no data, an Output will not actuate, PWM behaves oddly, PID does not control, Conditional code errors, Trigger timers miss, widgets show stale data, camera/energy/notes fail, or optional dependencies/hardware are absent.
- scripts/summarize_supported_modules.py
— run only when the user has a Mycodo checkout and wants a static, no-import
catalog summary from source metadata. Use
--helpfirst.
Start Here: Control Planning Loop
- Name the goal and risk: what condition changes, which device can change it, and what can be damaged by wrong state, frequency, duration, volume, or credentials?
- Choose the measurement: add and activate the Input or Function that writes the needed measurement to InfluxDB; set units, Period, and Max Age assumptions before adding control logic.
- Choose the actuator: add an Output with the correct type (
on_off,pwm,volume, orvalue), interface, channel, startup state, shutdown state, and energy-current metadata. - Pick the controller: PID for proportional feedback, Bang-Bang for simple hysteresis, Conditional for custom Python decisions, Trigger for events or timers, and Method/Setpoint Tracking when the target should change over time.
- Attach Actions: connect Input Actions, Conditional Actions, or Trigger Actions to Outputs, PID controls, MQTT, e-mail/photo, notes, logs, or controller activation.
- Observe first: create Live Measurements, Dashboard Widgets, graphs, and notes before leaving control unattended.
- Bound mutation: require explicit confirmation before changing Outputs, PID activation, system restart/shutdown, command Outputs, credentials, network endpoints, or any live wiring.
Minimal Web UI Workflows
Add An Input Measurement
- Navigate to
Setup -> Input. - Add the Input family matching the sensor/system source.
- Set interface/location fields such as GPIO BCM pin, I2C address and bus, UART device, FTDI device, 1-Wire serial, Bluetooth adapter, IP/HTTP/MQTT, or TTN credentials as required by the module.
- Set
Period (seconds)and measurement unit/channel options. - If a sample requires a purge fan, pump, or valve, configure
Pre Output,Pre Output Duration, and whether it stays on during measurement. - If the sensor can recover from power cycling, configure
Power Outputand verify the physical circuit can safely switch sensor power. - Save, activate, then confirm Live Measurements and graph data before adding control logic.
Show full SKILL.md (406 more words)Show less
Add An Output Actuator
- Navigate to
Setup -> Output. - Choose output type by physical action: On/Off relay, PWM, volume/pump, value output, MQTT, command, remote Mycodo, motor, DAC, or expander board.
- Configure channel options, On State, command strings, duty cycle, flow rate, value range, or protocol as appropriate.
- Set
Startup StateandShutdown State; useDo Nothingonly when the device has an independent safe state. - Set
Current Draw (amps)when energy duration accounting matters. - Test with short, supervised
Seconds to turn On, duty cycle, volume, or value commands before connecting loads that can heat, flood, dose, or move.
Add A Function Controller
- Use PID for feedback that should approach and maintain a setpoint with
proportional/integral/derivative terms. Set
Max Ageso stale measurements do not actuate Outputs. - Use PID Autotune only as experimental guidance after a supervised dry run; watch the daemon log and graph output during perturbation.
- Use Bang-Bang when a simple hysteresis band is sufficient.
- Use Conditional when Python logic must combine measurements, Output state, controller state, actions, and custom status text.
- Use Trigger for Output/PWM state events, edge events, timers, sunrise or sunset, and Run PWM Method schedules.
- Use Methods for PID setpoint tracking or time-varying PWM duty cycle.
Safety Checklist Before Activation
- Confirm target controller IDs, channel numbers, units, setpoints, and Max Age values from the live web UI.
- Confirm the Output can physically affect the selected measurement and that the
effect direction (
Raise,Lower, orBoth) is correct. - Confirm
Min Off Duration,Min/Max On Duration, duty cycle limits, volume limits, or DAC value limits for devices that can be damaged by rapid cycling. - Confirm command Outputs and Python code cannot leak secrets, erase files, restart services, or run untrusted input.
- Confirm MQTT/TTN/API credentials are scoped and not copied into logs or notes.
- Stop and ask the user before mutating GPIO/I2C/UART/1-Wire/Bluetooth/camera, system services, nginx, InfluxDB, Docker, backup/restore, or installer state.
Script Usage
Static source catalog summary from a checkout:
python scripts/summarize_supported_modules.py --repo-root /path/to/Mycodo --family all --limit 20JSON for integration notes:
python scripts/summarize_supported_modules.py --repo-root /path/to/Mycodo --json --show-modulesThe helper only parses Python source text with ast; it does not import Mycodo,
load optional dependencies, contact hardware, use credentials, or run daemon
operations.
Verification Limits
This sub-skill was produced from CPU/source inspection and documentation inspection only. Raspberry Pi GPIO/I2C/UART/1-Wire/Bluetooth/camera behavior, systemd/nginx/InfluxDB services, Docker deployment, backup/restore operations, and full installer execution were not run. Treat hardware and service claims as configuration guidance that must be verified on the user's live system before unsafe mutation.
© VectorSpaceLab, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (scripts, references) in skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/control-workflows.md
- references/device-catalog.md
- references/hardware-and-control-recipes.md
- references/troubleshooting.md
- scripts/summarize_supported_modules.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Devices And Control 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Devices And Control this skillVectorSpaceLab/AREX-Skill | 330 | — | ~2.3k | Automated safety check: Pass | GPL-3.0 | |
| Foundation Models On Deviceaffaan-m/ECC | 276k | 4 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Configuration Authentication Cross Devicegreenpau/caddy-security | 2.3k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Configure Channelopenclaw/openclaw | 392k | — | ~946 | Automated safety check: Pass | MIT | |
| Securing Serverless Functionsmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| ConfigurationBuilderIO/agent-native | 7.1k | — | ~2.1k | Automated safety check: Pass | None |
Similar skills
Configuration Authentication Cross Device
greenpau/caddy-security
Configure and verify optional cross-device portal login, QR activation, explicit approval, browser binding, cancellation, and lifecycle through Caddy.
Configure Channel
openclaw/openclaw
Configure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.
Securing Serverless Functions
mukul975/Anthropic-Cybersecurity-Skills
Hardens serverless compute platforms (AWS Lambda, Azure Functions, Google Cloud Functions): least-privilege IAM roles, dependency vulnerability scanning, secrets management integration, input…
Configuration
BuilderIO/agent-native
Where a configuration value belongs — app config schema, agent-native.config.ts, or an environment variable — and how the layers resolve.
Output Dev Step Function
growthxai/output
Create step functions in steps.ts for Output SDK workflows. An agent skill from growthxai/output.
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Questions about Devices And Control
What does Devices And Control do?
Configure Mycodo environmental-control workflows using Inputs, Outputs, Functions, Actions, Widgets, Dashboards, PID, Conditional, Trigger, Methods, cameras, energy, and notes. Devices And Control is an agent skill from VectorSpaceLab/AREX-Skill. Configure Mycodo environmental-control workflows using Inputs, Outputs, Functions, Actions, Widgets, Dashboards, PID, Conditional, Trigger, Methods, cameras, energy, and notes.
How do I install Devices And Control in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control in VectorSpaceLab/AREX-Skill) into .claude/skills/devices-and-control in your project. Claude Code loads it when a task matches its description.
How do I install Devices And Control in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill devices-and-control -a codex`. Or copy the skill folder (skills/repositories/repo-skills/mycodo/sub-skills/devices-and-control in VectorSpaceLab/AREX-Skill) into .agents/skills/devices-and-control in your project. Codex loads it when a task matches its description.
Can I use Devices And Control 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 VectorSpaceLab/AREX-Skill --skill devices-and-control -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/devices-and-control, .gemini/skills/devices-and-control, .github/skills/devices-and-control and .opencode/skills/devices-and-control in your project.
What does Devices And Control need to run?
Going by SKILL.md and its folder, Devices And Control needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3; Docker.
Does Devices And Control 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 Devices And Control 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Devices And Control use?
Devices And Control is published under the GPL-3.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Devices And Control use?
About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.
What are the alternatives to Devices And Control?
Skills that share tags, products or a category with Devices And Control: Foundation Models On Device (affaan-m/ECC, 276k stars), Configuration Authentication Cross Device (greenpau/caddy-security, 2.3k stars), Configure Channel (openclaw/openclaw, 392k stars) and Securing Serverless Functions (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Devices And Control?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.