← Back to Skills Marketplace
2477
Downloads
3
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install clawd-presence
Description
Physical presence display for AI agents. Shows a customizable monogram (A-Z), status state, and current activity on a dedicated terminal/screen. Provides faster feedback than chat - glance at the display to see what the agent is doing. Use when setting up always-on agent visibility.
README (SKILL.md)
Clawd Presence
Terminal-based presence display for AI agents.
Why
Chat has latency. A presence display inverts this - the agent broadcasts state continuously, you glance at it like a clock.
Setup
# Configure (auto-detect from clawdbot or manual)
python3 scripts/configure.py --auto
# or
python3 scripts/configure.py --letter A --name "AGENT"
# Run display in dedicated terminal
python3 scripts/display.py
Update Status
Call from your agent whenever starting a task:
python3 scripts/status.py work "Building feature"
python3 scripts/status.py think "Analyzing data"
python3 scripts/status.py idle "Ready"
python3 scripts/status.py alert "Need attention"
python3 scripts/status.py sleep
States
| State | Color | Use |
|---|---|---|
idle |
Cyan | Waiting |
work |
Green | Executing |
think |
Yellow | Processing |
alert |
Red | Needs human |
sleep |
Blue | Low power |
Auto-Idle
Returns to idle after 5 minutes of no updates. Prevents stale states.
python3 scripts/configure.py --timeout 300 # seconds, 0 to disable
Files
scripts/display.py- Main displayscripts/status.py- Update statusscripts/configure.py- Settingsassets/monograms/- Letter designs A-Z
Usage Guidance
This skill appears to be what it claims: a local terminal presence display. Before installing/running, note that:
- The scripts will create and update config.json and state.json in the skill directory (or repo root). Put the code where you expect those files to be written or adjust paths if needed.
- The configure --auto option tries to read a small set of clawdbot config files in your home directory (uses PyYAML if installed) to auto-detect an agent name — only use --auto if you trust those local config files will be read.
- There are no network calls, no credentials requested, and nothing is downloaded at runtime. If you want extra assurance, inspect the included Python files (they are small and readable) before running and avoid running as a privileged user (no need for root).
Capability Analysis
Type: OpenClaw Skill
Name: clawd-presence
Version: 1.0.1
The OpenClaw AgentSkills bundle 'clawd-presence' is designed for displaying agent status. Its scripts primarily perform local file I/O to manage configuration and state (config.json, state.json) and display ASCII art monograms. The `scripts/configure.py` script reads `config.yaml` files from common `clawd` or `clawdbot` configuration paths in the user's home directory to auto-detect the agent's name. This file access is limited to specific, non-sensitive data (agent name) for a stated purpose and uses `yaml.safe_load`. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or harmful prompt injection attempts against the agent. All operations are local and align with the skill's described functionality.
Capability Assessment
Purpose & Capability
Name/description (physical presence display, monogram, states) matches the provided scripts and assets. The skill only needs local files (monograms, config.json, state.json) and the CLI described in SKILL.md to operate.
Instruction Scope
Runtime instructions only invoke included Python scripts which read/write local files (config.json, state.json) and display in a terminal. The configure script optionally attempts to read several expected clawdbot config files in the user's home directory when --auto is used (it imports PyYAML if available). This file access is consistent with the advertised auto-detection behavior, but it does mean the script will attempt to read specific files in the home directory if you run --auto.
Install Mechanism
No install spec or remote downloads are present. All code and assets are included in the bundle; nothing is fetched or executed from external URLs.
Credentials
The skill declares no required environment variables or credentials. The code does not attempt to read arbitrary env vars or request tokens; only optional dependency is PyYAML for auto-detection.
Persistence & Privilege
Skill is not always-enabled; it does not modify other skills or system-wide agent settings. It writes its own config.json and state.json under the skill directory (or repo root), which is expected for its function.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install clawd-presence - After installation, invoke the skill by name or use
/clawd-presence - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Initial release: physical presence display for AI agents
v1.0.0
Initial release: physical presence display for AI agents
Metadata
Frequently Asked Questions
What is Clawd Presence?
Physical presence display for AI agents. Shows a customizable monogram (A-Z), status state, and current activity on a dedicated terminal/screen. Provides faster feedback than chat - glance at the display to see what the agent is doing. Use when setting up always-on agent visibility. It is an AI Agent Skill for Claude Code / OpenClaw, with 2477 downloads so far.
How do I install Clawd Presence?
Run "/install clawd-presence" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Clawd Presence free?
Yes, Clawd Presence is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Clawd Presence support?
Clawd Presence is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Clawd Presence?
It is built and maintained by voidcooks (@voidcooks); the current version is v1.0.1.
More Skills