← Back to Skills Marketplace
terrycarter1985

camsnap

by terrycarter1985 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
82
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install terrycarter-camsnap
Description
Take camera snapshots and save them to disk. Use when the user asks to take a photo, capture an image from webcam, or take a snapshot.
README (SKILL.md)

Take a snapshot from the default webcam using the camsnap utility.

Usage

/camsnap [output_path] [--preview]

If no output path is provided, the snapshot will be saved to the ./snapshots/ directory with a timestamp filename.

Steps

  1. Run the snapshot script:
python {{SKILL_DIR}}/src/camsnap.py {{ $ARGUMENTS }}
  1. Confirm the snapshot was saved successfully and return the file path.
Usage Guidance
Install only if you are comfortable granting a skill access to the local webcam. Until the Bash invocation is hardened, use simple output paths without shell characters, and make sure any OpenCV dependency is installed from a trusted source.
Capability Assessment
Purpose & Capability
The stated purpose, SKILL.md instructions, and Python code all align around taking a default-webcam snapshot and saving it locally.
Instruction Scope
SKILL.md instructs Bash execution as `python {{SKILL_DIR}}/src/camsnap.py {{ $ARGUMENTS }}`; the raw argument placeholder is not shown as quoted or otherwise constrained, so crafted arguments could be interpreted by the shell instead of only by the Python script.
Install Mechanism
There is no install spec, but the source imports OpenCV (`cv2`), so users may need an undeclared dependency from a trusted source.
Credentials
The code uses the default webcam and writes an image file, which is proportional to the described snapshot function; it prevents overwriting existing files and restricts common image extensions.
Persistence & Privilege
No background service, autostart, credentials, network transmission, or persistent agent memory behavior is shown; the only persistence is the user-requested image file.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install terrycarter-camsnap
  3. After installation, invoke the skill by name or use /terrycarter-camsnap
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
v1.0.0 — Code review fixes: path traversal protection, file overwrite guard, extension validation, camera resource safety (try/finally), imwrite return check, logging replaces print, type annotations, Path-based path handling, __all__ export. Optimized snapshot storage logic.
Metadata
Slug terrycarter-camsnap
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is camsnap?

Take camera snapshots and save them to disk. Use when the user asks to take a photo, capture an image from webcam, or take a snapshot. It is an AI Agent Skill for Claude Code / OpenClaw, with 82 downloads so far.

How do I install camsnap?

Run "/install terrycarter-camsnap" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is camsnap free?

Yes, camsnap is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does camsnap support?

camsnap is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created camsnap?

It is built and maintained by terrycarter1985 (@terrycarter1985); the current version is v1.0.0.

💬 Comments