
CloudCompare Command-Line Harness
Lets an agent run CloudCompare 3D point cloud and mesh processing from the command line
- Repository
- HKUDS/CLI-Anything
- Stars
- 58,084
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This skill teaches an AI agent to drive CloudCompare, a free open-source 3D point cloud and mesh processing program, through a command-line tool called cli-anything-cloudcompare. Once installed, the agent can create project files, load scans, subsample, crop, filter noise, compute normals, measure distances (C2C, C2M), run ICP alignment, and export to formats such as LAS, PLY, PCD, OBJ, STL and E57. The file describes 41 commands across 9 groups.
Great for
- Surveyors or engineers who process LiDAR or photogrammetry scans and want repeatable batch steps
- Developers building pipelines that convert or clean 3D point cloud data
- Users who want an AI agent to run CloudCompare operations without using the GUI
Skip it if
- People who do not have CloudCompare installed, since the tool wraps it and will not work alone
- Users who need a graphical interface or visual inspection, because this is command-line only
- Sensitive or confidential scan data sent through an agent with network access, since the file does not describe what leaves the machine
Try asking
- “Subsample my scan at 0.05 m spacing and save it as a LAS file”
- “Crop the cloud to a 10 by 10 by 5 metre bounding box and add the result to the project”
- “Remove statistical outliers from scan 0 and export as PLY”
- “Compute the C2C distance between two clouds and report the results”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
skills.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip skills.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip skills.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Always pass --json when the agent needs to parse output, and place global options like --project before the subcommand
- Use session undo or keep output files separate, since undo does not delete output files
- Check the command reference for exact option names before running batch operations on important data
What's inside
- SKILL.md
Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.