cli-anything-cloudanalyzer

Compare point clouds and trajectories against reference data using CLI metrics.

Updated May 7, 2026
One-click install
npx skills add https://github.com/dawsonblock/JUDGE_ATLAS --skill cli-anything-cloudanalyzer-dawsonblock
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cli-anything-cloudanalyzer
Source: https://github.com/dawsonblock/JUDGE_ATLAS/tree/main/external/CLI-Anything-main/cloudanalyzer/agent-harness/cli_anything/cloudanalyzer/skills
Command: npx skills add https://github.com/dawsonblock/JUDGE_ATLAS --skill cli-anything-cloudanalyzer-dawsonblock

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires cloudanalyzer.

What problem does it solve?

It solves the problem of manually evaluating and quality-gating mapping/localization/perception outputs by providing a standardized, agent-friendly CLI for comparing point clouds and trajectories.

Core Features & Use Cases

  • Point cloud evaluation: Computes similarity and error metrics such as Chamfer distance, F1 score, AUC, and Hausdorff distance for source-vs-reference comparisons.
  • Trajectory evaluation: Measures trajectory accuracy using metrics like ATE, RPE, drift, and coverage, enabling map-to-motion validation.
  • Config-driven quality gates & baselines: Runs QA from a config, promotes/rejects candidate baselines, and keeps a history for iterative improvement.

Quick Start

Run cli-anything-cloudanalyzer evaluate run source.pcd reference.pcd to score your point cloud against the reference using the built-in metrics.

Frequently Asked Questions about cli-anything-cloudanalyzer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I compare point clouds against a reference for quality assurance?

To compare point clouds for quality assurance, use a CLI harness to evaluate source files against reference data, computing metrics like Chamfer distance, F1 score, and Hausdorff distance to determine similarity and errors.

What metrics are used for trajectory evaluation in mapping and localization?

Trajectory evaluation measures mapping and localization accuracy using metrics like ATE, RPE, drift, and coverage, enabling validation of map-to-motion accuracy against reference trajectory data.

Can I automate point cloud QA with config-driven quality gates?

You can automate point cloud QA by running evaluations from a config file with thresholded acceptance criteria, allowing you to promote or reject candidate baselines while keeping a history for iterative improvement.

Does this point cloud evaluation tool output JSON for agent consumption?

The point cloud evaluation tool supports structured evaluation commands with JSON outputs specifically designed for agent consumption, enabling automated quality gating workflows.

Do I need a command-line harness to validate ground segmentation outputs?

You need a command-line harness to validate ground segmentation outputs, as it supports the structured evaluation commands and thresholded acceptance criteria required for automated point cloud quality gating.