← Back to Skills Marketplace
isaachan

Late Brake

by Han Kai · GitHub ↗ · v0.0.3 · MIT-0
cross-platform ✓ Security Clean
175
Downloads
1
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install late-brake
Description
Pure CLI racing lap data analysis tool. Supports NMEA/VBO import, auto lap splitting, lap comparison, outputs structured comparison results for AI coaching....
README (SKILL.md)

Late Brake - Racing Lap Data Analysis Skill

Late Brake is a pure command-line (CLI) racing lap data analysis tool that provides:

  • Import lap data in NMEA 0183 / RaceChrono VBO formats
  • Auto split laps based on track start/finish line
  • Compare any two laps for time/speed differences by sector and corner
  • Output structured JSON comparison results ready for AI coach analysis

Dependencies

  • Python >= 3.10
  • Dependencies: click, pydantic, numpy, geographiclib, jsonschema, wcwidth

Dependencies are declared in SKILL.md, OpenClaw will handle automatic installation.

Entry Points

Source code is directly in scripts/ directory, can be imported directly:

import sys
import os
SKILL_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, os.path.join(SKILL_DIR, "scripts"))
from late_brake.cli import main as late_brake_main

Or execute directly as command-line:

# Load data file, list all laps
python -m late_brake.cli load \x3Cfile> --json

# Compare two laps, output JSON result
python -m late_brake.cli compare \x3Cfile1> \x3Clap1> \x3Cfile2> \x3Clap2> --json

Features

Feature Command Description
Load data file late-brake load \x3Cfile> Parse data, auto split laps, list all detected laps
Compare two laps late-brake compare \x3Cfile1> \x3Clap1> \x3Cfile2> \x3Clap2> Compare lap differences, output text table or JSON
Track management late-brake track list/info/add Manage built-in/custom tracks

JSON Output Schema

Full JSON schema definition: compare-json-schema.md

Use Cases

  • Racing drivers upload lap data files for comparison analysis
  • AI racing coach needs structured comparison data to give advice
  • Batch processing multiple lap data files
Usage Guidance
This skill appears to be what it claims: a local CLI lap-data analysis tool. Before installing, note that: (1) OpenClaw (or your environment) will install the declared Python dependencies into the agent's Python environment; (2) the tool will write cache files next to any data files you process (.{filename}.lb.json) and will store custom tracks under ~/.late-brake/tracks — only run it on files you trust and be comfortable with those writes; (3) there are minor non-security issues (e.g., a small bug where the 'add' action reports update after write and a version string mismatch) but nothing indicates malicious behavior; (4) no network endpoints, credentials, or external servers are contacted by the shipped code in the included files. If you require stricter isolation, run the skill in a sandboxed environment or inspect/modify the code prior to use.
Capability Analysis
Type: OpenClaw Skill Name: late-brake Version: 0.0.3 The 'late-brake' skill is a legitimate racing lap data analysis tool designed to parse NMEA and VBO GPS data files. The codebase implements lap splitting, track matching, and performance comparison logic using standard libraries like numpy and geographiclib. Security-wise, the tool includes proactive path traversal checks in 'scripts/late_brake/io/cache.py' and 'scripts/late_brake/io/track_store.py' when managing local cache files and user-defined track data. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match the code and instructions: parsers, lap splitter, comparator, track management and JSON output are present. Required capabilities (file read/write, local track data) align with the stated purpose. No unrelated credentials or external services are requested.
Instruction Scope
Runtime instructions and CLI code operate on user-supplied data files and local track definitions. The skill reads input files, creates per-file cache files named .{filename}.lb.json in the same directory, and writes user track JSON under ~/.late-brake/tracks. These file operations are expected for the stated purpose, but users should be aware that the skill will write caches next to source files and store custom tracks in the home directory. The code includes path-normalization checks to mitigate path traversal when creating caches and user track files.
Install Mechanism
No install spec is provided (instruction-only install), which is low risk from arbitrary downloads. SKILL.md declares Python package dependencies (click, pydantic, numpy, geographiclib, jsonschema, wcwidth) that OpenClaw will install; the bundle includes source Python files. The absence of a platform-level install recipe is not inherently risky, but installing the declared Python dependencies will modify the agent environment.
Credentials
The skill does not request environment variables, secrets, or external credentials. It only needs filesystem access (reading input files, writing caches and user track JSON) which is appropriate for a CLI data analysis tool.
Persistence & Privilege
The skill is not marked always:true and does not modify other skills or global agent settings. Its persistent artifacts are confined to ~/.late-brake/tracks and per-file .{filename}.lb.json caches; this level of persistence is proportional to the function.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install late-brake
  3. After installation, invoke the skill by name or use /late-brake
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.3
late-brake v0.0.3 - Complete "Tianma" track (上海天马赛车场) data. - Fix runtime bug in v0.0.2.
v0.0.2
- Version downgraded from 0.0.1 to 0.0.2 in SKILL.md. - Fix reported suspicious patterns.
v0.0.1
late-brake 1.0.0 – Initial release - Launches a pure CLI tool for racing lap data analysis. - Supports importing NMEA 0183 and RaceChrono VBO lap data. - Automatically splits laps and lists detected laps from data files. - Compares two laps to show sector and corner timing/speed differences. - Outputs structured JSON results for use with AI coaching. - Includes commands for track management.
v1.0.0
Initial release: core racing lap analysis features - NMEA/VBO import, lap splitting, sector/turn comparison
Metadata
Slug late-brake
Version 0.0.3
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 4
Frequently Asked Questions

What is Late Brake?

Pure CLI racing lap data analysis tool. Supports NMEA/VBO import, auto lap splitting, lap comparison, outputs structured comparison results for AI coaching.... It is an AI Agent Skill for Claude Code / OpenClaw, with 175 downloads so far.

How do I install Late Brake?

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

Is Late Brake free?

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

Which platforms does Late Brake support?

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

Who created Late Brake?

It is built and maintained by Han Kai (@isaachan); the current version is v0.0.3.

💬 Comments