Setup & Installation
openclaw skills install @aadipapp/fsd-secure-skill
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install fsd-secure-skill
What This Skill Does
A camera-only autonomous driving simulation agent. Two independent algorithms must agree a path is clear before the vehicle proceeds, and three consecutive safe frames are required before acceleration. Any uncertainty triggers an immediate emergency stop.
Requiring consensus between two independent algorithms plus temporal consistency across frames catches false positives that single-pass approaches miss.
When to use it
- Testing autonomous driving safety logic in a controlled simulation
- Validating dual-algorithm path detection before real-world deployment
- Prototyping fail-safe emergency stop behavior under edge cases
- Running regression tests on driving decision pipelines
- Benchmarking temporal consistency requirements for lane-change safety
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: drive
AGENT
- 1Initialize simulated camera feed and begin frame capture
- 2Run first-pass algorithm to assess whether the path ahead is clear
- 3Run second-pass algorithm independently on the same frame
- 4Check whether both passes agree on a safe path
- 5Verify result holds across 3 consecutive frames before accelerating, or trigger emergency stop if any check fails
OUTPUT
Simulation proceeds with autonomous driving, or halts with an emergency stop report if safety conditions are not met