Find agent skills by outcome

@./.github/instructions/ts.instructions.md

@./.github/instructions/core.instructions.md

description: Use this agent when implementing AI/ML features

integrating language models

Hardware: Edge TPU

Jetson Nano/Orin integration

C++: ROS2 C++ nodes

performance optimization

Edge deployment (TensorRT

ONNX

focus_areas: Edge AI for military robotics

context-aware vision systems

target_companies: [Anduril

Palantir

target_skills: Edge AI optimization

ROS2

hardware: ESP32

RP2040

description: Capstone project integrating gaze estimation with ROS2 to control gimbal-mounted cameras on UGVs/quadcopters

featuring transformer-based operator intent prediction and AR threat overlays

- Elevated Grok to top-tier in AI engine recommendations (real-time

tool use

### Version 1.5 (January 11

2026)

12-Month AI and Computer Vision Roadmap for Defense Applications

{

- Clear

grounded

Data

- Suggested follow-up actions (prototype scope

data prep

- Recommendations for iteration (A/B testing

feedback loops)

Enhancement: Refactor Reva CLI with prompts

The current CLI is a bit cumbersome to use with users having to type commands

- Key risks or dependencies to monitor (e.g.

bias checks)

- Lightweight/chat-only models (older 7B–13B models

mini variants) — usually lack depth/context/tool reliability

- Mistral Large 2 / Devstral — Very strong price/performance

fast

Data

- Llama 4 / Llama 405B variants (Meta) — Best open-source frontier performance

excellent for self-hosting

- Gemini 2.5 Pro / Flash (Google) — Outstanding multimodal (especially video/document understanding)

very large context windows

Data

- Grok 3 / Grok 4 (xAI) — Excellent reasoning

real-time knowledge via X

- Claude 4 Opus/Sonnet (Anthropic) — Exceptional long-form reasoning

writing quality