Find agent skills by outcome

DOCS

We keep all important docs in .agent folder and keep updating them, structure like below

This is a unity project implementing Here to slay the board game as an offline single-player game for windows 10, against 1 ai player.

Architecture is model-view.

docs/AGENT.md

generic skill

C++: ROS2 C++ nodes

performance optimization

target_companies: [Anduril

Palantir

Edge deployment (TensorRT

ONNX

focus_areas: Edge AI for military robotics

context-aware vision systems

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

12-Month AI and Computer Vision Roadmap for Defense Applications

{

Data

- Suggested follow-up actions (prototype scope

data prep

- Instead

suggest non-AI or hybrid alternatives (e.g.

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

bias checks)

- Recommendations for iteration (A/B testing

feedback loops)

### Version 1.5 (January 11

2026)

- Clear

grounded

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

fast

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

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

Data

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

excellent for self-hosting

- Keep it minimal and adaptable

including placeholders for iteration or error handling

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

very large context windows

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

writing quality

Current Best-in-Class Ranking (January 2026 – general guidance

always tailor to the process):