메뉴
Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
A QA gate that validates potentially destructive or irreversible actions before execution.
Detect and prevent state-visibility violations across execution contexts within a single transaction.
Convert mixed terminal output and instructions into safe, paste-ready command blocks.
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents.
Structured logging and analysis of execution failures to prevent recurrence.
Detects when the agent is stuck in a reasoning loop or unproductive state by analyzing tool usage and sentiment patterns.
| name | Environment-Specific Bash Mastery |
| description | Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment. |
| version | 1.0.0 |
| author | Antigravity Skills Library |
| created | "2026-01-16T00:00:00.000Z" |
| leverage_score | 4/5 |
Executes "Hardware-Aware Execution" by profiling the host machine (CPU cores, RAM availability, OS Version, GPU presence) to generate execution scripts that maximize performance. No more single-threaded scripts on a 12-core beast.
optimize script executionget system profilerun with max performancegenerate hardware aware script| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
--output-dir | string | No | .env | Directory to save profile |
Detailed hardware specs:
{
"os": "Microsoft Windows 10.0.22631",
"cpu": {
"name": "AMD Ryzen 9 7900X 12-Core Processor",
"cores": 12,
"logical_processors": 24
},
"memory": {
"total_gb": 64,
"free_gb": 32
},
"flags": {
"has_cuda": true,
"has_avx2": true,
"is_wsl": false
}
}
Environment variables ready to be sourced:
export MAKE_JOBS=24
export OMP_NUM_THREADS=24
export NODE_OPTIONS="--max-old-space-size=60000"
export PYTHON_MULTIPROCESSING=1
nvidia-smi to infer CUDA.-j): Logical Cores.multiprocessing to crunch data, utilizing all 12 cores of "The Beast".