القائمة
Hidden stage for magnetar. Initialize TASK_DIR structure, logs, status files, and stage directories.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | init |
| description | Hidden stage for magnetar. Initialize TASK_DIR structure, logs, status files, and stage directories. |
目标：创建隔离工作目录和审计文件。
TASK_DIR/
origin/
export/
compile/
simulate/
sdk/
python/
cpp/
runonboard/
package/
cache/
acquire/
toolchain/
task.md
analysis.md
TASK_DIR 未指定，创建 todos/work/<timestamp>-<model-name>/。origin/ 中 ACQUIRE 产物。task.md：
INITanalysis.md：
uv 可用性；缺少 uv 时 STOP，不得降级到 python -m venv、virtualenv 或 conda。TASK_DIR 内，并用 uv venv <path> 创建。uv pip install --python <venv>/bin/python ...。python -m venv、virtualenv 或 conda 创建/管理任务环境。初始化后如果缺少 TARGET_HARDWARE 或模型主文件，停止等待用户补充。
Hidden stage for magnetar. Assemble validated AXMODEL, SDKs, reports, and usage documentation into a customer delivery directory.
Convert remote or local AI models into AXera AXMODEL packages with Python and C++ SDKs for customer delivery. Use when Codex must acquire a model from Git/HuggingFace/URL/local path, export ONNX, compile with Pulsar2, simulate/validate AXMODEL accuracy, optionally run on AX hardware, generate SDKs, or package deployment artifacts.
Hidden stage for magnetar. Compile static ONNX to AXMODEL with Pulsar2 and record compile artifacts.
Hidden stage for magnetar. Export the acquired model to static-shape ONNX, validate it against the source model, and generate model_meta.json plus calibration data.
Hidden stage for magnetar. Acquire a remote or local model into TASK_DIR/origin without modifying the source.
Hidden stage for magnetar. Generate customer-facing Python and C++ inference SDKs from model_meta.json and AXMODEL artifacts.