메뉴
Code execution and submission tools for DataNode (Black/Red) agents. Manages DataLoader code, runs assembled scripts, validates and grades submissions.
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
Dataset discovery and download toolkit covering HuggingFace, GitHub, Google, and academic paper search. Use when you need to find, inspect, or download ML datasets.
Tree-structured memory management for node-based exploration. Manages global memory, data link records, and per-node manifest (TL;DR + recordings). Use when agents need to persist, share, or retrieve exploration knowledge.
Data loading, cleaning, external-data merge, and validation-diagnosis guidance for black-node style ML agents. Use when a coding agent must improve data quality or integrate external datasets without changing the core model logic, especially for image tasks but also for tabular and text tasks.
Retrieval-Augmented Generation (RAG) skill for generic semantic search and knowledge retrieval. Use when you need to build or call vector-based search over your own documents using vector indexes (optional FAISS) and embedding models (local transformers or OpenAI embeddings), or when integrating LLMs with external knowledge bases in a project-agnostic way.
| name | operate-tools |
| description | Code execution and submission tools for DataNode (Black/Red) agents. Manages DataLoader code, runs assembled scripts, validates and grades submissions. |
| license | Complete terms in LICENSE.txt |
Code management, execution, validation, and grading for Black/Red nodes. Nodes can only modify code_{node_id}_dataloader.py; template is inherited and read-only.
base_dataloader.py + "\n\n" + code_{node_id}_dataloader.py + code_{node_id}_template.py
All commands require -w WORKSPACE -n NODE_ID.
| Tool | CLI |
|---|---|
read_code | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID read-code |
write_code | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID write-code --code "..." |
write_code (file) | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID write-code --code-file /path/to/file.py |
write_code (override) | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID write-code --code "..." --override |
fix_code | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID fix-code --old "..." --new "..." |
fix_code (all) | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID fix-code --old "..." --new "..." --replace-all |
| Tool | CLI |
|---|---|
run_code | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID run-code [--timeout 3600] |
| Tool | CLI |
|---|---|
validate_submission | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID validate |
grade_code | python scripts/operate_cli.py -w WORKSPACE -n NODE_ID grade [--timeout 300] |
{workspace}/
├── input/ # Input data (train.csv, test.csv, val.csv, ...)
├── submission/
│ └── submission_{node_id}.csv # Generated submission file
├── code_{node_id}_dataloader.py # YOUR code (modifiable)
├── code_{node_id}_template.py # Parent's template (read-only)
└── code_{node_id}.py # Assembled code (auto-generated on run)
code_{node_id}_dataloader.py must define a MyDataLoader(BaseDataLoader) class:
# No import statements needed - auto-assembled with base_dataloader.py
class MyDataLoader(BaseDataLoader):
def __init__(self, **kwargs):
super().__init__(**kwargs)
def setup(self):
# Load data, feature engineering, augmentation
# Must set self.train_data and self.test_data
self.train_data = ...
self.test_data = ...
def describe(self) -> str:
return "Description of data processing approach"
Constraints:
MyDataLoader, inheriting BaseDataLoaderBaseDataLoader (auto-assembled)input/val.csv if it exists; do not use train_test_split randomly1. read-code → View base + dataloader + template
2. write-code → Write MyDataLoader class
3. run-code → Execute (auto-assembles all components)
4. fix-code → Fix issues in dataloader
5. validate → Validate submission file
6. grade → Get final score
scripts/
├── operate_cli.py # CLI wrapper
├── for_datanode.py # Tool functions (from operate_submission/)
├── _submission_utils.py # Shared utilities (from operate_submission/)
├── base_dataloader.py # BaseDataLoader ABC
└── grading_server_runner.py # Standalone grading server