field-keywords
4
总安装量
4
周安装量
#47798
全站排名
安装命令
npx skills add https://github.com/orientpine/honeypot --skill field-keywords
Agent 安装分布
mcpjam
4
claude-code
4
replit
4
junie
4
windsurf
4
zencoder
4
Skill 文档
Field Keywords Skill
Overview
This skill provides domain-specific keyword mappings for automatic research domain detection and chapter content mapping. It includes three domain keyword sets:
- ROS2: Robot Operating System 2 development
- AI/ML: Artificial Intelligence and Machine Learning
- GENERAL: Generic engineering/research (fallback)
ROS2 Keywords
{
"domain": "ROS2",
"description": "ROS2 (Robot Operating System 2) ê¸°ë° ë¡ë´ ìì¤í
ê°ë° ë¶ì¼",
"chapter_keywords": {
"chapter_1_hardware": {
"title": "íëì¨ì´ íµí© ë° ì¼ì ìµí©",
"primary_keywords": ["CAN", "SocketCAN", "CANopen", "ì¼ì", "ê²½ì¬ê³", "inclinometer", "ìë ¥ì¼ì", "ì ì", "íµì ", "ì¸í°íì´ì¤"],
"secondary_keywords": ["can_bridge", "SDO", "PDO", "ë¹í¸ë ì´í¸", "ë²ì¤", "ë©í°ì¤ë ë", "íìì¤í¬í", "ë기í"]
},
"chapter_2_computation": {
"title": "기구í ì°ì° ìì¤í
",
"primary_keywords": ["기구í", "kinematics", "ì 기구í", "ì기구í", "forward", "inverse", "DOF", "ìì ë"],
"secondary_keywords": ["ë³í", "ì¢í", "ê´ì ", "ë§í¬", "ìë³´", "elbow", "í´ìì ", "ìì¹ì "]
},
"chapter_3_generation": {
"title": "궤ì ìì± ìì¤í
",
"primary_keywords": ["궤ì ", "trajectory", "ê²½ë¡", "path", "ê³í", "planning", "ìì±", "generator"],
"secondary_keywords": ["ìíì¤", "ì¤ì¼ì¤ë§", "ë°°ì¹", "batch", "í¬ì¸í¸", "ì¨ì´í¬ì¸í¸"]
},
"chapter_4_control": {
"title": "ì ì´ ìì¤í
",
"primary_keywords": ["ì ì´", "control", "PI", "PID", "ê²ì¸", "gain", "í¼ëë°±", "feedback"],
"secondary_keywords": ["Kp", "Ki", "Kd", "ì¤ì¼ì¤ë§", "íë", "threshold", "ì¤ì°¨", "error"]
},
"chapter_5_ai": {
"title": "AI ê°ííìµ ìì¤í
",
"primary_keywords": ["AI", "ê°ííìµ", "reinforcement", "learning", "ì ì±
", "policy", "ìí¼ìë", "episode"],
"secondary_keywords": ["ê´ì¸¡", "observation", "ì¡ì
", "action", "리ìë", "reward", "ë¤í¸ìí¬", "ì¶ë¡ ", "inference"]
},
"chapter_6_interface": {
"title": "ROS2 íµì ì¸í°íì´ì¤",
"primary_keywords": ["ë©ìì§", "msg", "ìë¹ì¤", "service", "ì¡ì
", "action", "í í½", "topic"],
"secondary_keywords": ["publisher", "subscriber", "client", "server", "QoS", "callback", "executor"]
},
"chapter_7_integration": {
"title": "ìì¤í
íµí© ë° ê²ì¦",
"primary_keywords": ["HMI", "GUI", "ì뮬ë ì´ì
", "simulation", "í
ì¤í¸", "test", "ê²ì¦", "validation"],
"secondary_keywords": ["PyQt", "Rviz", "Gazebo", "모ëí°ë§", "ìê°í", "visualization"]
},
"chapter_8_safety": {
"title": "ìì ì± ë° ì¤ë¥ ì²ë¦¬",
"primary_keywords": ["ìì ", "safety", "ë¹ì", "emergency", "ìë¬", "error", "복구", "recovery"],
"secondary_keywords": ["ì¬ìë", "retry", "íììì", "timeout", "ë°±ì¤í", "backoff", "ìê³ê°", "threshold"]
}
},
"domain_specific_terms": {
"generic_to_domain": {
"모ë": "ë
¸ë(node)",
"ì²ë¦¬": "í¼ë¸ë¦¬ì(publish)",
"ì¤ì ": "íë¼ë¯¸í°(parameter)",
"ì°ê²°": "í í½/ìë¹ì¤(topic/service)",
"ì
ë ¥": "구ë
(subscribe)",
"ì¶ë ¥": "ë°í(publish)",
"í¨ì í¸ì¶": "ìë¹ì¤ í¸ì¶(service call)",
"ë¹ë기 ìì
": "ì¡ì
(action)"
}
},
"common_packages": [
"excavator_msgs",
"excavator_signal_manager",
"excavator_trajectory_planning",
"excavator_control",
"excavator_task_management"
],
"common_file_extensions": [".py", ".cpp", ".hpp", ".yaml", ".launch.py", ".msg", ".srv", ".action"]
}
AI/ML Keywords
{
"domain": "AI_ML",
"description": "AI/ML (ì¸ê³µì§ë¥/머ì ë¬ë) ê¸°ë° ìì¤í
ê°ë° ë¶ì¼",
"chapter_keywords": {
"chapter_1_hardware": {
"title": "ë°ì´í° ìì§ ë° ì ì²ë¦¬ ìì¤í
",
"primary_keywords": ["ë°ì´í°", "data", "ìì§", "collection", "ì ì²ë¦¬", "preprocessing", "íì´íë¼ì¸", "pipeline"],
"secondary_keywords": ["ë°°ì¹", "batch", "ì¤í¸ë¦¬ë°", "streaming", "ETL", "ì ê·í", "normalization"]
},
"chapter_2_computation": {
"title": "ëª¨ë¸ ìí¤í
ì² ì¤ê³",
"primary_keywords": ["모ë¸", "model", "ìí¤í
ì²", "architecture", "ë ì´ì´", "layer", "ë¤í¸ìí¬", "network"],
"secondary_keywords": ["CNN", "RNN", "Transformer", "attention", "embedding", "encoder", "decoder"]
},
"chapter_3_generation": {
"title": "íìµ ë°ì´í° ìì± ìì¤í
",
"primary_keywords": ["ìì±", "generation", "augmentation", "ì¦ê°", "í©ì±", "synthetic", "ìíë§", "sampling"],
"secondary_keywords": ["ë¼ë²¨ë§", "labeling", "ì´ë
¸í
ì´ì
", "annotation", "ë°¸ë°ì±", "balancing"]
},
"chapter_4_control": {
"title": "íìµ íë¡ì¸ì¤ ì ì´",
"primary_keywords": ["íìµ", "training", "ìµì í", "optimization", "ìì¤", "loss", "ìì í", "backpropagation"],
"secondary_keywords": ["íìµë¥ ", "learning_rate", "ìí", "epoch", "ë°°ì¹", "batch_size", "ê·¸ëëì¸í¸", "gradient"]
},
"chapter_5_ai": {
"title": "ì¶ë¡ ë° ë°°í¬ ìì¤í
",
"primary_keywords": ["ì¶ë¡ ", "inference", "ë°°í¬", "deployment", "ìë¹", "serving", "ì측", "prediction"],
"secondary_keywords": ["ONNX", "TensorRT", "ììí", "quantization", "ê°ìí", "acceleration"]
},
"chapter_6_interface": {
"title": "API ë° ìë¹ì¤ ì¸í°íì´ì¤",
"primary_keywords": ["API", "REST", "gRPC", "ìëí¬ì¸í¸", "endpoint", "ìì²", "request", "ìëµ", "response"],
"secondary_keywords": ["FastAPI", "Flask", "Docker", "Kubernetes", "ë§ì´í¬ë¡ìë¹ì¤"]
},
"chapter_7_integration": {
"title": "ëª¨ë¸ íê° ë° ê²ì¦",
"primary_keywords": ["íê°", "evaluation", "ê²ì¦", "validation", "í
ì¤í¸", "test", "ë©í¸ë¦", "metric"],
"secondary_keywords": ["ì íë", "accuracy", "ì ë°ë", "precision", "ì¬íì¨", "recall", "F1", "AUC"]
},
"chapter_8_safety": {
"title": "ëª¨ë¸ ìì ì± ë° ëª¨ëí°ë§",
"primary_keywords": ["모ëí°ë§", "monitoring", "ë리íí¸", "drift", "ì´ìíì§", "anomaly", "ë¡ê¹
", "logging"],
"secondary_keywords": ["MLOps", "ë²ì ê´ë¦¬", "versioning", "롤백", "rollback", "A/Bí
ì¤í¸"]
}
},
"domain_specific_terms": {
"generic_to_domain": {
"모ë": "모ë/ë ì´ì´(module/layer)",
"ì²ë¦¬": "ì¶ë¡ (inference)",
"ì¤ì ": "íì´í¼íë¼ë¯¸í°(hyperparameter)",
"ì°ê²°": "ë ì´ì´ ì°ê²°(layer connection)",
"ì
ë ¥": "ì
ë ¥ í
ì(input tensor)",
"ì¶ë ¥": "ì¶ë ¥ í
ì(output tensor)",
"ë°ë³µ": "ìí(epoch)",
"ì ì¥": "ì²´í¬í¬ì¸í¸(checkpoint)"
}
},
"common_frameworks": [
"PyTorch",
"TensorFlow",
"Keras",
"scikit-learn",
"Hugging Face",
"JAX"
],
"common_file_extensions": [".py", ".ipynb", ".onnx", ".pt", ".pth", ".h5", ".yaml", ".json"]
}
GENERAL Keywords
{
"domain": "GENERAL",
"description": "ë²ì© ì°êµ¬/ê°ë° ë¶ì¼ (í¹ì ëë©ì¸ ê°ì§ ì¤í¨ ì ì ì©)",
"chapter_keywords": {
"chapter_1_hardware": {
"title": "ìì¤í
ì¸íë¼ êµ¬ì¶",
"primary_keywords": ["ì¼ì", "sensor", "íëì¨ì´", "hardware", "ì¸í°íì´ì¤", "interface", "íµì ", "communication"],
"secondary_keywords": ["íë¡í ì½", "protocol", "ì°ê²°", "connection", "ëë¼ì´ë²", "driver", "í¬í¸", "port"]
},
"chapter_2_computation": {
"title": "íµì¬ ì°ì° 모ë",
"primary_keywords": ["ìê³ ë¦¬ì¦", "algorithm", "ì°ì°", "computation", "ì²ë¦¬", "processing", "ë³í", "transformation"],
"secondary_keywords": ["í¨ì", "function", "ê³ì°", "calculation", "ìì", "formula", "모ë¸", "model"]
},
"chapter_3_generation": {
"title": "ë°ì´í°/ê²°ê³¼ ìì± ìì¤í
",
"primary_keywords": ["ìì±", "generation", "ê³í", "planning", "ì¤ì¼ì¤", "schedule", "ìíì¤", "sequence"],
"secondary_keywords": ["íì´íë¼ì¸", "pipeline", "ìí¬íë¡ì°", "workflow", "ìëí", "automation"]
},
"chapter_4_control": {
"title": "ì ì´ ë° ì¡°ì ìì¤í
",
"primary_keywords": ["ì ì´", "control", "ì¡°ì ", "regulation", "í¼ëë°±", "feedback", "루í", "loop"],
"secondary_keywords": ["ì¤ì ê°", "setpoint", "ì¤ì°¨", "error", "ë³´ì ", "correction", "ìì í", "stabilization"]
},
"chapter_5_ai": {
"title": "ì§ë¥í ìì¤í
",
"primary_keywords": ["AI", "ML", "íìµ", "learning", "ì측", "prediction", "ë¶ë¥", "classification"],
"secondary_keywords": ["모ë¸", "model", "íë ¨", "training", "ì¶ë¡ ", "inference", "ë°ì´í°", "data"]
},
"chapter_6_interface": {
"title": "ì¸í°íì´ì¤ ì¤ê³",
"primary_keywords": ["API", "ì¸í°íì´ì¤", "interface", "íë¡í ì½", "protocol", "íµì ", "communication"],
"secondary_keywords": ["ë©ìì§", "message", "ìì²", "request", "ìëµ", "response", "í¬ë§·", "format"]
},
"chapter_7_integration": {
"title": "ìì¤í
íµí© ë° ê²ì¦",
"primary_keywords": ["í
ì¤í¸", "test", "ê²ì¦", "verification", "íµí©", "integration", "ì뮬ë ì´ì
", "simulation"],
"secondary_keywords": ["ì ë", "unit", "E2E", "ì±ë¥", "performance", "벤ì¹ë§í¬", "benchmark"]
},
"chapter_8_safety": {
"title": "ìì ì± ë° ì¤ë¥ ì²ë¦¬",
"primary_keywords": ["ìì ", "safety", "ì¤ë¥", "error", "ìì¸", "exception", "복구", "recovery"],
"secondary_keywords": ["ë¡ê¹
", "logging", "모ëí°ë§", "monitoring", "ì림", "alert", "ë°±ì
", "backup"]
}
},
"domain_specific_terms": {
"generic_to_domain": {
"모ë": "모ë(module)",
"ì²ë¦¬": "ì²ë¦¬(processing)",
"ì¤ì ": "ì¤ì (configuration)",
"ì°ê²°": "ì°ê²°(connection)",
"ì
ë ¥": "ì
ë ¥(input)",
"ì¶ë ¥": "ì¶ë ¥(output)"
}
},
"detection_hints": {
"ros2_indicators": ["ROS", "ros2", "node", "topic", "service", "action", "msg", "launch"],
"ai_ml_indicators": ["PyTorch", "TensorFlow", "model", "training", "inference", "neural", "deep learning"],
"physics_indicators": ["quantum", "particle", "field", "energy", "wave", "equation"],
"biotech_indicators": ["gene", "protein", "cell", "DNA", "RNA", "assay", "sequencing"]
}
}
Usage
Domain Detection
Use keyword frequency analysis to detect research domain:
1. Count keyword occurrences in research notes
2. Calculate domain scores:
- primary_keyword * 3 points
- secondary_keyword * 1 point
3. Select domain with highest score
4. If score difference < 30%, use GENERAL
Chapter Mapping
Use chapter keywords to map content to chapters:
1. For each file, calculate chapter relevance scores
2. Match file headers/keywords to chapter keywords
3. Assign files to chapters with highest scores
4. Calculate sufficiency score (0-100) per chapter
5. Skip chapters with score < 30
Domain-Specific Term Substitution
Replace generic terms with domain-specific terms in generated reports:
ROS2: "모ë" â "ë
¸ë(node)"
AI/ML: "모ë" â "모ë/ë ì´ì´(module/layer)"
GENERAL: "모ë" â "모ë(module)"
File Naming Convention
Keyword files follow the pattern: {domain_normalized}_keywords.json
Normalization rules:
- Lowercase domain name
- Replace “/” with “_”
- Examples:
- “ROS2” â “ros2_keywords.json”
- “AI/ML” â “ai_ml_keywords.json”
- “GENERAL” â “general_keywords.json”