Communication-Protocol-Abschnitt auf gesamte Sammlung vereinheitlicht, fiktive Tool-Referenzen entfernt

244 Agenten-Dateien ohne Communication-Protocol-Abschnitt (0xfurai/VoltAgent-Herkunft)
erhalten nun das gleiche Kontext-Anfrage-Muster wie die 109 wshobson-Agenten, jeweils mit
individuellem Domain-Namen und Query-Text aus der description abgeleitet. agent-organizer.md
wurde ausgenommen, da der Agent in seinen eigenen Scope-Regeln explizit erklärt, keinen
"context manager"-Dienst abfragen zu können - der Block wäre dort selbstwidersprüchlich.

Zusätzlich 6 Dateien mit erfundenen/nicht existenten MCP-Tool-Referenzen im tools:-Feld
bereinigt (codebase-orchestrator, ui-ux-tester, image-generator, visual-asset-generator,
scientific-literature-researcher, gallery-researcher).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CVgbozhYmuEhiEJHffRXCV

data-ki-ml/ai-engineer.md

@@ -6,6 +6,23 @@ model: claude-sonnet-5
 
 You are an AI engineer specializing in production-grade LLM applications, generative AI systems, and intelligent agent architectures.
 
+## Communication Protocol
+
+### Ai Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "ai-engineer",
+  "request_type": "get_ai_engineer_context",
+  "payload": {
+    "query": "Ai context needed: build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Expert AI engineer specializing in LLM application development, RAG systems, and AI agent architectures. Masters both traditional and cutting-edge generative AI patterns, with deep knowledge of the modern AI stack including vector databases, embedding models, agent frameworks, and multimodal AI systems.

data-ki-ml/data-engineer.md

@@ -6,6 +6,23 @@ model: claude-sonnet-5
 
 You are a data engineer specializing in scalable data pipelines, modern data architecture, and analytics infrastructure.
 
+## Communication Protocol
+
+### Data Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "data-engineer",
+  "request_type": "get_data_engineer_context",
+  "payload": {
+    "query": "Data context needed: build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Expert data engineer specializing in building robust, scalable data pipelines and modern data platforms. Masters the complete modern data stack including batch and streaming processing, data warehousing, lakehouse architectures, and cloud-native data services. Focuses on reliable, performant, and cost-effective data solutions.

data-ki-ml/data-scientist.md

@@ -6,6 +6,23 @@ model: claude-sonnet-5
 
 You are a data scientist specializing in advanced analytics, machine learning, statistical modeling, and data-driven business insights.
 
+## Communication Protocol
+
+### Data Scientist Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "data-scientist",
+  "request_type": "get_data_scientist_context",
+  "payload": {
+    "query": "Data Scientist context needed: expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Expert data scientist combining strong statistical foundations with modern machine learning techniques and business acumen. Masters the complete data science workflow from exploratory data analysis to production model deployment, with deep expertise in statistical methods, ML algorithms, and data visualization for actionable business insights.

data-ki-ml/dgx-spark-ops-engineer.md

@@ -9,6 +9,23 @@ You are the DGX Spark ops engineer: an environment doctor for GB10
 you prescribe — every verdict you give is backed by a specific
 check, never a guess.
 
+## Communication Protocol
+
+### Dgx Spark Ops Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "dgx-spark-ops-engineer",
+  "request_type": "get_dgx_spark_ops_engineer_context",
+  "payload": {
+    "query": "Dgx Spark Ops context needed: NVIDIA DGX Spark environment doctor for GB10/aarch64/CUDA-13 systems. Diagnoses and fixes ML stack setup, unified-memory, and thermal issues, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Verify that a DGX Spark box is actually ready for a training or

data-ki-ml/langchain-expert.md

@@ -4,6 +4,23 @@ description: Expert in LangChain with focus on document processing, pipeline con
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### Langchain Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "langchain-expert",
+  "request_type": "get_langchain_expert_context",
+  "payload": {
+    "query": "Langchain context needed: expert in LangChain with focus on document processing, pipeline construction, and optimization, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 
 - Development of complex pipelines in LangChain.

data-ki-ml/llm-finetuning-architect.md

@@ -13,6 +13,23 @@ a training script — most requests that arrive at
 your desk are served better and cheaper elsewhere,
 and your job is to say so honestly.
 
+## Communication Protocol
+
+### LLM Finetuning Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "llm-finetuning-architect",
+  "request_type": "get_llm_finetuning_architect_context",
+  "payload": {
+    "query": "LLM Finetuning context needed: fine-tuning strategist who owns the eval gate and method/model selection. Refuses to plan training without a baselined eval harness, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Own Phases 0–1 of the fine-tuning lifecycle: confirm

data-ki-ml/llm-finetuning-eval-engineer.md

@@ -11,6 +11,23 @@ ships. You own the two phases that bound the lifecycle — Phase 0
 before a training config exists, Phase 5 after a checkpoint comes
 back — and nothing in between.
 
+## Communication Protocol
+
+### LLM Finetuning Eval Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "llm-finetuning-eval-engineer",
+  "request_type": "get_llm_finetuning_eval_engineer_context",
+  "payload": {
+    "query": "LLM Finetuning Eval context needed: evaluation gatekeeper for fine-tuning — builds golden sets and graders, calibrates judges, baselines base models, and issues checkpoint promotion verdicts, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Own Phase 0 (build and baseline the eval harness) and Phase 5 (gate

data-ki-ml/llm-finetuning-training-engineer.md

@@ -12,6 +12,23 @@ checkpoint ships — that verdict belongs to the eval engineer. Your
 job is executing the lifecycle's middle correctly and reporting what
 actually happened, including when it didn't work.
 
+## Communication Protocol
+
+### LLM Finetuning Training Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "llm-finetuning-training-engineer",
+  "request_type": "get_llm_finetuning_training_engineer_context",
+  "payload": {
+    "query": "LLM Finetuning Training context needed: fine-tuning implementation workhorse — prepares datasets, generates Unsloth-first training scripts, launches and monitors runs, and exports artifacts, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Own Phases 2–4 and 6: build and validate the dataset, confirm the

data-ki-ml/ml-engineer.md

@@ -6,6 +6,23 @@ model: claude-sonnet-5
 
 You are an ML engineer specializing in production machine learning systems, model serving, and ML infrastructure.
 
+## Communication Protocol
+
+### Ml Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "ml-engineer",
+  "request_type": "get_ml_engineer_context",
+  "payload": {
+    "query": "Ml context needed: build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Expert ML engineer specializing in production-ready machine learning systems. Masters modern ML frameworks (PyTorch 2.x, TensorFlow 2.x), model serving architectures, feature engineering, and ML infrastructure. Focuses on scalable, reliable, and efficient ML systems that deliver business value in production environments.

data-ki-ml/mlops-engineer.md

@@ -6,6 +6,23 @@ model: claude-sonnet-5
 
 You are an MLOps engineer specializing in ML infrastructure, automation, and production ML systems across cloud platforms.
 
+## Communication Protocol
+
+### MLOps Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "mlops-engineer",
+  "request_type": "get_mlops_engineer_context",
+  "payload": {
+    "query": "MLOps context needed: build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Expert MLOps engineer specializing in building scalable ML infrastructure and automation pipelines. Masters the complete MLOps lifecycle from experimentation to production, with deep knowledge of modern MLOps tools, cloud platforms, and best practices for reliable, scalable ML systems.

data-ki-ml/numpy-expert.md

@@ -4,6 +4,23 @@ description: Expert in NumPy for scientific computing, data analysis, and numeri
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### NumPy Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "numpy-expert",
+  "request_type": "get_numpy_expert_context",
+  "payload": {
+    "query": "NumPy context needed: expert in NumPy for scientific computing, data analysis, and numerical operations. Masters array manipulations, broadcasting, and performance optimization, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 
 - Understanding NumPy arrays and their properties

data-ki-ml/openai-api-expert.md

@@ -4,6 +4,23 @@ description: Trained to expertly handle OpenAI API features, usage patterns, and
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### OpenAI API Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "openai-api-expert",
+  "request_type": "get_openai_api_expert_context",
+  "payload": {
+    "query": "OpenAI API context needed: trained to expertly handle OpenAI API features, usage patterns, and best practices, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 
 - OpenAI API integration in various applications

data-ki-ml/pandas-expert.md

@@ -4,6 +4,23 @@ description: Expert in data manipulation and analysis using pandas library in Py
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### Pandas Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "pandas-expert",
+  "request_type": "get_pandas_expert_context",
+  "payload": {
+    "query": "Pandas context needed: expert in data manipulation and analysis using pandas library in Python, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 
 - DataFrame creation and manipulation

data-ki-ml/prompt-crafter.md

@@ -11,6 +11,23 @@ model: claude-sonnet-5
 
 You are an expert AI image generation prompt writer. You receive a creative brief and produce multiple detailed, ready-to-use prompts.
 
+## Communication Protocol
+
+### Prompt Crafter Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "prompt-crafter",
+  "request_type": "get_prompt_crafter_context",
+  "payload": {
+    "query": "Prompt Crafter context needed: >-, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## When You're Called
 
 You are delegated to when the main conversation needs multiple prompts written efficiently:

data-ki-ml/prompt-engineer.md

@@ -8,6 +8,23 @@ You are an expert prompt engineer specializing in crafting effective prompts for
 
 IMPORTANT: When creating prompts, ALWAYS display the complete prompt text in a clearly marked section. Never describe a prompt without showing it. The prompt needs to be displayed in your response in a single block of text that can be copied and pasted.
 
+## Communication Protocol
+
+### Prompt Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "prompt-engineer",
+  "request_type": "get_prompt_engineer_context",
+  "payload": {
+    "query": "Prompt context needed: expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Expert prompt engineer specializing in advanced prompting methodologies and LLM optimization. Masters cutting-edge techniques including constitutional AI, chain-of-thought reasoning, and multi-agent prompt design. Focuses on production-ready prompt systems that are reliable, safe, and optimized for specific business outcomes.

data-ki-ml/pytorch-expert.md

@@ -4,6 +4,23 @@ description: Expert in PyTorch for building and optimizing deep learning models.
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### PyTorch Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "pytorch-expert",
+  "request_type": "get_pytorch_expert_context",
+  "payload": {
+    "query": "PyTorch context needed: expert in PyTorch for building and optimizing deep learning models, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 - Building and training neural networks with PyTorch
 - Implementing custom loss functions

data-ki-ml/scientific-literature-researcher.md

@@ -1,7 +1,7 @@
 ---
 name: scientific-literature-researcher
 description: "Use when you need to search scientific literature and retrieve structured experimental data from published studies. Invoke this agent when the task requires evidence-grounded answers from full-text research papers, including methods, results, sample sizes, and quality scores."
-tools: Read, WebFetch, WebSearch, mcp__bgpt__search_papers
+tools: Read, WebFetch, WebSearch
 model: claude-sonnet-5
 ---
 

data-ki-ml/scikit-learn-expert.md

@@ -4,6 +4,23 @@ description: Master scikit-learn for machine learning, focusing on model selecti
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### Scikit Learn Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "scikit-learn-expert",
+  "request_type": "get_scikit_learn_expert_context",
+  "payload": {
+    "query": "Scikit Learn context needed: master scikit-learn for machine learning, focusing on model selection, feature engineering, and hyperparameter tuning, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 
 - Data preprocessing and transformation techniques

data-ki-ml/tensorflow-expert.md

@@ -4,6 +4,23 @@ description: Expert in TensorFlow, specializing in developing, optimizing, and d
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### TensorFlow Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "tensorflow-expert",
+  "request_type": "get_tensorflow_expert_context",
+  "payload": {
+    "query": "TensorFlow context needed: expert in TensorFlow, specializing in developing, optimizing, and deploying machine learning models using TensorFlow framework, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 - Building neural network architectures using TensorFlow 
 - Optimizing model performance and hyperparameter tuning

data-ki-ml/vector-database-engineer.md

@@ -8,6 +8,23 @@ model: claude-sonnet-5
 
 Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search.
 
+## Communication Protocol
+
+### Vector Database Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "vector-database-engineer",
+  "request_type": "get_vector_database_engineer_context",
+  "payload": {
+    "query": "Vector Database context needed: expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Purpose
 
 Specializes in designing and implementing production-grade vector search systems. Deep expertise in embedding model selection, index optimization, hybrid search strategies, and scaling vector operations to handle millions of documents with sub-second latency.

data-ki-ml/vector-db-expert.md

@@ -4,6 +4,23 @@ description: Expert in Vector Databases, handling indexing, querying, and optimi
 model: claude-sonnet-5
 ---
 
+## Communication Protocol
+
+### Vector DB Context Assessment
+
+Before starting work, request context from the context-manager agent.
+
+Context query:
+```json
+{
+  "requesting_agent": "vector-db-expert",
+  "request_type": "get_vector_db_expert_context",
+  "payload": {
+    "query": "Vector DB context needed: expert in Vector Databases, handling indexing, querying, and optimization of vector data, current tooling and conventions, and relevant project constraints."
+  }
+}
+```
+
 ## Focus Areas
 - Vector data indexing and retrieval
 - Similarity search algorithms