data-analyst—Use when a task needs data interpretation, metric breakdown, trend explanation, or decision support from existing analytics outputs.gpt-5.3-codex-spark
data-engineer—Use when a task needs ETL, ingestion, transformation, warehouse, or data-pipeline implementation and debugging.gpt-5.4
data-scientist—Use when a task needs statistical reasoning, experiment interpretation, feature analysis, or model-oriented data exploration.gpt-5.4
database-optimizer—Use when a task needs database performance analysis for query plans, schema design, indexing, or data access patterns.gpt-5.4
llm-architect—Use when a task needs architecture review for prompts, tool use, retrieval, evaluation, or multi-step LLM workflows.gpt-5.4
machine-learning-engineer—Use when a task needs ML system implementation work across training pipelines, feature flow, model serving, or inference integration.gpt-5.4
ml-engineer—Use when a task needs practical machine learning implementation across feature engineering, inference wiring, and model-backed application logic.gpt-5.4
mlops-engineer—Use when a task needs model deployment, registry, pipeline, monitoring, or environment orchestration for machine learning systems.gpt-5.4
nlp-engineer—Use when a task needs NLP-specific implementation or analysis involving text processing, embeddings, ranking, or language-model-adjacent pipelines.gpt-5.4
postgres-pro—Use when a task needs PostgreSQL-specific expertise for schema design, performance behavior, locking, or operational database features.gpt-5.4
prompt-engineer—Use when a task needs prompt revision, instruction design, eval-oriented prompt comparison, or prompt-output contract tightening.gpt-5.4
README.md
written by Forgecat
05. Data & AI
Agents for data pipelines, LLM integrations, and database behavior.
ai-engineer — Use when a task needs implementation or debugging of model-backed application features, agent flows, or evaluation hooks. gpt-5.4Data & AI
data-analyst — Use when a task needs data interpretation, metric breakdown, trend explanation, or decision support from existing analytics outputs. gpt-5.3-codex-sparkData & AI
data-engineer — Use when a task needs ETL, ingestion, transformation, warehouse, or data-pipeline implementation and debugging. gpt-5.4Data & AI
data-scientist — Use when a task needs statistical reasoning, experiment interpretation, feature analysis, or model-oriented data exploration. gpt-5.4Data & AI
database-optimizer — Use when a task needs database performance analysis for query plans, schema design, indexing, or data access patterns. gpt-5.4Data & AI
llm-architect — Use when a task needs architecture review for prompts, tool use, retrieval, evaluation, or multi-step LLM workflows. gpt-5.4Data & AI
machine-learning-engineer — Use when a task needs ML system implementation work across training pipelines, feature flow, model serving, or inference integration. gpt-5.4Data & AI
ml-engineer — Use when a task needs practical machine learning implementation across feature engineering, inference wiring, and model-backed application logic. gpt-5.4Data & AI
mlops-engineer — Use when a task needs model deployment, registry, pipeline, monitoring, or environment orchestration for machine learning systems. gpt-5.4Data & AI
nlp-engineer — Use when a task needs NLP-specific implementation or analysis involving text processing, embeddings, ranking, or language-model-adjacent pipelines. gpt-5.4Data & AI
postgres-pro — Use when a task needs PostgreSQL-specific expertise for schema design, performance behavior, locking, or operational database features. gpt-5.4Data & AI
prompt-engineer — Use when a task needs prompt revision, instruction design, eval-oriented prompt comparison, or prompt-output contract tightening. gpt-5.4Data & AI
ForgeCat