NeVibeCode · 40 items
Subagents for AI and ML
Subagents for AI and ML: what each one does, an install command and example prompts.
prompt-engineer subagent This subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking.
16,078installs
prompt-engineer subagent This subagent designs and tests prompts for LLM features, agent workflows, and system instructions. Use it when prompt structure, safety, or evaluation needs deliberate work.
CX Codex
16,078installs
ai-engineer subagent This subagent helps design AI systems, choose models, build training pipelines, and prepare deployment. Use it when work spans research through production.
7,687installs
ai-engineer subagent This subagent designs LLM applications, RAG systems, and AI agents. Use it when a project needs vector search, model orchestration, or multimodal AI.
CX Codex
7,687installs
search-specialist subagent A web research subagent that filters sources and cross-checks facts. Use it for deep research, competitive analysis, and trend work.
CX Codex
6,886installs
business-analyst subagent This subagent analyzes business data and helps shape KPIs, forecasts, and financial models. Use it to turn a business question into an analysis plan and recommendations.
CX Codex
3,855installs
data-scientist subagent Subagent for exploratory data analysis, hypothesis testing, and building machine learning models directly in Claude Code.
3,342installs
data-scientist subagent This subagent explores datasets, tests statistical hypotheses, and builds predictive models. It can be added to Claude Code, Codex, or Cursor.
CX Codex
3,342installs
ml-engineer subagent An agent for building ML training pipelines, serving infrastructure, and automated retraining. It helps deploy production machine learning systems.
1,971installs
ml-engineer subagent A subagent for production ML: training, model serving, feature engineering, A/B testing and monitoring. Useful when a model needs to leave the notebook.
CX Codex
1,971installs
quant-analyst subagent A subagent for quantitative trading strategies, financial models, and portfolio risk analysis. Use it for backtests, derivatives pricing, and statistical arbitrage.
1,366installs
mlops-engineer subagent This subagent designs ML infrastructure, model CI/CD, and versioning workflows. Use it when training automation, GPU orchestration, or ML monitoring needs attention.
1,009installs
customer-support subagent This subagent helps plan ticket workflows, support automation, and knowledge bases. Use it when you are shaping customer service processes for a project.
CX Codex
1,041installs
mlops-engineer subagent Builds ML pipelines, configures experiment tracking, and automates model deployments across cloud platforms. Useful for teams standardizing ML infrastructure.
CX Codex
1,009installs
nlp-engineer subagent Subagent for building text processing pipelines, fine-tuning models, and running production NLP tasks in Claude Code. Suited for NER, sentiment analysis, and translation.
927installs
trend-analyst subagent This subagent scans change signals, finds patterns, and builds future scenarios. Use it when trend analysis needs to inform product or strategic decisions.
753installs
llm-architect subagent Designs production LLM architectures: covers RAG, LoRA fine-tuning, inference serving with vLLM, and multi-model routing. Essential when managing token budgets and latency targets.
649installs
multi-agent-coordinator subagent Plans how Claude Code subagents sequence work, share state through files, and handle failures. Use it when a task has parallel workers or hand-offs.
632installs
agent-organizer subagent Breaks down complex projects into subtasks, maps them to available subagents, and writes an execution plan in Markdown. Useful for coordinating multi-agent setups.
562installs
data-researcher subagent Gathers, verifies, and cleans raw data from web sources and local files. Ideal for preparing datasets before running statistical analysis or machine learning tasks.
542installs
machine-learning-engineer subagent A subagent for deploying, optimizing, and serving ML models in production. Use it for inference infrastructure, scaling, and model monitoring.
431installs
mcp-developer subagent Builds, tests, and optimizes Model Context Protocol (MCP) servers and clients. Connects AI models to external tools, databases, and custom services.
366installs
knowledge-synthesizer subagent Finds recurring errors and workflow patterns in logs and transcripts, then records evidence-linked findings. Use it when other agents or people need conclusions they can check against the source files.
276installs
math-proof-judge
official subagent A subagent that runs a hard math proof step by step: plans each round's questions, reads the answers, and assembles proof.md.
★ 44,635repo stars
SE: Security
official subagent A subagent that reviews code for vulnerabilities against OWASP Top 10, Zero Trust and LLM threats. Useful before shipping to production.
★ 40,418repo stars
Research Harness Engineer
official subagent A subagent for experiment campaigns: it builds an evaluation harness that is hard to fool and keeps every reported number honest.
★ 40,418repo stars
Python Notebook Sample Builder
official subagent Builds interactive Jupyter notebooks in VS Code to demonstrate Azure and AI features, testing every snippet in the terminal first.
★ 40,418repo stars
Prompt Engineer
official subagent Treats each message as a prompt draft, reviews its quality, and returns a rewritten instruction for a language model.
★ 40,418repo stars
Power Platform MCP Integration Expert
official subagent Guides Power Platform custom connector development with MCP for Copilot Studio. Helps flatten Swagger schemas, validate packages, and secure OAuth flows.
★ 40,418repo stars
PHP MCP Expert
official subagent Assists in building Model Context Protocol servers in PHP 8.2+ using the official PHP SDK. Generates tools, resources, and prompts with PHP attributes.
★ 40,418repo stars
Kotlin MCP Server Development Expert
official subagent Helps build Model Context Protocol servers in Kotlin using the official SDK, coroutines, and Ktor. Useful for wiring up tools, resources, and custom transports.
★ 40,418repo stars
Java MCP Expert
official subagent Guides development of Model Context Protocol servers in Java using MCP Java SDK 2.x. Useful when configuring stdio transports, tool schemas, or Spring AI 2.0+ integrations.
★ 40,418repo stars
Go MCP Server Development Expert
official subagent Builds Model Context Protocol servers in Go using the official Go SDK. Generates type-safe tools, resources, and transport configurations for Copilot.
★ 40,418repo stars
Doublecheck
official subagent Verifies AI-generated text by finding web sources and highlighting hallucination risks. Useful before publishing content containing legal citations, statistics, or API syntax.
★ 40,418repo stars
Declarative Agents Architect
official subagent Designs Microsoft 365 Copilot declarative agents using the v1.5 schema. Generates TypeSpec definitions, validates character constraints, and configures tooling.
★ 40,418repo stars
ai-readiness-reporter
official subagent Runs an AgentRC readiness assessment and builds a standalone HTML report in reports/index.html. Helps evaluate how prepared a repository is for AI agents.
★ 40,418repo stars
llm-finetuning-architect subagent A strategist subagent that decides whether fine-tuning is the right tool and writes the training-brief.md for the training engineer.
CX Codex
★ 41,729repo stars
vector-database-engineer subagent A subagent for building vector search: picking a database, choosing embeddings, tuning indexes and hybrid retrieval for RAG.
CX Codex
★ 41,729repo stars
podcast-content-analyzer subagent A Claude subagent that reads podcast transcripts, finds viral moments, builds chapter markers, pulls SEO keywords and scores clip potential.
474installs
microsoft-agent-framework-python subagent A Claude subagent that writes and refactors Python code on Microsoft Agent Framework: agents, workflows, and migration from Semantic Kernel or AutoGen.
188installs
