Data and AI agents

buiphucminhtam/forgewright

Agent Cursor

Translates natural language chat into structured pipeline requests. Use at the start of every conversation when the user describes what they want. Powered by prompt-master methodology.

agentarea/agentarea

Agent

A skill is a folder of files an agent loads only when a task calls for it — this page covers the three tiers of disclosure, where the files land, and what the model is told at each stage.

RainLib/AI-Storyboard

Agent Claude Code

An animation specialist that turns a four-panel storyboard into a prompt for generating moving video. A storyboard is a sequence of still images showing how a scene should develop.

congmnguyen/claude-code-wsl2-setup

Agent

Delegate a well-specified implementation, refactor, migration, or bulk-mechanical coding task to the configured Codex CLI model and return ONLY a compact summary. Keeps Codex's large transcript out of the orchestrator's context. Use for multi-step tasks; not for tiny one-shot edits.

hoangsonww/AI-RAG-Assistant-Chatbot

Agent Claude Code

Use for isolated server-side API, retrieval, and knowledge-base work in server/, especially route behavior, service logic, citations, and knowledge CLI workflows.

AutomatosAI/automatos-ai

Agent

Agent "_index" from AutomatosAI/automatos-ai, covering agents, purpose and scope, agent entity model, agent data model with relationships and creating agents.

lazymac2x/agent-wiki

Agent

An example core for mobile and web apps that keeps records, statistics, and assistant answers based on one trusted data source.

raffertyuy/github-copilot-prompts

Agent Claude Code

Data engineer agent for SQL generation with database schema awareness.

cubeplexai/cubepi

Agent

How CubePi maximises prompt cache hit rates — append-only message storage, automatic cache breakpoints, and how to avoid breaking the cache.

aws-samples/sample-kiro-cli-prompts-for-product-teams

Agent Claude Code ✓ vendor

Use for the AI Framing phase (AI/ML products ONLY) — ML problem framing, input/output schemas, evaluation metrics with thresholds, and data strategy. Dispatch after Deep Market Research is approved and before the PRFAQ, when the product involves ML models, predictions, generative AI, or automated decisions.

tdimino/claude-code-minoan

Agent

GitHub-focused research subagent. Searches, explores, and fetches files from remote GitHub repos using gh CLI. Caches files in /tmp/claude-librarian/ to avoid polluting the project. Use when you need to explore upstream repos, check framework source, or investigate dependencies without cloning. Preferred model: sonnet…

DeevsDeevs/agent-system

Agent

Alpha Squad - mechanisms and confounding lens. Orthogonalizes signals via Frisch-Waugh-Lovell, runs Double ML, designs placebo tests. Correlation is unobserved confounding until proven otherwise.

oimiragieo/agent-studio

Agent Claude Code

The agent system contains 119 specialized AI agents organized into 4 tiers. Each agent is a markdown file defining its role, tools, model preference, and behavioral instructions. Agents are spawned by the router via Task() — they never run independently.

Pretend-to/mio-chat-backend

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

Pretend-to/mio-chat-backend

Agent

Compare two outputs WITHOUT knowing which skill produced them.

Pretend-to/mio-chat-backend

Agent

Evaluate expectations against an execution transcript and outputs.

Azure-Samples/claude

Agent

Deploy, verify, modify, debug, and tear down a Claude model deployment on Microsoft Foundry using the Azure-Samples/claude starter kit (Bicep or Terraform, single command: azd up). Drives the repo's own scripts and env-var contract over Microsoft Entra ID (no API keys).

zhouguoqing/QianYuan.AIAgenticFramework

Agent

Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces stunning, professional-quality photography through generative AI tools.

freema/cursor-plugin-cc

Agent

Hand off a well-specified coding task to the Cursor CLI (cursor-agent) via /cursor:delegate. Use for small-to-medium, well-scoped changes where speed matters (default model composer-2.5-fast). Do NOT use this agent for code review, design decisions, or large refactors — those stay with the main Claude conversation.

tosin2013/mcp-adr-analysis-server

Agent

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

sfc-gh-dflippo/snowflake-dbt-demo

Agent Claude Code

Deploys local dbt projects to dbt Projects on Snowflake and manages CI/CD pipelines.

Nagarjuna2997/ios-agent-skill

Agent Claude Code

Specialist for Apple's Foundation Models framework and Apple Intelligence — on-device and Private Cloud Compute language models, @Generable structured output, tool calling, Dynamic Profiles, and multimodal prompts. Use when building, reviewing, or debugging any on-device LLM feature. Enforces availability gating and…

DNYoussef/context-cascade

Agent

This system extends Claude Code with unique capabilities from Gemini CLI and Codex CLI by creating specialized skills for each model's strengths. Instead of being limited to Claude's capabilities, you can now access.

PolicyEngine/policyengine-claude

Agent

Stage-5 comparator. Takes the microsim output and the prior-scores anchor, returns PASS (within expected band, write up the result) or INVESTIGATE (mismatch, trigger calibration-diagnostics). Normalizes single-year vs 10-year scores and accounts for dataset-version drift.