Agency is a minimal framework for building agent-integrated systems using LLMs.
Find, trial, compare, and govern AI agents before hiring
Data
Connect APIs, databases, warehouses, spreadsheets, analytics, and ETL workflows.
What team job or business role does the user need filled?
Start from a plain-language department or occupational family, then open related technical categories or job-matcher prompts.
- department or team-role discovery
- plain-language job briefs
- business outcome shortlists
- non-technical browsing
Start from user language
- Connect a dataset or API to a reusable analysis workflow.
- Evaluate extraction, transformation, and retrieval candidates.
Sandbox-first next steps
Data candidates
Showing 12 of 4771. Adjust filters to narrow the review list without losing job context.
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured...
Review links
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want...
Review links
Shared versioned state for multi-agent AI workflows
Review links
This skill enables quantum-resistant, lock-free version control for multiple AI agents, delivering self-learning decisions and conflict-free collaboration.
Review links
This skill helps orchestrate autonomous agent teams with role-based collaboration and memory for complex tasks.
Review links
AgentVerse enables deployment of multiple LLM-based agents for task-solving and simulation frameworks.
Review links
A collection of Python adapters that let agent frameworks like LangChain, LlamaIndex, CrewAI, and n8n submit results to the P2PCLAW leaderboard. Each adapter handles the protocol translation so agents can benchmark against a shared scoring system.
Review links
Use when you need to **measure** (not just describe) brand citation frequency across AI search surfaces over time. Runs a configurable brand-mention prompt set weekly against ChatGPT (OpenAI API), Perplexity (Sonar API), and optionally Google AI Mode / AI Overviews / Bing Copilot / Claude.ai (manual workflow). Stores NDJSON history for trend analysis. Trigg...
Review links
Browse modality-based prompt templates (text, image, video, audio) with generators and examples. Separate from course prompt collections on /prompts.
Review links
The **PactFlow skill** turns your AI coding assistant into a Pact and PactFlow contract testing expert. It provides deep knowledge of consumer test patterns, provider verification configuration, can-i-deploy diagnostics, and full workspace management — surfaced directly in your editor without leaving your flow. It ships as part of the [`swagger-contract-tes...
Review links
AI assistant providing field service pros step-by-step guidance, part identification, & journeyman knowledge to make any repair.
Review links
Review links
Role-family pages stay focused on plain-language job review; complete review records and finalist profile resources stay linked here.
Supporting review linksLinks, review order, and page-specific notes remain available here.
4771 candidates for Data. Open matching profiles for fit, setup guidance, trust evidence, and sandbox trial planning.
- 01Site contextShared review rules
- 02Role familyOpen the focused review record
- 03Profile pageOpen the candidate page
- 04Profile resourcesEvidence, setup, trust, trial, and history files
Use the links and review path below for role-family candidates, job brief context, and finalist profile resources before action.