Agent Building Agent Skills

Run Claude Code autonomously in loops, from simple sequential pipelines to multi-agent DAG orchestration.

Orchestrates building a new feature end-to-end by delegating research, planning, TDD implementation, review, and gated commit to specialized agents.

Uses a multi-agent generator-evaluator feedback loop to build high-quality applications from a single prompt, inspired by GANs and Anthropic's harness design.

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions.

Progressively refines context retrieval in multi-agent workflows to solve the subagent context problem.

Guides teams in adapting engineering processes, architecture, code review, and testing for high-volume AI-assisted code generation.

Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

Rates an agent's own output on five axes — accuracy, completeness, clarity, actionability, conciseness — producing a structured scorecard with evidence and improvement suggestions.

Design task-local harnesses, eval gates, and reusable skill extraction for adaptive agent workflows.

Convert human-written CLAUDE.md files into a structured label format that AI models follow more reliably using fewer tokens.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines with observability and security.

Build real-time voice and multimodal AI applications using Pipecat and Daily, covering pipeline architecture, AI service integration, and transport options.

Designs and orchestrates multi-agent AI teams using the CrewAI framework, covering agent roles, task decomposition, crew processes, memory, and flows.

Build cross-platform AI chat interfaces with Makepad using MolyKit, including async utilities, chat widgets, and OpenAI-compatible client integration.

Generates a step-by-step construction plan from a one-line objective, where each step is self-contained and executable by a fresh agent in a new session.

Build production-grade stateful AI agents using LangGraph, covering graph construction, state management, persistence, and human-in-the-loop patterns.

Auto-routes Claude Code subtasks to the cheapest capable model (Haiku/Sonnet/Opus), logs token costs, and A/B tests tiers to validate savings against real workloads.

Guides building production-grade AI features with LLM integration patterns, RAG architecture, prompt engineering, and cost optimization.

Build LLM-powered applications using the Claude API, Anthropic SDKs, or the Agent SDK with language-specific guidance and best practices.

Build evaluation frameworks for agent systems, covering rubric design, test set creation, and automated evaluation pipelines.

Configure and optimize .faf files, MCP servers, and bi-directional sync for AI context across multiple platforms, with championship scoring to achieve 85%+ AI-readiness.

Discover, audit, repair, adapt, and design bounded, verifiable AI-agent loops with explicit triggers, actions, stopping conditions, and guardrails.

Build, deploy, evaluate, debug, and measure latency for a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection and VLM classification.

Builds and validates DeepStream GStreamer pipelines through an interactive questionnaire and a BM25 retrieval engine over 270+ verified pipelines.

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores like S3, GCS, Azure, HTTP, or HuggingFace.

Maps a described workflow to the right ECC command-group with run-order and stop condition, and browses all command-group recipe families.

Designs and reviews feedback loops for AI agents to ensure goals are machine-decidable, loops are damped, and human judgment is preserved.

Orchestrate dynamic multi-agent workflows with parallel agents and adversarial verification via a local daemon, or fall back to native agent orchestration.

Discover, compare, audit, repair, adapt, craft, run, debrief, and publish repeatable AI-agent loops for engineering workflows.

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions.

Build AI agents on Cloudflare Workers using the Agents SDK, covering stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, and browser automation.

Provides authoritative, current guidance from OpenAI developer docs using the developers.openai.com MCP server, including model selection, API migration, and prompt-upgrade guidance.

Scaffold, build, and refactor ChatGPT Apps SDK projects with a docs-first workflow, combining MCP servers and widget UIs.

Scaffolds VS Code custom agent files (.agent.md) with YAML frontmatter, tool configuration, handoffs, and instructions for specialized AI personas.

Test C# MCP servers at unit and integration levels using xUnit, Moq, and the MCP client SDK.

Run, debug, and interactively test C# MCP servers locally with IDE configuration, MCP Inspector, and GitHub Copilot Agent Mode integration.