Agent Orchestration Skill Leaderboard

A comprehensive collection of standardized agentic skills for AI automation, ranging from solution architecture and 3D web development to security auditing.

Implements persistent state management for AI agents using local markdown files to track task plans, findings, and session progress.

A library of over 800 AI skill definitions covering agent orchestration, accessibility auditing, marketing optimization, and engineering workflows.

A comprehensive suite of 74 skills for game development, featuring studio-hierarchy coordination, technical decision tracking, and project auditing.

A collection of agent skills focused on context engineering, harness design, and multi-agent architecture for production systems.

An autonomous iteration loop that modifies and verifies code against a set metric to optimize performance.

Provides tools for agent payments, ERC-7710 delegated permissions, x402 paid APIs, and dispute resolution for agent-to-agent commerce.

Tools for designing and deploying repo-local agentic control loops and iterated coding-agent workflows.

Parallel divergent ideation for coding agents. Spawns isolated branches under cognitive frames, scores, clusters, prunes traps, and deepens top survivors for open-ended design and architecture problems.

Provides CLI tools and plugin development capabilities for managing agent threads, environments, and system extensions.

Converts images into structured JSON evidence including OCR and layout semantics for text-only AI agents.

A suite of tools for importing AI chat histories, automating wiki cross-links, and generating architecture maps within Obsidian.

A workspace management skill for maintaining durable state, evidence, and consistency during long-horizon AI reasoning and repository engineering.

A bridge utility to route Claude session outputs to external instant messaging apps via a background daemon.

A guide to provider-neutral agent architecture covering tool design, memory management, observability, and recursive harness deployment.

Runs high-stakes decisions through five independent AI advisors with peer review and synthesis for a clear verdict and actionable next step.

Implements a think-act-prove orchestration method for AI agents featuring domain research and adversarial verification of outputs.

A set of delegation skills that allow an orchestrator agent to dispatch tasks to specialized AI CLI tools including Aider, Claude Code, and Antigravity.

Manages project knowledge by drafting architectural contributions and coordinating durable team handoffs.

Designs agent-walkable folder pipelines, knowledge libraries, and codebase maps with explicit routing, state, and review contracts.

Integrates Codex CLI capabilities for automated code analysis, refactoring, and session-based editing using high-reasoning models.

A set of skills for generating release notes from git logs, designing 360-degree feedback reports, and summarizing hiring panel activities.

A collection of 14 sales skills covering prospect research, lead qualification, decision maker identification, cold outreach sequences, follow-ups, meeting prep, proposals, competitor intelligence, and pipeline reporting.

A set of developer tools for designing technical specifications and generating AGENTS.md context files to bootstrap AI-assisted development.

Agent orchestration skills for provisioning isolated environments, auditing agent context, and establishing verifiable development harnesses.

Provides core utilities for Deep Agent creation, including harness architecture and state management via ephemeral and persistent backends.

A knowledge engine featuring parallel research decomposition, intelligent thought capture, and a closed-loop V-model verification process for AI tasks.

An agentic development harness for Claude Code featuring SPEC-driven workflows and high-performance Go CLI patterns.

Orchestration skills for agent-to-agent handoffs, transcript management, and contract-based behavior validation.

A developer toolkit featuring a Rust-based headless browser CLI, Codex hook management, and high-fidelity frontend interface generation.

Helps technical founders scope, launch, and iterate on Claude Managed Agents with support for scheduled deployments and outcome rubrics.

A set of skills for auditing inherited implementations, executing customer-specific software changes, and drafting executive business cases.

Agent orchestration skills for browser and desktop GUI automation and transcript compaction for context window optimization.

Covers idiomatic Synalinks development: data models, program APIs, modules, control flow, agents, RAG, training, rewards, and providers.

An agent orchestration framework that enforces staged planning, sub-agent delegation, and self-verification to improve the reliability of complex AI workflows.

Orchestrates five AI advisors to independently analyze, peer-review, and synthesize a final verdict on complex decisions.

Management utilities for Codex custom model installation, task context handoffs, and enterprise clone building.

A set of orchestration tools for building, upgrading, and refining reusable AI agent skills from execution history.

An orchestration skill for multi-file builds and refactors that separates high-level planning from delegated implementation.

A library of agentic primitives for implementing structured architectural design and rigorous workflows across various AI harnesses.

A set of agent workflows for backend technical decision-making, anti-pattern detection, and documentation criteria.

A collection of AI agent skills for browser automation, web scraping, and implementing features via the Vercel AI SDK.

A set of AI skills for codebase design, architectural research, and adversarial review to generate precise technical specifications.

A continuously curated runbook that activates every session to store reusable guidance, gotchas, and directives for faster and more reliable agent execution.

A collection of workflows and critique dimensions for designing, validating, and refining AI agents.

A collection of 53 agent skills covering API integration, financial analysis, and generative art using p5.js.

An agent orchestration toolkit for designing foundational AI architectures and optimizing workflow latency, cost, and provider compatibility.

Implements knowledge graph construction—including ontology design and entity fusion—and multi-agent task orchestration using graph-based workflows.

Queries ChatGPT and Gemini APIs for implementation perspectives, synthesizes their responses, and presents a plan informed by multiple LLMs.

A comprehensive guide to LangGraph 1.0 for building ReAct agents, state graphs, and agent middleware.