Skill UI

This skill allows orchestrators to delegate bounded coding tasks to the OpenCode CLI while retaining review and commit authority. It requires the opencode CLI installed and authenticated, enabling agents to run shell commands and read files for task execution.

OrcaReplay enables agents to query past execution recordings instead of relying on memory. It supports replaying or forking previous agent runs to investigate why specific actions occurred or to reproduce failures. This skill ensures accurate debugging by reading traces directly, distinguishing between recorded evidence and inferred data, and safely re-executing commands within isolated environments to verify historical behavior.

Coordinate focused subagents on substantial work while maintaining non-overlapping ownership and integrating verified results. Ideal for large-scope tasks where parallel processing reduces elapsed time. Decompose tasks into distinct assignments, run scouts in parallel, assign distinct ownership, and synthesize outputs. Keep trivial work with the coordinator to avoid overhead.

A specialized AI agent designed to build and audit business models using Alexander Osterwalder’s comprehensive 9-block framework. It moves beyond mere filling of blocks, focusing on establishing the critical logical 'lock' between core components like Value Propositions, Customer Segments, and Cost Structures. This tool is ideal for initial business architecture design, auditing existing models for internal consistency (e.g., ensuring every key activity has a corresponding cost), or re-validating the core logic during a strategic pivot.

API-first control plane for reply-aware cold outbound email workflows, managing inboxes, contacts, templates, sequences, approvals, pacing, webhooks, and delivery metrics for AI agents.

Coordinates multiple specialized agents via Claude Code's native Agent Tool for complex tasks requiring diverse expertise, such as comprehensive code analysis, feature reviews, and security audits. Enables sequential chains, context passing, and resumable work, with a synthesis protocol for unified recommendations.

A comprehensive suite designed for AI agents to perform safe, deep, and multi-format web searches. It allows agents to retrieve current web information, analyze PDFs, extract YouTube transcripts, and access GitHub code files. Instructions include guidelines for varying search depths and using specialized tools for code context retrieval.

Pilot Protocol provides AI agents with permanent network addresses, encrypted P2P messaging, and NAT traversal capabilities. It includes an installable app store for agent-native services. Use it for direct agent communication, stable addressing across clouds, and installing local capabilities without REST plumbing.

This blueprint guides the creation of F.R.I.D.A.Y., a tactical, low-latency voice assistant inspired by Iron Man. It utilizes the specialized Pipecat framework to orchestrate a comprehensive, real-time audio pipeline: STT (OpenAI Whisper/GPT-4o) -> LLM (Gemini) -> TTS (OpenAI Nova). Ideal for developers needing to build advanced, multi-provider, conversational voice applications.

Polis Protocol transforms static AI agent workflows into a self-improving, dynamic team environment. It uses a learning router to assign tasks based on an agent's historical track record and effectiveness on specific domains, rather than fixed roles. It is vendor-agnostic, allowing diverse agents (e.g., Claude, Gemini) to collaborate under a unified, auditable governance structure where agents can propose and vote on amending the protocol's core rules.

A protocol enabling AI agents from different vendors to collaborate on long-running projects, route work to best-suited agents, and improve over time. Uses markdown files with no central server, featuring capability cards, contracts, chronicles, and self-amendment mechanisms for cross-vendor optimization and constitutional evolution.

A specialized AI agent for product management in the Chinese internet market. It helps prioritize requirements, plan roadmaps, analyze growth and retention metrics, and handle operational issues like project delays. The agent uses silent reasoning to identify core blockages and dominant mechanisms before providing actionable next steps, stop lists, and switching conditions. It focuses on direct, executable advice without unnecessary theoretical explanations or historical references, suitable for product owners and managers facing complex decision-making scenarios.