Skill UI

This skill captures and persists critical user decisions, project constraints, and architectural choices across multiple sessions and agents. It saves this context into a structured memory database (`mdbase`), ensuring that future development steps or agents can retrieve the original intent without re-deriving it from scratch. Ideal for documenting project rules, tech stacks, and design rationale.

A powerful tool for designing and writing deterministic, multi-agent workflow scripts in JavaScript. It allows users to orchestrate complex, repeatable, multi-step tasks using advanced patterns like fan-out, pipelines, loops, and judge-panels. Ideal for automating sophisticated business processes that require multiple specialized sub-agents and robust context management.

Polis Protocol is an advanced, vendor-agnostic framework designed to coordinate multiple AI agents as a self-improving team. Unlike passive task lists, it utilizes a learning router (bandit) to assign tasks based on an agent's proven track record for specific tags. It includes a robust governance layer, allowing agents to propose and vote on amendments to the protocol itself, ensuring the system evolves with its work.

This tool audits the activation metadata of coding skills used by AI agents. It grades skills (A-F) based on description clarity, simulates which skill a prompt will trigger, and identifies metadata collisions where one skill might silently overshadow another. It is essential for ensuring robust, predictable, and reliable AI agent behavior during development and CI processes.

This skill provides a comprehensive playbook for setting up and orchestrating multi-agent systems using the standalone Antigravity 2.0 Agent Manager alongside the Antigravity IDE. It guides developers on creating a dual-window workspace to coordinate specialized AI agents (e.g., front-end, back-end, QA) to work in parallel on a single codebase, significantly boosting development efficiency and managing concurrent code changes.

This skill provides comprehensive management for Opencode's permission system. It allows users to review currently always-allowed commands, suggest safe read-only commands, and configure granular access controls using allow/deny/ask patterns. It is essential for optimizing security, performing system audits, and managing the operational scope of the agent.

Open Dynamic Workflows (ODW) is an advanced, open-source engine designed to manage complex coding tasks using multiple AI agents. It operates in three stages: planning the task into parallel subtasks, orchestrating various coding agents (like Codex or Antigravity) to work concurrently, and finally, performing an adversarial verification pass to challenge and validate the combined output before merging. It supports multiple model providers and is ideal for structured, high-reliability software development.

This skill helps developers build, validate, and troubleshoot deep links for major coding environments like VS Code, Cursor, and Codex. It is essential when creating clickable, actionable links (especially in chat platforms like Slack) that direct users to specific files, threads, or settings within an application.

This skill provides a direct, fast shell invocation to capture the current git diff (staged, working-tree, or specific file list) as raw text. It is designed to replace slower LLM agent steps that merely execute 'git diff' commands, significantly speeding up CI/CD workflows and meta-steps that require repository state analysis.

A lightweight tool designed to fetch data from a single URL via HTTP/HTTPS using various methods (GET, POST, PUT, DELETE). It serves as a fast, direct shell wrapper, ideal for replacing complex agent steps that only require simple data retrieval. Supports configurable timeouts and response body capping, making it perfect for quick data fetching in meta-skill workflows.

This meta-skill automates the process of handling a GitHub issue by fetching context, delegating the fix to a sub-agent, summarizing the resolution, and finally opening a pull request (PR). It is best suited for small, well-scoped issues with clear acceptance criteria. This pipeline simulates a complete development workflow.

A meta-skill designed to monitor long-running processes, such as model fine-tunes or CI builds, executed within a detached tmux session. It captures output, automatically uses a sub-agent to diagnose failures, proposes a fix, and records the complete debugging process to memory. Ideal for intermittent failure debugging and continuous integration pipelines.