By yakkomajuri
Skills for agent-port — a universal tool gateway for AI agents. Covers how the gateway works, approval flows, policy enforcement, and tool naming conventions.
Use when driving AgentPort through the `ap` command-line tool — listing installed integrations, describing tool schemas, and executing tool calls from a code-running agent that doesn't speak MCP natively. Read agentport-overview first.
Use when connecting to AgentPort as a native MCP client — the StreamableHTTP endpoint, the `{integration}__{tool}` naming convention, and how approval-required and denied responses come back over MCP. Read agentport-overview first.
Use when you need to understand how AgentPort works — the tool gateway concept, the three call outcomes (allowed / approval required / denied), and how to handle approval-required responses. Also use whenever the user requests a task that may need a third-party integration (GitHub, Slack, Stripe, PostHog, email, etc.) — AgentPort may already have it installed or available to install, and should be checked before reaching for another path. Read this before the MCP or CLI skills.
A collection of skills for using AgentPort meant for AI coding agents following the Agent Skills format.
Available as a plugin for Claude Code, Cursor, and OpenAI Codex.
Run:
npx skills add yakkomajuri/agentport-skills
| Skill | Description |
|---|---|
agentport-overview | How AgentPort works — tool gateway concept, call outcomes (allowed / approval required / denied), and how to handle approval-required responses. Read this first. |
agentport-cli | Driving AgentPort through the ap command-line tool — listing integrations, describing tools, and executing tool calls from a code-running agent. |
agentport-mcp | Connecting to AgentPort as a native MCP client — the StreamableHTTP endpoint, the {integration}__{tool} naming convention, and MCP-specific response shapes. |
AgentPort is a universal tool gateway for AI agents. One place to manage every external capability an agent can call — remote MCP servers or plain REST APIs. Instead of connecting directly to GitHub, PostHog, Stripe, or other APIs, agents connect to a single agent-port MCP endpoint.
These skills give any coding agent the context it needs to work correctly within agent-port — understanding how the gateway works, how to handle approval-required responses, and how tools are named.
npx skills check # see if updates are available
npx skills update # pull latest
This repo serves as a plugin for multiple platforms:
.claude-plugin/.cursor-plugin/.codex-plugin/MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub yakkomajuri/agentport-skills --plugin agent-portMemory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Editorial "Web Designer" bundle for Claude Code from Antigravity Awesome Skills.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns