Skip to main content
plugin CX Codex

runtype-skills — Claude Code plugin: what it does, how to install

A skill bundle for building and operating AI products on Runtype, covering platform work, agent tools, Persona widgets, templates, and SDK workflows.

MIT ★ 1,596 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install runtype-skills@awesome-codex-plugins
Open on GitHub

What runtype-skills does

This plugin adds skills for building, deploying, and operating AI products on Runtype’s managed edge runtime. The runtype skill scopes the task and sends the agent to a focused guide for product work, account administration, Persona integrations, templates, or SDK-based workflows.

Another group covers agent tool design: interfaces, schemas, outputs, errors, execution, composition, and security. The bundle also includes guidance for connecting externally run agents built with Flue, Cloudflare Agents SDK, Vercel AI SDK, LangGraph, or custom loops to Runtype traces, evals, and surfaces.

You can install selected skills with repeated --skill arguments. Comma-separated names and glob patterns are not supported, so each requested skill needs its own argument. Live account changes through the admin skill are limited to the requested scope.

What it helps with

  • scope a Runtype project
  • build or modify a Runtype-hosted AI product
  • design agent-facing tool schemas and outputs
  • connect an external agent to Runtype traces and evals
  • package a distributable FPO template

Example prompts for the agent

  • Use runtype to scope this project and choose the right Runtype skill.
  • Build an AI product with an agent, flow, and surface using runtype-build-product.
  • Audit this agent tool’s schema, errors, execution, and security with tool-design.

How to install runtype-skills

Plugin marketplace

/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install runtype-skills@awesome-codex-plugins

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about runtype-skills

How do I install runtype-skills in Claude Code?

First run /plugin marketplace add hashgraph-online/awesome-codex-plugins, then install it with /plugin install runtype-skills@awesome-codex-plugins.

What does runtype-skills do?

It provides skills for Runtype product development, account administration, Persona widgets, templates, and SDK workflows. It also includes focused guides for designing AI agent toolsets.

Can I install only selected skills?

Yes. Run npx skills add runtypelabs/skills --skill tool-design --skill tool-design-interface, repeating --skill for each requested name. Comma lists and glob patterns are unsupported.

Source text

skills · MIT
# Runtype Skills

[![skills.sh](https://skills.sh/b/runtypelabs/skills)](https://skills.sh/runtypelabs/skills)

Official agent skills for the [Runtype](https://runtype.com) platform — install them in Claude Code, Cursor, Copilot, and 35+ other AI coding agents.

## Install

**All skills:**

```bash
npx skills add runtypelabs/skills
```

**Pick specific skills** (repeat `--skill` once per skill; comma lists and globs are not supported):

```bash
npx skills add runtypelabs/skills --skill tool-design --skill tool-design-interface
```

**Browse what's available:**

```bash
npx skills add runtypelabs/skills --list
```

## Skills

### Runtype platform

Start with `runtype`; it routes to the focused skill for the job.

| Skill | Description |
|-------|-------------|
| [`runtype`](skills/runtype/) | Scope a Runtype project or set up platform access; route implementation to the relevant Runtype skill. |
| [`runtype-build-product`](skills/runtype-build-product/) | Build or modify Runtype-hosted AI products, agents, flows, and surfaces using current platform instructions. |
| [`runtype-admin`](skills/runtype-admin/) | Inspect, debug, or manage a live Runtype account through MCP or CLI; mutate only within the requested scope. |
| [`runtype-persona`](skills/runtype-persona/) | Embed, style, or debug Runtype Persona widgets and browser-side chat integrations. |
| [`runtype-external-agents`](skills/runtype-external-agents/) | Connect externally executed agents (Flue, Cloudflare Agents SDK, Vercel AI SDK, LangGraph, custom loops) to Runtype traces, evals, or surfaces; not Runtype-hosted execution. |
| [`runtype-templates`](skills/runtype-templates/) | Create, validate, or package distributable Runtype FPO templates and their setup requirements. |
| [`runtype-sdk-marathon`](skills/runtype-sdk-marathon/) | Build source-controlled Runtype workflows with the SDK or CLI, including Marathon tasks and playbooks. |

### Tool design

Framework-agnostic guidance for designing the tools an AI agent calls. Start with `tool-design`; it routes to the focused guide.

| Skill | Description |
|-------|-------------|
| [`tool-design`](skills/tool-design/) | Design or audit an AI agent toolset; route naming, schemas, output, errors, execution, and security to focused guides. |
| [`tool-design-interface`](skills/tool-design-interface/) | Design agent-facing tool names, descriptions, and parameter schemas; diagnose incorrect tool selection or inputs. |
| [`tool-design-output`](skills/tool-design-output/) | Design agent tool results, including pagination, partial success, context size, and actionable next steps. |
| [`tool-design-errors`](skills/tool-design-errors/) | Design actionable agent tool errors, ambiguity handling, retry guidance, and fallback behavior. |
| [`tool-design-execution`](skills/tool-design-execution/) | Design agent tool execution: async jobs, idempotency, timeouts, transactions, and compensation. |
| [`tool-design-composition`](skills/tool-design-composition/) | Compose and expose agent toolsets: task-level operations, batching, discovery, dry runs, and versioning. |
| [`tool-design-security`](skills/tool-design-security/) | Design tool identity, credential injection, authorization, tenant scope, and audit boundaries. |

Skill descriptions above mirror each skill's `SKILL.md` frontmatter; update both together.

## Validation

Run the repository skill lint before publishing:

```bash
node scripts/lint-skills.mjs
node scripts/smoke-install-skills.mjs
```

The lint checks frontmatter, description length, linked references, forbidden internal URLs, common secret leaks, semantic guardrails for drift-prone claims, and extra drift against the neighboring `../core` monorepo when it is present. The smoke test copies each skill into an isolated install directory and confirms standalone metadata and local references still resolve.

For the recommended private-source/public-publish workflow, see [Keeping Runtype Skills in Sync](docs/keeping-skills-in-sync.md).

## Authoring a New Skill

Create a directory under `skills/` with a `SKILL.md` file:

```
skills/
└── my-skill/
    ├── SKILL.md           # Required: frontmatter + instructions
    ├── scripts/           # Optional: executable helpers
    ├── references/        # Optional: API specs, schemas, docs
    └── examples/          # Optional: example inputs/outputs
```

### SKILL.md format

```yaml
---
name: my-skill
description: >-
  What it does and when to use it. Include trigger phrases.
  Max 1024 chars.
user-invocable: true
argument-hint: "[optional args hint]"
---

Instructions for the agent go here. Keep under 500 lines.
Move detailed reference material to references/ or scripts/.
```

### Best practices

- **Description**: Use imperative phrasing ("Use when..."), include specific trigger phrases
- **Size**: Keep SKILL.md under 500 lines / 5,000 tokens
- **Structure**: Move API specs, schemas, and long docs to `references/`
- **Scripts**: Bundle reusable helpers in `scripts/` instead of inlining
- **No secrets**: Never include API keys, internal URLs, or credentials

## License

[MIT](LICENSE)

© hashgraph-online · MIT · hashgraph-online/awesome-codex-plugins

Similar plugins

Plugins catalog →
ub-mode unclebob The ub-mode skill for Claude Code helps developers structure code changes. It guides the development process by following the principles of "First Make it Work, Then Make it Right, Then Follow Practice." CX Codex +1 930installs methodology-advisor FlorianBruniaux The methodology-advisor command for Claude Code and Codex reads the codebase and asks three questions to recommend an AI-development methodology stack. Run it at the start of a project, before choosing a workflow. CX Codex +1 ★ 6,529repo stars discernment-nudge official anthropics discernment-nudge — a plugin for Claude Code and Claude.ai that appends two or three short questions after a substantive answer. Helps check key facts, probe the reasoning, and spot missing context. ★ 198,522repo stars academy-guide official anthropics academy-guide is a Claude Code plugin that points users to Claude Academy courses, tutorials, and use cases. It responds to questions about using Claude. ★ 198,522repo stars claude-api official anthropics This plugin adds Claude API and SDK guidance for building LLM-powered applications. Install it when your project needs a Claude integration. ★ 198,522repo stars example-skills official anthropics example-skills — a plugin for Claude Code and Claude.ai with a set of sample skills. Demonstrates how to build skills, MCP servers, artifacts, web tests, and internal communication tools. ★ 198,522repo stars document-skills official anthropics Document processing suite for Excel, Word, PowerPoint, and PDF files. Equips the assistant to inspect and generate common document formats. ★ 198,522repo stars impeccable pbakaus impeccable — a Claude Code plugin that gives the agent a designer's vocabulary and 24 commands for working with interfaces. Kick it off at any stage, from gathering product context to the final polish pass. ★ 114,575repo stars

From the same set391

The whole set →
skill-skill skill-skill writes agent skills that change what gets generated, then lints SKILL.md against the Agent Skills spec and scores its health from 0 to 100. CX Codex ★ 1,596repo stars since-cutoff since-cutoff finds Python dependency changes after your model's knowledge cutoff and records short rules in AGENTS.md to stop the assistant from generating outdated API calls. CX Codex ★ 1,596repo stars simple-man The simple-man plugin cuts praise, recaps, and filler from agent replies while preserving actionable details. Use it when coding responses need less noise. CX Codex ★ 1,596repo stars sealos Deploys applications to Sealos Cloud directly from an agent, configuring databases, storage, and HTTPS with readiness checks. CX Codex ★ 1,596repo stars roadmapsmith roadmapsmith keeps ROADMAP.md honest: one command writes it, the other proposes edits backed by real code and waits for your ok. CX Codex ★ 1,596repo stars river-review river-review runs perspective-based code reviews in Claude Code and Codex using versioned, repo-owned skills to verify diffs against team standards. CX Codex ★ 1,596repo stars reviewable-html-workbench The reviewable-html-workbench plugin turns agent-produced HTML into browser-reviewable documents with inline comments and follow-up edits. Use it for reports, design docs, and comparison tables. CX Codex ★ 1,596repo stars research-agent-skills Loads 281 agent skills for the full academic research lifecycle into Claude Code and Codex. Covers literature search, hypothesis generation, data analysis, citation checks and peer review. CX Codex ★ 1,596repo stars

Project sponsors

Companies that keep this analytics open