Create a skill

Use this guide when the Studio starter or user request asks Veryfront Agent to create a reusable skill. Skills are best for repeatable instructions. Resources are best for read-only context the skill can load by name.

Agent-facing flow

Load the Veryfront router skill: load_skill({ "skillId": "veryfront" }).
Treat this page as the guide for creating or editing a project skill.
If the request is broad, ask one short form_input with a required brief field, then continue from the submitted brief.
Create or update the smallest useful skill. Prefer the framework source shape when editing project files. Use the MCP tool call when Studio exposes skill creation tools instead.
If the skill needs stable reference material, add a focused resource instead of pasting long background text into the skill.
If the request does not name a domain, create a small skill for reviewing AI agent designs. Include a compact Mermaid example only as supporting output, not as the skill’s main purpose.
Return the skill path or skill id, any resource path or resource id, and a short note on how to invoke it.

Guardrails

Do not load a removed create-skill sub-skill.
Do not create UI files, app routes, or unrelated project code for a skill-only request.
Do not invent tool names, resource ids, or project paths. Use the tools and conventions available in the current project.
Keep one skill focused on one repeatable workflow.
Keep resources read-only. Use a tool when the task needs to change state.
Do not turn the Mermaid example into the main point unless the user asked for a diagram skill.
Do not default to a diagram-only skill for the Studio starter. Default to a generic AI-agent-building helper.
Do not finish with inline-only guidance when file or skill creation tools are available.

Example pattern

Default to source when you are editing a project. Use the tool call form when the available MCP surface owns skill creation.

---
name: agent-design-review
description: Review AI agent designs for goal fit, tool access, context, handoffs, and verification.
allowed-tools:
  - list_files
  - get_file
  - search_files
---

# Agent Design Review

Use this skill when a user asks for a quick review of an AI agent, tool agent, or multi-agent design.

## Steps

1. Read only the agent, skill, resource, or tool files needed for the review.
2. Identify the agent's goal, required context, tools, handoffs, and verification path.
3. Read `agent-design-guide://review` when it is available.
4. Return the main risks, recommended edits, and a small Mermaid map only when the relationships are not obvious.

## Example

```mermaid
flowchart LR
  User --> Orchestrator
  Orchestrator --> ToolAgent
  ToolAgent --> ExternalTool
  Orchestrator --> VerifiedAnswer
```

create_skill({
  "project_reference": "<project>",
  "name": "agent-design-review",
  "description": "Review AI agent designs for goal fit, tool access, context, handoffs, and verification.",
  "allowed_tools": ["list_files", "get_file", "search_files"],
  "instructions": "# Agent Design Review\n\nUse this skill when a user asks for a quick review of an AI agent, tool agent, or multi-agent design.\n\n## Steps\n\n1. Read only the agent, skill, resource, or tool files needed for the review.\n2. Identify the agent's goal, required context, tools, handoffs, and verification path.\n3. Read `agent-design-guide://review` when it is available.\n4. Return the main risks, recommended edits, and a small Mermaid map only when the relationships are not obvious.\n\n## Example\n\n```mermaid\nflowchart LR\n  User --> Orchestrator\n  Orchestrator --> ToolAgent\n  ToolAgent --> ExternalTool\n  Orchestrator --> VerifiedAnswer\n```"
})

The two tabs above describe the same skill. In framework source, allowed-tools maps to the MCP allowed_tools array, and the frontmatter name and description map to the fields of the same name; when you write through the tool, the API renders that frontmatter itself, in its own canonical form. Everything below the frontmatter is the MCP instructions string, carried across verbatim. On update_skill, sending instructions replaces the whole body, and omitting it leaves the body untouched.

Resource example

Use a resource when the skill needs reusable context that should be read, not executed.

import { resource } from "veryfront/resource";

const agentDesignGuide = resource({
  pattern: "agent-design-guide://review",
  description: "Review checks for AI agent and tool-agent designs.",
  load: () => {
    return {
      content: [
        "# Agent design review guide",
        "",
        "- Start from the user outcome and the stop condition.",
        "- Keep one agent responsible for one clear job.",
        "- Name required tools, integrations, and resource inputs explicitly.",
        "- Define handoffs, approval points, and verification evidence.",
        "- Use Mermaid only when agent/tool relationships need a map.",
      ].join("\n"),
    };
  },
});

export default agentDesignGuide;

create_resource({
  "project_reference": "<project>",
  "id": "agent-design-guide",
  "title": "Agent design review guide",
  "description": "Review checks for AI agent and tool-agent designs.",
  "pattern": "agent-design-guide://review"
})

Output shape

Return the created or updated skill name, skill ID or source path, allowed tools, any backing resource ID or source path, and one short invocation example. Keep the final answer brief and do not claim a placeholder resource was created when the resource content is empty.

Goal	Page
Understand project skills	Skills
Create a project agent	Create an agent
Understand resources	Resource
Use the resource API	veryfront/resource
Use the skill creation tool	create_skill
Use the resource creation tool	create_resource

Getting Started

Concepts

Guides

Agent-facing flow

Guardrails

Example pattern

Resource example

Output shape

Next

​Agent-facing flow

​Guardrails

​Example pattern

​Resource example

​Output shape

​Next

Agent-facing flow

Guardrails

Example pattern

Resource example

Output shape

Next