create-agents

Generate reusable agent manifests with model profiles and harness-style contracts.

28|2|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/labs21-dev/agents-stack --skill create-agents-labs21-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-agents
Source: https://github.com/labs21-dev/agents-stack/tree/main/templates/.agents/skills/skill-authoring/create-agents
Command: npx skills add https://github.com/labs21-dev/agents-stack --skill create-agents-labs21-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables teams to author portable, well-scoped agent manifests for templates and shared directories, ensuring consistent contracts, metadata, and evaluation scaffolding across projects.

Core Features & Use Cases

  • Portable manifest authoring for templates and cross-project reuse.
  • Enforce harness-style contracts, model profiles, and uncertainty protocols.
  • References and assets for shared conventions and templates.
  • Evaluation scaffolding and final checklist to validate manifests.

Quick Start

Create a new agent manifest for a bounded task using the default role set and include the frontmatter name and description.

Frequently Asked Questions about create-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create reusable agent manifests for cross-project templates?

Agent manifests are configuration files defining portable, well-scoped AI agent roles. They provide explicit model profiles, harness-style contracts, and frontmatter metadata to ensure consistent behavior, uncertainty handling, and verifiable scaffolding across templates and shared directories.

What is an agent manifest and when do I need frontmatter metadata?

Agent manifests are configuration files defining portable, well-scoped AI agent roles. They provide explicit model profiles, harness-style contracts, and frontmatter metadata to ensure consistent behavior, uncertainty handling, and verifiable scaffolding across templates and shared directories.

How do I enforce narrow roles and uncertainty handling in shared agent directories?

Agent manifests are configuration files defining portable, well-scoped AI agent roles. They provide explicit model profiles, harness-style contracts, and frontmatter metadata to ensure consistent behavior, uncertainty handling, and verifiable scaffolding across templates and shared directories.

Can I use generated agent manifests for cross-project evaluation scaffolding?

Agent manifests are configuration files defining portable, well-scoped AI agent roles. They provide explicit model profiles, harness-style contracts, and frontmatter metadata to ensure consistent behavior, uncertainty handling, and verifiable scaffolding across templates and shared directories.

What's the best way to structure portable frontmatter for agent discovery?

Agent manifests are configuration files defining portable, well-scoped AI agent roles. They provide explicit model profiles, harness-style contracts, and frontmatter metadata to ensure consistent behavior, uncertainty handling, and verifiable scaffolding across templates and shared directories.

Does authoring agent manifests require explicit model profiles and harness contracts?

Agent manifests are configuration files defining portable, well-scoped AI agent roles. They provide explicit model profiles, harness-style contracts, and frontmatter metadata to ensure consistent behavior, uncertainty handling, and verifiable scaffolding across templates and shared directories.