spec-agent-command

Generates agent and command markdown files from design documents for Claude Code plugins.

1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/JaviMontano/mao-plugin-qa --skill spec-agent-command-javimontano
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: spec-agent-command
Source: https://github.com/JaviMontano/mao-plugin-qa/tree/main/skills/spec-agent-command
Command: npx skills add https://github.com/JaviMontano/mao-plugin-qa --skill spec-agent-command-javimontano

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Writing agent and command specification files for Claude Code plugins by hand is error-prone: forbidden frontmatter fields slip in, alias commands drift from their canonical counterparts, and cross-references to skills break silently. This Skill turns a design document into validated, production-ready agent and command .md files. ## Core Features & Use Cases - Agent File Generation: Produces complete agent .md files with frontmatter, role, responsibilities, skills table, execution flows, and operating principles, while enforcing plugin subagent constraints (no hooks, mcpServers, or permissionMode). - Canonical + Alias Command Generation: Creates canonical command files with usage, execution flow, and output sections, plus matching alias files with correct alias-of pointers. - Validation: Checks kebab-case naming compliance and verifies that all skill and command cross-references resolve to existing entities. - Use Case: After finishing an agent/command design document for a new plugin, run this Skill to generate all agent and command files at once, with warnings for any unresolved skill references or naming violations. ## Quick Start Generate the agent and command specification files from my design document at designs/plugin-agents.md and validate all cross-references.

Frequently Asked Questions about spec-agent-command

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

FAQPage Schema
How do I generate Claude Code agent and command files from a design document?▼

Provide the path to your agent/command design document as the argument. The Skill reads the design, generates agent .md files with role, skills table, execution flows, and operating principles, plus canonical and alias command .md files, then validates naming and cross-references.

What frontmatter fields are forbidden in Claude Code plugin subagents?▼

Plugin subagents cannot define hooks, mcpServers, or permissionMode in their frontmatter. The Skill automatically removes these fields during generation and adds an INFO note, since hooks belong in the plugin-level hooks/hooks.json file.

How do command aliases work in Claude Code plugins?▼

Each user-facing command has a canonical file with the full definition and an alias file containing an alias-of field pointing to the canonical name. The alias body is a single line referencing the canonical file, so updates to the canonical propagate automatically.

Can this Skill create agent designs from scratch without a design document?▼

No. It requires a completed agent/command design document as input and cannot infer agent roles or command routing on its own. Designing agents is the responsibility of a separate design step such as a design-agent skill.

What are the limitations of the cross-reference validation?▼

Validation checks existence only, not semantic correctness. A command referencing an existing but unrelated skill will pass, and the Skill cannot verify that execution flows will actually work at runtime.