output-style-authoring

Author and review Claude Code output styles with correct frontmatter and system-prompt bodies.

Updated Jun 28, 2026
One-click install
npx skills add https://github.com/JaviMontano/claude-plugins --skill output-style-authoring-javimontano
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: output-style-authoring
Source: https://github.com/JaviMontano/claude-plugins/tree/main/plugins/claude-native-toolkit/skills/output-style-authoring
Command: npx skills add https://github.com/JaviMontano/claude-plugins --skill output-style-authoring-javimontano

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Writing Claude Code output styles incorrectly causes lost coding behavior, broken frontmatter, and confusion between styles, skills, and artifacts. This Skill guides the creation, review, and plugin packaging of output-styles Markdown files so they behave safely and predictably. ## Core Features & Use Cases - Frontmatter Authoring: Produces correct name, description, keep-coding-instructions, and plugin-only force-for-plugin fields with a machine-readable schema. - Boundary Routing: Decides whether a request belongs in an output style, a skill, CLAUDE.md, an agent, or an artifact, preventing mixed surfaces. - Plugin Packaging & Safety Review: Covers plugin output-styles/ directories, manifest outputStyles overrides, forced-style risks, and coding-instruction preservation. - Use Case: A user asks for a project-level style that leads every coding response with an architecture decision and risk table; the Skill produces .claude/output-styles/architecture-brief.md with keep-coding-instructions: true and a system-prompt body. ## Quick Start Ask the assistant to create a Claude Code output style for your desired tone and format, specifying the target scope and whether coding instructions should be preserved.

Frequently Asked Questions about output-style-authoring

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

FAQPage Schema
How do I create a custom Claude Code output style?▼

Create a Markdown file with YAML frontmatter under `~/.claude/output-styles/` for user scope or `.claude/output-styles/` for project scope. Write the body as durable system-prompt instructions covering role, tone, and format, then select the style via `/config`.

What does keep-coding-instructions do in an output style?▼

The keep-coding-instructions field preserves Claude Code's built-in software engineering instructions while changing communication style. Set it to true for coding, review, debugging, or refactoring styles; omit it only for genuinely non-coding personas.

Should I use an output style or a skill for a reusable workflow?▼

Use an output style only for persistent response role, tone, or format across turns. Reusable procedures, checklists, and task workflows belong in a skill, while project conventions belong in CLAUDE.md.

Can a Claude Code plugin force an output style on users?▼

Yes, plugin output styles can set `force-for-plugin: true`, which overrides the user's outputStyle setting while the plugin is enabled. Use it only when the plugin cannot operate safely without the style, since multiple forced styles depend on plugin load order.

Why did my output style change not take effect?▼

Output styles are read as part of the system prompt at session start, so changes require `/clear` or a new session. Plugin component changes additionally require `/reload-plugins` or a restart.