Central authority for Claude Code output styles. Covers built-in output styles (Default, Explanatory, Learning), custom output styles, output style frontmatter (name, description, keep-coding-instructions), /output-style command, style switching, output style creation and customization, output style comparisons (vs CLAUDE.md, vs agents, vs slash commands), and output style settings. Assists with selecting appropriate output styles, creating custom styles, configuring output behavior, and understanding style differences. Delegates 100% to docs-management skill for official documentation.
Manages Claude Code output styles for customizing response format and verbosity. Triggers when users ask about built-in styles (Default, Explanatory, Learning), create custom styles, switch styles with /output-style command, or configure style frontmatter.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install claude-code-observability@melodic-softwareThis skill is limited to using the following tools:
references/audit-framework.md🚨 MANDATORY: Invoke docs-management First
STOP - Before providing ANY response about output styles:
- INVOKE
docs-managementskill- QUERY for the user's specific topic
- BASE all responses EXCLUSIVELY on official documentation loaded
Skipping this step results in outdated or incorrect information.
Verification Checkpoint
Before responding, verify:
- Did I invoke docs-management skill?
- Did official documentation load?
- Is my response based EXCLUSIVELY on official docs?
If ANY checkbox is unchecked, STOP and invoke docs-management first.
Central authority for Claude Code output styles. This skill uses 100% delegation to docs-management - it contains NO duplicated official documentation.
Architecture: Pure delegation with keyword registry. All official documentation is accessed via docs-management skill queries.
Keywords: output styles, output style, concise style, verbose style, markdown style, code-sparse style, /output-style command, custom output styles, output style frontmatter, output style prompt, style switching, output behavior, response format, output formatting
Use this skill when:
Use these keywords when querying docs-management skill for official documentation:
| Topic | Keywords |
|---|---|
| Overview | "output styles", "output style overview", "response formatting" |
| Built-in Styles | "built-in output styles", "default styles" |
| Custom Styles | "custom output styles", "creating output styles" |
| Topic | Keywords |
|---|---|
| Default Style | "default output style", "default style", "software engineering style" |
| Explanatory Style | "explanatory style", "explanatory output", "educational insights", "codebase insights" |
| Learning Style | "learning style", "learning output", "learn-by-doing", "TODO human markers", "collaborative coding" |
| Topic | Keywords |
|---|---|
| Frontmatter | "output style frontmatter", "style YAML frontmatter" |
| Name Field | "output style name", "style naming" |
| Description Field | "output style description", "style description" |
| Keep Coding Instructions | "keep-coding-instructions", "coding instructions", "software engineering prompts" |
| Style File Location | "output style file location", "~/.claude/output-styles", ".claude/output-styles", "user level styles", "project level styles" |
| Topic | Keywords |
|---|---|
| Switching Styles | "/output-style command", "switch output style", "change style" |
| Style Selection | "select output style", "choose style", "style recommendations" |
| Style Comparison | "compare output styles", "style differences", "style comparison" |
| Topic | Keywords |
|---|---|
| Task-Based Selection | "output style use cases", "when to use styles" |
| Coding Tasks | "output style coding", "code-focused style" |
| Documentation Tasks | "output style documentation", "writing-focused style" |
| Learning Tasks | "output style learning", "educational style" |
| Topic | Keywords |
|---|---|
| vs CLAUDE.md | "output styles vs CLAUDE.md", "system prompt vs user message", "output style CLAUDE.md difference" |
| vs append-system-prompt | "output styles vs append-system-prompt", "system prompt modification", "--append-system-prompt" |
| vs Agents | "output styles vs agents", "output style agent difference", "sub-agents vs output styles" |
| vs Slash Commands | "output styles vs slash commands", "stored prompts vs stored system prompts" |
| Topic | Keywords |
|---|---|
| Creating Styles | "create custom output style", "new output style" |
| Style Templates | "output style template", "style starting point" |
| Style Location | "output style file location", "where to save styles" |
| Style Testing | "test output style", "validate style" |
What do you want to do?
TODO(human) markers for user contributionsUser asks: "What output styles are available?"
1. Invoke docs-management skill
2. Use keywords: "built-in output styles", "output style overview"
3. Load official documentation
4. Provide guidance based EXCLUSIVELY on official docs
User asks: "I want brief responses with less code"
1. Invoke docs-management skill with multiple queries:
- "concise style", "brief responses"
- "code-sparse style", "minimal code"
2. Synthesize guidance from official documentation
User reports: "My custom output style isn't working"
1. Invoke docs-management skill
2. Use keywords: "output style frontmatter", "create custom output style"
3. Check official docs for style configuration requirements
4. Guide user through proper style setup
| Issue | Keywords for docs-management |
|---|---|
| Style not changing | "/output-style command", "switch output style" |
| Custom style not loading | "output style frontmatter", "style file location" |
| Too verbose responses | "concise style", "brief responses" |
| Not enough detail | "verbose style", "detailed responses" |
| Want formatted output | "markdown style", "formatted output" |
| Too much code in output | "code-sparse style", "minimal code" |
| Style selection guidance | "output style use cases", "style recommendations" |
This repository does not currently use custom output styles. Output style documentation is relevant for:
When working with output style topics, always use the docs-management skill to access official documentation.
This skill provides the validation criteria used by the output-style-auditor agent for formal audits.
| Resource | Location | Purpose |
|---|---|---|
| Audit Framework | references/audit-framework.md | Query guides and scoring criteria |
| Category | Points | Key Criteria |
|---|---|---|
| File Structure | 20 | Correct location, .md extension |
| YAML Frontmatter | 30 | Required fields present and valid |
| Content Quality | 30 | Clear instructions, proper structure |
| Compatibility | 20 | Works with style switching, no conflicts |
Thresholds: 85+ = PASS, 70-84 = PASS WITH WARNINGS, <70 = FAIL
The output-style-auditor agent (Haiku model) performs formal audits using this skill:
skills: output-customization/audit-output-styles commandWhen auditing output styles that reference external technologies (scripts, packages, runtimes), the auditor MUST validate claims using MCP servers before flagging findings.
Technologies Requiring MCP Validation:
Validation Rule:
Never flag a technology usage as incorrect without first:
Stale Data Warning:
Official Documentation (via docs-management skill):
Repository-Specific:
.claude/settings.json (outputStyle setting)Date: 2025-11-28 Model: claude-opus-4-5-20251101
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.