output-customization
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.
What this skill does
# Output Styles Meta Skill > ## ๐จ MANDATORY: Invoke docs-management First > > **STOP - Before providing ANY response about output styles:** > > 1. **INVOKE** `docs-management` skill > 2. **QUERY** for the user's specific topic > 3. **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 **Skipping this step results in outdated or incorrect information.** 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. ## Overview 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. ## When to Use This Skill **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:** - Understanding available output styles - Selecting appropriate output style for a task - Creating custom output styles - Configuring output style frontmatter - Switching between output styles - Comparing output style behaviors - Customizing output format and verbosity ## Keyword Registry for docs-management Queries Use these keywords when querying docs-management skill for official documentation: ### Output Style Fundamentals | 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" | ### Built-in 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" | ### Style Configuration | 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" | ### Style Management | 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" | ### Use Cases | 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" | ### Comparisons to Related Features | 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 Skills | "output styles vs skills", "stored prompts vs stored system prompts" | ### Custom Style Development | 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" | ## Quick Decision Tree **What do you want to do?** 1. **Understand available styles** -> Query docs-management: "built-in output styles", "output style overview" 2. **Use default coding assistant** -> Query docs-management: "default output style", "software engineering style" 3. **Learn about the codebase** -> Query docs-management: "explanatory style", "educational insights" 4. **Learn by doing (hands-on)** -> Query docs-management: "learning style", "TODO human markers", "learn-by-doing" 5. **Switch output style** -> Query docs-management: "/output-style command", "switch output style" 6. **Create custom style** -> Query docs-management: "create custom output style", "output style frontmatter" 7. **Compare to related features** -> Query docs-management: "output styles vs CLAUDE.md", "output styles vs agents" 8. **Where to save style files** -> Query docs-management: "output style file location", "~/.claude/output-styles" ## Topic Coverage ### Built-in Output Styles - Default: Standard software engineering assistant behavior - Explanatory: Adds educational "Insights" between tasks to help understand implementation choices - Learning: Collaborative learn-by-doing mode with `TODO(human)` markers for user contributions ### Output Style Frontmatter - name field (optional - defaults to filename) - description field (optional - for UI display in /output-style menu) - keep-coding-instructions field (optional - default false, whether to keep coding instructions in system prompt) ### Style Configuration Options - Default style configuration - Per-session style switching - Style persistence across sessions ### /output-style Command - List available styles - Switch to different style - View current style - Style selection syntax ### Custom Style Creation - File location for custom styles - Frontmatter structure - Prompt crafting for custom behavior - Testing and validation ### Style Selection Criteria - Task-based recommendations - Verbosity preferences - Output format needs - Code vs explanation balance ### Style Comparisons - Output Styles vs CLAUDE.md vs --append-system-prompt (system prompt modification approaches) - Output Styles vs Agents (main loop vs specific tasks, different configuration options) - Output Styles vs Skills (stored system prompts vs stored prompts) - When to use each approach ## Delegation Patterns ### Standard Query Pattern ```text User 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 ``` ### Multi-Topic Query Pattern ```text 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 ``` ### Troubleshooting Pattern ```text 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 ``` ## Troubleshooting Quick Reference | 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 | "mar
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts โ single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score โฅ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.