generating-output-styles
Creates custom output styles for Claude Code that modify system prompts and behavior. Use when the user asks to create output styles, customize Claude's response format, generate output-style files, or mentions output style configuration.
What this skill does
# Generating Output Styles Creates custom output styles for Claude Code following Anthropic's standards and best practices. ## Context Output styles modify Claude Code's system prompt to adapt its behavior beyond software engineering. They directly affect the main agent loop and control response tone, structure, and approach. **Key capabilities:** - Generate valid output style markdown files with frontmatter - Apply proper naming and description standards - Structure instructions following progressive disclosure - Configure keep-coding-instructions appropriately - Place files in correct locations (user vs project level) ## Workflow ### Phase 1: Gather Requirements 1. Determine the output style purpose and target behavior 2. Identify if coding instructions should be retained 3. Choose placement: `~/.claude/output-styles/` (user) or `.claude/output-styles/` (project) 4. Reference output style documentation at `.claude/skills/output-style/references/output-style-docs.md` ### Phase 2: Create Output Style File 1. **Craft frontmatter:** - `name`: Clear, descriptive name (shown in UI) - `description`: Brief explanation for users - `keep-coding-instructions`: true/false (default: false) 2. **Write system prompt modifications:** - Start with role definition - Define specific behaviors and approaches - Include formatting guidelines - Add any special instructions or constraints - Keep instructions concise and actionable 3. **Structure content:** - Use markdown headers for organization - Provide concrete examples when helpful - Avoid contradicting core Claude Code functionality - Focus on additive instructions, not restrictions ### Phase 3: Validate and Save 1. Verify YAML frontmatter syntax (opening/closing ---) 2. Ensure description is user-friendly and clear 3. Confirm keep-coding-instructions matches requirements 4. Save to appropriate location 5. Test activation with `/output-style` command ## Implementation Strategy **File format:** ```markdown --- name: Style Name description: User-facing description of what this style does keep-coding-instructions: false --- # Custom Style Instructions You are an interactive CLI tool that helps users with software engineering tasks. [Custom instructions...] ## Specific Behaviors [Define how the assistant should behave in this style...] ``` **Naming guidelines:** - Use title case for `name` field - Keep names concise but descriptive - Avoid technical jargon in names - Examples: "Explanatory", "Learning", "Technical Writer" **Description guidelines:** - Write for end users, not developers - Explain what the style does, not how - Keep under 200 characters - Focus on benefits and use cases **keep-coding-instructions:** - `false` (default): Removes software engineering instructions, clean slate - `true`: Retains coding guidance, adds modifications on top ## Constraints - Must include valid YAML frontmatter with all required fields - System prompt modifications should complement, not contradict, core Claude Code - Cannot override tool permissions or security restrictions - File must use `.md` extension - Must be placed in recognized output-styles directory - Description shown in UI, so must be user-friendly ## Success Criteria - Valid markdown file with proper YAML frontmatter - Name and description follow guidelines - keep-coding-instructions set appropriately - System prompt instructions are clear and actionable - File saved to correct location - Can be activated via `/output-style` command - Produces expected behavioral changes when active ## Examples **Example 1: Technical Writer Style** ```markdown --- name: Technical Writer description: Produces detailed documentation with comprehensive explanations keep-coding-instructions: true --- # Technical Writer Instructions You are an interactive CLI tool that helps users with software engineering tasks. ## Documentation Approach - Provide comprehensive explanations for all code changes - Include detailed comments in code - Document edge cases and assumptions - Create thorough README sections when relevant - Explain trade-offs in implementation decisions ## Formatting - Use clear section headers - Include code examples with explanations - Add inline comments for complex logic - Structure responses with intro, body, conclusion ``` **Example 2: Minimalist Style** ```markdown --- name: Minimalist description: Provides concise responses with minimal explanation keep-coding-instructions: true --- # Minimalist Instructions You are an interactive CLI tool that helps users with software engineering tasks. ## Communication Style - Keep responses under 5 lines when possible - Use code without explanatory prose - Omit obvious explanations - Respond with direct answers - Only elaborate when explicitly asked ``` ## Quick Reference **Common output style patterns:** 1. **Educational styles**: Set `keep-coding-instructions: true`, add explanatory guidance 2. **Specialized domain styles**: Set `keep-coding-instructions: false`, define new role 3. **Formatting styles**: Set `keep-coding-instructions: true`, add response structure rules 4. **Tone modifiers**: Set `keep-coding-instructions: true`, adjust communication style **Testing workflow:** 1. Create output style file 2. Run `/output-style` to verify it appears in menu 3. Activate the style 4. Test with representative tasks 5. Iterate based on behavior 6. Verify style persists in `.claude/settings.local.json` ## Related Documentation - Output Style Docs: `.claude/skills/output-style/references/output-style-docs.md` - Output Style Template: `.claude/templates/output-style.md` (if exists) - Settings Documentation: Claude Code settings reference
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 — 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 ≥ 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.