command-creator
Create custom slash commands for Claude Code with proper markdown structure and YAML frontmatter. Use when: creating commands, generating slash commands, making workflow automations. Activates for: "create command", "generate command", "new command", "slash command", "make command"
What this skill does
# Command Creator Generate custom slash commands for Claude Code with proper structure. ## When to Use - Creating project-specific commands - Automating repetitive workflows - Building team-shared commands - Standardizing common operations ## Command Structure Commands are markdown files in the `commands/` directory with YAML frontmatter: ```markdown --- description: Brief description of what this command does --- # Command instructions Detailed instructions for Claude to follow when this command is executed. ## Context Information about when and how to use this command. ## Examples Example usage and expected outcomes. ``` ## Core Workflow ### 1. Gather Requirements Ask the user: - **Command name**: `/command-name` (what should user type?) - **Purpose**: What does this command do? - **Parameters**: Does it need arguments? - **Context**: When should it be used? - **Location**: Project-local or global? ### 2. Generate Command File **Location:** - Global: `~/.claude/skills/super-claude/plugins/[plugin]/commands/command-name.md` - Project: `/path/to/project/.claude/commands/command-name.md` **Format:** ```markdown --- description: One-line description (required) --- # Command Name ## Purpose Clear explanation of what this command does. ## Usage \`\`\` /command-name [arguments] \`\`\` ## Instructions for Claude Step-by-step instructions for Claude to follow: 1. First action 2. Second action 3. Third action ## Parameters - `arg1`: Description of first argument - `arg2`: Description of second argument (optional) ## Examples ### Example 1: Common Use Case \`\`\` /command-name value1 value2 \`\`\` Expected outcome: [description] ### Example 2: With Options \`\`\` /command-name --option value \`\`\` Expected outcome: [description] ## Notes - Important consideration 1 - Important consideration 2 ``` ### 3. Validate Command Ensure: - ✅ Description is clear and concise - ✅ Instructions are actionable - ✅ Examples are realistic - ✅ Parameter descriptions are complete - ✅ File is in correct location ## Example Commands ### Project Setup Command ```markdown --- description: Initialize a new TanStack Start project with drizzle and better-auth --- # Setup TanStack Fullstack ## Purpose Quickly scaffold a new TanStack Start project with database and authentication. ## Usage \`\`\` /setup-tanstack-fullstack [project-name] \`\`\` ## Instructions for Claude 1. Create new directory with project-name 2. Initialize TanStack Start project 3. Install and configure Drizzle ORM with Postgres 4. Set up better-auth with Drizzle adapter 5. Create initial database schema 6. Set up environment variables 7. Create README with setup instructions ## Parameters - `project-name`: Name of the new project directory ## Examples ### Example: Create New Project \`\`\` /setup-tanstack-fullstack my-app \`\`\` Creates: - my-app/ directory - TanStack Start configuration - Drizzle + Postgres setup - better-auth integration - Initial schema and migrations ``` ### Code Review Command ```markdown --- description: Perform comprehensive code review with focus areas --- # Review Code ## Purpose Systematic code review checking for common issues and best practices. ## Usage \`\`\` /review-code [--focus=area] \`\`\` ## Instructions for Claude 1. Analyze current file or git diff 2. Check for: - Type safety issues - Accessibility concerns - Performance problems - Security vulnerabilities - Best practice violations 3. If --focus provided, emphasize that area 4. Provide specific, actionable feedback 5. Suggest improvements with code examples ## Parameters - `--focus`: Optional focus area (security, performance, accessibility, types) ## Examples ### Example: General Review \`\`\` /review-code \`\`\` ### Example: Security Focus \`\`\` /review-code --focus=security \`\`\` ``` ### Deployment Command ```markdown --- description: Deploy to Cloudflare Pages with pre-deployment checks --- # Deploy Cloudflare ## Purpose Deploy current project to Cloudflare Pages with safety checks. ## Usage \`\`\` /deploy-cloudflare [--environment=prod|staging] \`\`\` ## Instructions for Claude 1. Run pre-deployment checks: - All tests passing - No TypeScript errors - No ESLint errors - Build succeeds 2. Confirm environment variables are set 3. Build production bundle 4. Deploy to Cloudflare Pages 5. Verify deployment successful 6. Provide deployment URL ## Parameters - `--environment`: Target environment (default: staging) ## Examples ### Example: Deploy to Staging \`\`\` /deploy-cloudflare \`\`\` ### Example: Deploy to Production \`\`\` /deploy-cloudflare --environment=prod \`\`\` ``` ## Command Categories ### Project Setup - `/setup-*`: Initialize new projects - `/scaffold-*`: Create project structure ### Code Generation - `/generate-*`: Create code/files - `/create-*`: Create components/modules ### Code Quality - `/review-*`: Code review commands - `/fix-*`: Auto-fix issues - `/lint-*`: Linting operations ### Testing - `/test-*`: Run tests - `/coverage-*`: Coverage analysis ### Deployment - `/deploy-*`: Deployment operations - `/release-*`: Release management ### Documentation - `/docs-*`: Generate documentation - `/explain-*`: Explain code/concepts ## Best Practices 1. **Clear Names**: Use descriptive command names 2. **Single Purpose**: One command = one clear action 3. **Good Defaults**: Sensible default parameters 4. **Safe Operations**: Confirm destructive actions 5. **Helpful Output**: Provide clear feedback ## Anti-Patterns - ❌ Generic names (helper, util, do-thing) - ❌ Multiple unrelated actions in one command - ❌ Missing parameter descriptions - ❌ No examples - ❌ Destructive operations without confirmation ## Troubleshooting ### Command Not Found **Solution**: Ensure file is in `commands/` directory and Claude Code has been restarted ### Command Parameters Not Working **Solution**: Check parameter format in examples, ensure clear documentation ## References - [Claude Code Commands Documentation](https://docs.claude.com/en/docs/claude-code/commands) - [super-claude Command Examples](../../commands/)
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.