Command Development
Author reusable Claude Code slash commands with frontmatter, dynamic arguments, and bash-backed context so solo builders stop retyping the same agent prompts.
Overview
Command Development is an agent skill most often used in Build (also Ship, Operate) that teaches how to create, structure, and maintain Claude Code slash commands with frontmatter and dynamic execution patterns.
Install
npx skills add https://github.com/anthropics/claude-code --skill command-developmentWhat is this skill?
- Markdown slash commands with YAML frontmatter for configuration and reuse
- Dynamic arguments, file references, and bash execution to inject live context
- AskUserQuestion and interactive command patterns for guided workflows
- Command organization, namespacing, and team-sharing conventions
- Explicit guidance that commands are instructions for the agent, not end-user UI copy
Adoption & trust: 9.4k installs on skills.sh; 131k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You rely on Claude Code daily but keep rewriting the same multi-step prompts instead of packaging them as dependable, shareable slash commands.
Who is it for?
Solo builders standardizing Claude Code workflows in a repo or small team kit who already use slash commands occasionally and want production-grade structure.
Skip if: Builders only using Cursor or Codex without Claude Code slash commands, or anyone who needs REST API design rather than agent prompt packaging.
When should I use this skill?
User asks to create a slash command, add a command, write a custom command, define command arguments, use command frontmatter, organize commands, create commands with file references, interactive commands, or AskUserQues
What do I get? / Deliverables
You ship a folder of well-structured command Markdown files your agent invokes consistently, with arguments, context hooks, and optional user prompts wired in.
- One or more slash command Markdown files with valid frontmatter
- Documented argument and bash-context conventions for your project
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Slash commands are agent-side workflow assets you create while shaping how Claude Code behaves in your repo. Canonical shelf is agent-tooling because the skill teaches command file structure, namespacing, and interaction patterns—not generic app backend work.
Where it fits
Define a /scaffold-api slash command that reads package.json via bash and applies your folder layout rules.
Package a /pr-review command with file refs to changed paths so every review follows the same severity checklist.
Refactor command namespaces after merging two repos so teammates still find the right slash workflow.
How it compares
Use for Claude Code slash-command authoring—not for OpenAPI contracts or MCP server wiring.
Common Questions / FAQ
Who is command development for?
Indie and solo developers shipping with Claude Code who want reusable slash commands for recurring agent tasks like reviews, scaffolding, or release prep.
When should I use command development?
During Build when adding agent-tooling to a repo; during Ship when codifying review or launch checklists as commands; during Operate when updating shared team command libraries after process changes.
Is command development safe to install?
Review the Security Audits panel on this Prism page before installing; commands that run bash can read local files and shell output, so scope permissions and secrets carefully in your own frontmatter.
SKILL.md
READMESKILL.md - Command Development
# Command Development for Claude Code ## Overview Slash commands are frequently-used prompts defined as Markdown files that Claude executes during interactive sessions. Understanding command structure, frontmatter options, and dynamic features enables creating powerful, reusable workflows. **Key concepts:** - Markdown file format for commands - YAML frontmatter for configuration - Dynamic arguments and file references - Bash execution for context - Command organization and namespacing ## Command Basics ### What is a Slash Command? A slash command is a Markdown file containing a prompt that Claude executes when invoked. Commands provide: - **Reusability**: Define once, use repeatedly - **Consistency**: Standardize common workflows - **Sharing**: Distribute across team or projects - **Efficiency**: Quick access to complex prompts ### Critical: Commands are Instructions FOR Claude **Commands are written for agent consumption, not human consumption.** When a user invokes `/command-name`, the command content becomes Claude's instructions. Write commands as directives TO Claude about what to do, not as messages TO the user. **Correct approach (instructions for Claude):** ```markdown Review this code for security vulnerabilities including: - SQL injection - XSS attacks - Authentication issues Provide specific line numbers and severity ratings. ``` **Incorrect approach (messages to user):** ```markdown This command will review your code for security issues. You'll receive a report with vulnerability details. ``` The first example tells Claude what to do. The second tells the user what will happen but doesn't instruct Claude. Always use the first approach. ### Command Locations **Project commands** (shared with team): - Location: `.claude/commands/` - Scope: Available in specific project - Label: Shown as "(project)" in `/help` - Use for: Team workflows, project-specific tasks **Personal commands** (available everywhere): - Location: `~/.claude/commands/` - Scope: Available in all projects - Label: Shown as "(user)" in `/help` - Use for: Personal workflows, cross-project utilities **Plugin commands** (bundled with plugins): - Location: `plugin-name/commands/` - Scope: Available when plugin installed - Label: Shown as "(plugin-name)" in `/help` - Use for: Plugin-specific functionality ## File Format ### Basic Structure Commands are Markdown files with `.md` extension: ``` .claude/commands/ ├── review.md # /review command ├── test.md # /test command └── deploy.md # /deploy command ``` **Simple command:** ```markdown Review this code for security vulnerabilities including: - SQL injection - XSS attacks - Authentication bypass - Insecure data handling ``` No frontmatter needed for basic commands. ### With YAML Frontmatter Add configuration using YAML frontmatter: ```markdown --- description: Review code for security issues allowed-tools: Read, Grep, Bash(git:*) model: sonnet --- Review this code for security vulnerabilities... ``` ## YAML Frontmatter Fields ### description **Purpose:** Brief description shown in `/help` **Type:** String **Default:** First line of command prompt ```yaml --- description: Review pull request for code quality --- ``` **Best practice:** Clear, actionable description (under 60 characters) ### allowed-tools **Purpose:** Specify which tools command can use **Type:** String or Array **Default:** Inherits from