Command Code

Agent Skills

Command Code supports Agent Skills - a lightweight, open standard for extending AI agents with specialized knowledge and workflows.

What are Agent Skills?

Agent Skills are modular, self-contained instruction sets that teach Command Code how to perform specific tasks. Each skill is a folder containing a skill.md file with metadata and step-by-step guidance.

Think of skills as expert playbooks that Command Code can reference when needed. Instead of explaining the same process repeatedly, you define it once in a skill, and Command Code automatically applies it when appropriate.

How Command Code implements skills?

Command Code fully implements the Agent Skills open standard with two storage locations:

User-level skills (global)

Stored in ~/.commandcode/skills/ and available across all your projects.

Perfect for:

  • General development workflows
  • Exploratory workflows
  • Cross-project best practices

Project-level skills (local)

Stored in .commandcode/skills/ within your project and only available in that project.

Perfect for:

  • Project-specific patterns
  • Team conventions
  • Architecture guidelines
  • Domain-specific workflows

Quickstart

Create your first skill

User-level skill:

Create a global code review skill

mkdir -p ~/.commandcode/skills/code-review cat > ~/.commandcode/skills/code-review/SKILL.md << 'EOF' --- name: code-review description: Perform thorough code reviews checking for bugs, security issues, and best practices --- # Code Review Checklist When reviewing code, check: ## Security - [ ] No hardcoded credentials or API keys - [ ] Input validation on all user data - [ ] Proper authentication and authorization ## Code Quality - [ ] Clear, descriptive variable names - [ ] Functions do one thing well - [ ] No code duplication - [ ] Edge cases handled ## Performance - [ ] No unnecessary loops or operations - [ ] Efficient data structures - [ ] Database queries optimized ## Testing - [ ] Unit tests cover main functionality - [ ] Edge cases tested - [ ] Error conditions tested EOF

Project-level skill:

Create a project-specific API skill

mkdir -p .commandcode/skills/api-guidelines cat > .commandcode/skills/api-guidelines/SKILL.md << 'EOF' --- name: api-guidelines description: API design patterns and conventions for this project --- # API Guidelines ## Endpoint naming - Use plural nouns: `/users`, `/posts` - Use kebab-case: `/user-profiles` - Version in URL: `/v1/users` ## Response format \```json { "data": { ... }, "meta": { "count": 10, "page": 1 } } \``` ## Error handling - 400: Bad request (validation errors) - 401: Unauthorized - 403: Forbidden - 404: Not found - 500: Server error EOF

Browse and use skills

Use the /skills slash command to view all available skills:

Open skills menu

# In Command Code session /skills

This shows:

  • All user-level skills with (user) label
  • All project-level skills with (project) label
  • Use arrow keys to navigate
  • Press Enter to open any skill in your editor
  • Press Esc to close

Command Code automatically sees all your skills and uses them when relevant to the task.

Skill format

Every skill is a directory containing a SKILL.md file:

my-skill/ ├── SKILL.md # Required: instructions + metadata ├── scripts/ # Optional: executable code ├── references/ # Optional: documentation └── assets/ # Optional: templates, resources

SKILL.md structure

--- name: skill-name description: What this skill does and when to use it license: MIT (optional) compatibility: ["Requires git"] (optional) metadata: (optional) author: "team-name" version: "1.0" allowed-tools: ["Read", "Grep"] (optional) --- # Skill Instructions Step-by-step guidance for Command Code... ## When to use this skill Use this skill when... ## How to perform the task 1. First step... 2. Second step...

Required fields:

  • name: Short identifier (lowercase, hyphens only)
  • description: What the skill does and when to use it (max 1024 characters)

Optional fields:

  • license: License information
  • compatibility: Environment requirements
  • metadata: Author, version, etc.
  • allowed-tools: Pre-approved tools (experimental)

How it works

Skills use progressive disclosure to manage context efficiently:

  1. Discovery: Command Code loads only name + description of each skill at startup (~100 tokens per skill)

  2. Activation: When a task matches a skill's description, Command Code reads the full SKILL.md instructions

  3. Execution: Command Code follows the instructions, optionally loading referenced files as needed

This keeps Command Code fast while giving access to more context on demand.

Next steps