Skip to content
mcp/skillhub

Agent Skill

Skill Development skill

Skill Developmentanthropics/claude-codeplugins/plugin-dev/skills/skill-development/SKILL.md

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

153k

always on

63 tokname + description

once used

4,941 tokSKILL.md body

bundled files

111 KB

repo stars

153kGitHub

Install the Skill Development skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/anthropics/claude-code --skill 'Skill Development'

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/anthropics/claude-code.git /tmp/claude-code
mkdir -p ~/.claude/skills
cp -R /tmp/claude-code/plugins/plugin-dev/skills/skill-development ~/.claude/skills/skill-development

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description63 tok
When the agent uses itThe SKILL.md instructions4,941 tok
Only if opened1 bundled files (11 KB)varies

Until it is used, Skill Development costs about 22× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 10 skills from anthropics/claude-code would load 819 tokens of descriptions. Skills vs MCP study

Checks

  • The instructions are over 500 lines; the specification suggests moving detail into reference files.
  • The name breaks the specification (lowercase letters, digits and single hyphens, up to 64 characters).

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Skill Development for Claude Code Plugins
  • About Skills
  • What Skills Provide
  • Anatomy of a Skill
  • Progressive Disclosure Design Principle
  • Skill Creation Process
  • Step 1: Understanding the Skill with Concrete Examples
  • Step 2: Planning the Reusable Skill Contents
  • Step 3: Create Skill Structure
  • Step 4: Edit the Skill
  • Step 5: Validate and Test
  • Step 6: Iterate
  • Plugin-Specific Considerations
  • Skill Location in Plugins
  • Auto-Discovery
  • No Packaging Needed
  • Testing in Plugins
  • Examples from Plugin-Dev
  • Progressive Disclosure in Practice
  • What Goes in SKILL.md
  • What Goes in references/
  • What Goes in examples/
  • What Goes in scripts/
  • Writing Style Requirements

More skills from anthropics/claude-code

All skills in this repo
  1. Agent Developmentanthropics/claude-code

    This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

    153k180 tok idle · 2,389 in use
  2. Command Developmentanthropics/claude-code

    This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

    153k99 tok idle · 4,170 in use
  3. Hook Developmentanthropics/claude-code

    This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

    153k6117 tok idle · 3,853 in use
  4. MCP Integrationanthropics/claude-code

    This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

    153k97 tok idle · 2,921 in use
  5. Plugin Settingsanthropics/claude-code

    This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.

    153k381 tok idle · 3,021 in use
  6. Plugin Structureanthropics/claude-code

    This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.

    153k92 tok idle · 3,110 in use
  7. Writing Hookify Rulesanthropics/claude-code

    This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

    153k51 tok idle · 2,188 in use
  8. claude-opus-4-5-migrationanthropics/claude-code

    Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

    153k100 tok idle · 1,175 in use