Awesome-omni-skill extend-agent

<essential_principles>

Types of Agent Extensions

~/.claude/skills/<name>/SKILL.md

.cursor/rules/<name>.mdc

~/.claude/commands/<name>.md

.cursor/rules/<name>.mdc

.claude/hooks.json

alwaysApply: true

~/.claude/agents/<name>.md

.cursor/agents/<name>.md

Both Claude Code and Cursor use the same

.claude/agents/

Frontmatter Format by Type

Skill — Claude Code (SKILL.md):

---
name: skill-name
description: What it does and when to use it.
---

Skill — Cursor (.mdc):

---
description: What it does and when it applies
globs: ["**/*.py"]      # File patterns (empty = on-demand)
alwaysApply: false       # true = always in context
---

Subagent — Claude Code vs Cursor differences:

name

description

model

sonnet/opus/haiku/inherit

fast/inherit/<model-id>

tools

readonly

is_background

</essential_principles>

1. Skill — Domain expertise module (SKILL.md for Claude / .mdc for Cursor)
2. Command — Quick action shortcut
3. Hook — Event-driven automation
4. Subagent — Specialist AI instance

Wait for response before proceeding. </intake>

<create_command>

Creating a Command

Claude Code (

.claude/commands/<name>.md

---
description: What this command does (appears in /help)
argument-hint: [optional-arg]
allowed-tools: Bash(git add:*), Bash(git commit:*)  # Optional
---

<objective>
What to accomplish. Use $ARGUMENTS if taking user input.
</objective>

<context>
Current status: !`git status`
Relevant file: @package.json
</context>

<process>
1. Step one
2. Step two
3. Verify
</process>

<success_criteria>
Definition of done.
</success_criteria>

Install:

cp command.md ~/.claude/commands/

/command-name [args]

Cursor (

.cursor/rules/<name>.mdc

alwaysApply: false

---
description: When asked to [action], follow this workflow
globs: []
alwaysApply: false
---

<process>
1. Step one
2. Step two
</process>

Key difference: Cursor has no

/

Arguments:

• $ARGUMENTS

  — all args as one string:

  /fix-issue 123

  →

  $ARGUMENTS = "123"

• $1

  ,

  $2

  ,

  $3

  — positional:

  /review-pr 456 high

  →

  $1=456

  ,

  $2=high

• No args — operates on current context (git status, open file, etc.)

</create_command>

<create_hook>

Creating a Hook (Claude Code)

Hooks are event-driven automation in

.claude/hooks.json

Hook events:

PreToolUse

PostToolUse

UserPromptSubmit

Stop

SubagentStop

SessionStart

SessionEnd

PreCompact

Notification

Command hook template:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/my-hook.sh",
            "timeout": 10000
          }
        ]
      }
    ]
  }
}

Blocking hook output (stdout from your script):

{"decision": "block", "reason": "Why this was blocked"}

Prompt hook template (LLM evaluates instead of a script):

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "Bash",
      "hooks": [{"type": "prompt", "prompt": "Is this command safe: $ARGUMENTS\nReturn JSON: {\"decision\": \"approve\" or \"block\", \"reason\": \"...\"}"}]
    }]
  }
}

Use

prompt

command

claude --debug

Matchers:

"Bash"           → Exact tool name
"Write|Edit"     → Multiple tools (regex OR)
"mcp__.*"        → All MCP tools
(omit matcher)   → Fires for all tools

Cursor equivalent: No native hook system. Use

alwaysApply: true

---
alwaysApply: true
---

NEVER run: rm -rf, git push --force, DROP TABLE.
ALWAYS check git status before committing.

See

skills/security/hooks/

</create_hook>

<create_skill_and_subagent_notes>

Skill complexity rule:

• Simple (4-10 lines of instructions) → single

  SKILL.md

  file
• Complex (multi-step workflows, multiple domains) → router pattern with

  workflows/

  ,

  references/

  ,

  templates/

  subdirs

Subagent execution model — critical constraints:

• Subagents cannot use

  AskUserQuestion

  or wait for user input
• Run isolated — user sees only final output, not intermediate steps
• Invoked automatically (Claude matches

  description

  field) or explicitly via the Task tool
• Project subagents (

  .claude/agents/

  ) override user subagents (

  ~/.claude/agents/

  ) on name conflict
• For multi-stage orchestration (research → plan → execute pipeline): use the planning skill + Task tool, not a single subagent

</create_skill_and_subagent_notes>

<reference_index>

• references/skill-structure.md

  — Complete skill patterns and XML tags

• references/cursor-format.md

  — Cursor .mdc format in depth

• references/core-principles.md

  — Prompting principles for all extension types </reference_index>

<workflows_index>

workflows/create-simple-skill.md

workflows/convert-to-cursor.md

workflows/create-subagent.md

<success_criteria>

• Valid YAML frontmatter for the target platform
• XML-structured body (no markdown headings in body)
• Description specific enough to trigger at the right time
• Installed in the correct location for the platform
• Tested with a representative user request </success_criteria>