Claude code mastery

Skill ToruAI/toru-claude-agents/skills/claude-code-mastery

Multi-agent team for Claude Code: 7 AI specialists (strategy, dev, security, sales, design, data, research) that collaborate and challenge you. Dev-cycle workflow with machine-verifiable completion.

Install

npx -y skills add ToruAI/toru-claude-agents --skill claude-code-mastery

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

15 stars15 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Design better agents, skills and hooks for Claude Code, checking the current spec instead of guessing at fields.

SKILL.md

4.5 KB, as published. Nobody here has run it

Claude Code Mastery - Building Better AI Systems

Use the cc-docs skill to read the official Claude Code documentation before you design anything against it — the spec moves, and this file is a map, not a substitute for it.

Use this knowledge to continuously improve how you work.

Core Capabilities

Subagents

Location: ~/.claude/agents/ (user) or .claude/agents/ (project)

Key fields:

---
name: agent-name
description: When Claude should delegate here
tools: Read, Grep, Glob, Bash, Edit, Write
model: sonnet | opus | haiku | inherit
permissionMode: default | acceptEdits | bypassPermissions
skills: skill-1, skill-2
hooks:
  PreToolUse: [...]
  PostToolUse: [...]
---

System prompt content here...

Use subagents when:

Task needs isolated context
Different tools/permissions needed
Specialized behavior required

Skills

Location: ~/.claude/skills/ (user) or .claude/skills/ (project)

Structure:

skill-name/
├── SKILL.md          # Required - main instructions
├── reference.md      # Optional - detailed docs
└── scripts/          # Optional - utilities

Key fields:

---
name: skill-name
description: When to apply this skill (triggers auto-loading)
allowed-tools: Read, Grep, Glob  # Optional tool restriction
context: fork  # Optional - run in subagent
---

Instructions here...

Use skills when:

Knowledge should auto-apply based on task
Pattern repeats across projects
Want to inject expertise without delegation

Hooks

Location: .claude/settings.json or subagent frontmatter

Events:

PreToolUse - Before tool executes (can block)
PostToolUse - After tool executes
SubagentStart - When subagent begins
SubagentStop - When subagent completes
SessionStart - When session begins

Example:

{
  "hooks": {
    "PostToolUse": [{
      "matcher": "Edit|Write",
      "hooks": [{
        "type": "command",
        "command": "./scripts/auto-lint.sh"
      }]
    }]
  }
}

Use hooks when:

Deterministic action needed (not AI judgment)
Automation on every occurrence
Validation before allowing operations

MCP Servers

Configuration: ~/.claude.json or .mcp.json

Access external tools:

megg (memory)
shadcn (UI components)
perplexity (research)
Custom servers

Improvement Patterns

Pattern: Repeated Context Loading

Problem: Same context loaded every session Solution: Create a skill that auto-applies

---
name: project-context
description: Apply when working on [project]. Auto-loads conventions.
---

Pattern: Manual Validation

Problem: Manually checking things before commit Solution: Create PreToolUse hook

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "Bash(git commit:*)",
      "hooks": [{"type": "command", "command": "./scripts/pre-commit-check.sh"}]
    }]
  }
}

Pattern: Complex Delegation

Problem: Unclear when to use which agent Solution: Improve agent descriptions, add proactive triggers

description: Use proactively when [specific trigger]. Handles [specific task].

Pattern: Lost Knowledge

Problem: Decisions forgotten between sessions Solution: megg_remember after every significant decision

Documentation Reference

Fetch these with the cc-docs skill rather than trusting a remembered field list:

Topic	URL
Subagents	`https://code.claude.com/docs/en/sub-agents`
Skills	`https://code.claude.com/docs/en/skills`
Hooks	`https://code.claude.com/docs/en/hooks-guide`
MCP	`https://code.claude.com/docs/en/mcp`
Headless mode	`https://code.claude.com/docs/en/headless`
Settings	`https://code.claude.com/docs/en/settings`
CLI reference	`https://code.claude.com/docs/en/cli-reference`

Self-Improvement Checklist

When improving workflows:

Identify the friction point
Check docs for existing solution
Choose right tool (skill vs hook vs subagent)
Implement minimal version
Test it works
Document in megg
Consider if others need it (project vs user scope)

Anti-Patterns

Over-engineering: Don't create skills for one-time tasks
Premature automation: Prove manual workflow first
Isolated improvements: Log all changes in megg
Ignoring scope: User skills for personal, project for team