claude-code-masteryMaster Claude Code for coding tasks. Includes setup scripts, dev team subagents (starter pack or full team), self-improving learning system, diagnostics, and troubleshooting.
Install via ClawdBot CLI:
clawdbot install cheenu1092-oss/claude-code-masteryComplete skill for setting up, optimizing, and mastering Claude Code with a full development team of subagents.
Official Docs: https://code.claude.com/docs
Run this first:
command -v claude >/dev/null && echo "✅ Claude Code installed - SKIP to 'Daily Use' section" || echo "❌ Not installed - follow 'First-Time Setup' below"If Claude Code is already installed, skip directly to the "Daily Use" section below.
Note to bot: Only follow this section if Claude Code is NOT installed. Check with the command above. Once setup is complete, this section can be ignored on future invocations.
Run these in order:
cd ~/clawd/skills/claude-code-mastery/scripts
# 1. Check dependencies
./01-check-dependencies.sh
# 2. Install Claude Code
./02-install-claude-code.sh
# 3. Authenticate
./03-first-time-auth.sh
# 4. Install dev team subagents
./04-install-subagents.sh # Starter pack (3 agents) - recommended
./04-install-subagents.sh --full-team # All 11 agents
# 5. (Optional) Persistent memory - prompts y/N, default No
./05-setup-claude-mem.sh # Interactive prompt
./05-setup-claude-mem.sh --skip # Skip entirely
./05-setup-claude-mem.sh --yes # Install without promptingEdit config.sh to customize:
VALID_MODELS — Add models as Anthropic releases themHEARTBEAT_DIAGNOSTICS — Enable/disable in heartbeat (default: false)INSTALL_MODE — Default to "starter" or "full"| Issue | Solution |
|-------|----------|
| "Command not found" | Add ~/.local/bin to PATH |
| Auth errors | Run ./03-first-time-auth.sh |
| Slow startup | First run indexes codebase |
| Subagents not showing | Run ./04-install-subagents.sh |
After setup, add the maintenance task to your HEARTBEAT.md (see "Heartbeat Maintenance" in Daily Use section).
Setup complete! Continue to Daily Use section.
This section covers ongoing usage - reference this for all coding tasks.
Subagents are installed to ~/.claude/agents/. Each has a "Learn More" section with curated links to deepen expertise.
Most users only need these:
| Agent | Model | Purpose |
|-------|-------|---------|
| senior-dev | Sonnet | Architecture, complex code, code review |
| project-manager | Sonnet | Task breakdown, timelines, dependencies |
| junior-dev | Haiku | Quick fixes, simple tasks (fast & cheap) |
Install: ./04-install-subagents.sh (or --minimal)
For larger projects, install all 11 with --full-team:
| Agent | Model | Purpose |
|-------|-------|---------|
| senior-dev | Sonnet | Architecture, complex code, code review |
| project-manager | Sonnet | Task breakdown, timelines, dependencies |
| junior-dev | Haiku | Quick fixes, simple tasks (fast & cheap) |
| frontend-dev | Sonnet | React, UI, CSS, client-side |
| backend-dev | Sonnet | APIs, databases, server-side |
| ai-engineer | Sonnet | LLM apps, RAG, prompts, agents |
| ml-engineer | Sonnet | ML models, training, MLOps |
| data-scientist | Sonnet | SQL, analysis, statistics |
| data-engineer | Sonnet | Pipelines, ETL, data infrastructure |
| product-manager | Sonnet | Requirements, user stories, prioritization |
| devops | Sonnet | CI/CD, Docker, K8s, infrastructure, automation |
Interactive mode: Use the /agent slash command or natural language:
/agent senior-dev
Use the senior-dev agent to review this codeNon-interactive mode (-p): Use the --agent flag:
claude --agent senior-dev -p "review this code for security issues"
claude --agent project-manager -p "create a task breakdown for auth feature"
claude --agent junior-dev -p "fix the typo in README.md"Note: Claude Code does NOT auto-delegate to subagents based on task type. You must explicitly specify which agent to use.
Multi-agent handoff: For tasks needing multiple specialists, use HANDOFF.md to pass context between agents. See docs/workflows.md for the full pattern.
claude # Start interactive
claude -c # Continue previous session
claude -p "prompt" # Non-interactive mode/agents - Manage subagents
/clear - Clear conversation (use between tasks!)
/compact - Compress context
/model - Change model
/help - All commandsShift+Tab - Toggle Plan mode (read-only exploration)
Ctrl+C - Cancel operation
Ctrl+B - Background task| Command | What it does | When to use |
|---------|--------------|-------------|
| /clear | Clear conversation, start fresh | Between unrelated tasks |
| /compact | Summarize and compress context | When context getting full |
| Shift+Tab | Toggle Plan mode (read-only) | Exploration before implementing |
Best practices:
/clear between unrelated tasksCreate .claude/settings.json in your project:
{
"model": "sonnet",
"permissions": {
"allow": ["Bash(npm:*)", "Bash(git:*)", "Read", "Write", "Edit"],
"deny": ["Bash(rm -rf:*)", "Bash(sudo:*)"]
}
}Create CLAUDE.md in your project root (Claude reads this automatically):
# Project: MyApp
## Tech Stack
- Frontend: React, TypeScript, Tailwind
- Backend: Node.js, PostgreSQL
## Commands
- `npm run dev` - Start dev server
- `npm test` - Run testsSee examples/CLAUDE-template.md for a full template.
Check status:
pgrep -f "worker-service" >/dev/null && echo "running" || echo "stopped"Start if stopped:
cd ~/.claude/plugins/marketplaces/thedotmack && bun plugin/scripts/worker-service.cjs startWeb UI: http://localhost:37777
Quick diagnostics:
~/clawd/skills/claude-code-mastery/scripts/06-diagnostics.shFull troubleshooting (if issues found):
~/clawd/skills/claude-code-mastery/scripts/08-troubleshoot.shCommon issues guide: See docs/troubleshooting.md for solutions to:
Add to your HEARTBEAT.md for automatic maintenance:
## Claude Code Maintenance
**Last Health Check:** [timestamp]
**Last Learning Session:** [timestamp]
### Every Heartbeat (if coding tasks active):
1. Quick claude-mem check (if installed):
`pgrep -f "worker-service" >/dev/null && echo "running" || echo "stopped"`
- Only restart if stopped
- Note: pgrep saves ~500 tokens vs full status command
### Daily (morning):
1. Quick health check: `command -v claude && pgrep -f "worker-service"`
2. Only run full diagnostics if quick check fails
### Weekly (Sunday):
1. Run: `~/clawd/skills/claude-code-mastery/scripts/07-weekly-improvement-cron.sh`
2. Propose improvements (require human approval)
### Weekly Learning & Skill Improvement (rotate through agents):
1. Pick ONE agent file from the skill's `agents/` folder (rotate weekly)
2. Read the "Learn More" section
3. Visit 2-3 links that are relevant to current projects
4. Internalize key concepts and update your workflows
5. **Improve the skill itself:**
- Found a better resource? Add it to "Learn More"
- Discovered a new best practice? Update the agent's guidelines
- Link broken or outdated? Remove or replace it
- New tool or framework worth mentioning? Add it
6. Commit changes locally with clear commit messages
7. **Don't push directly to shared repos** — propose changes as a PR or request human review first
8. Note learnings in your memory files
**Rotation schedule:**
- Week 1: senior-dev, junior-dev
- Week 2: frontend-dev, backend-dev
- Week 3: ai-engineer, ml-engineer
- Week 4: data-scientist, data-engineer
- Week 5: project-manager, product-manager
- Week 6: devops
**What to update:**
- `agents/*.md` — Add new links, update best practices, fix outdated info
- `SKILL.md` — Improve documentation, add tips discovered
- `docs/*.md` — Enhance guides based on real usageWhy this matters:
| Script | Purpose | When to use |
|--------|---------|-------------|
| 06-diagnostics.sh | Health check and status report | When issues occur |
| 07-weekly-improvement-cron.sh | Generate improvement report | Weekly (Sunday) |
| 08-troubleshoot.sh | Comprehensive troubleshooting | When 06 finds issues |
For coding tasks:
/clear and Plan modeHeartbeat handles:
The dev team subagents turn Claude Code into a full development organization.
Generated Feb 25, 2026
A small agency uses the skill to streamline client projects by delegating tasks to specialized subagents like senior-dev for architecture and junior-dev for quick fixes. It improves efficiency by isolating complex coding tasks and managing project timelines with the project-manager agent.
An e-commerce company employs the skill to handle code updates and bug fixes across frontend and backend systems. Subagents like frontend-dev and backend-dev ensure specialized attention to UI and API changes, while devops manages deployment pipelines for continuous integration.
A startup building LLM-based applications leverages the ai-engineer and ml-engineer subagents to design and optimize machine learning models. The skill facilitates rapid prototyping and troubleshooting, with context management tools like /clear to maintain focus between iterative tasks.
A consulting firm uses the skill to analyze client datasets, with data-scientist and data-engineer subagents handling SQL queries and ETL pipelines. It enables efficient data processing and report generation, supported by the project-manager agent for task breakdowns and deadlines.
Offer the skill as part of a monthly subscription for developers, providing access to subagents and updates. Revenue is generated through tiered pricing based on features like the full team of agents or advanced diagnostics.
Provide basic functionality like the starter pack subagents for free, with premium features such as the full team or persistent memory requiring a one-time purchase. This attracts users and converts them to paid plans for enhanced capabilities.
License the skill to large organizations for internal development teams, with custom configurations and support. Revenue comes from annual contracts that include setup assistance, training, and priority access to new features.
💬 Integration Tip
Integrate the skill by adding the maintenance task to HEARTBEAT.md post-setup and customize config.sh for model updates to ensure seamless operation in development workflows.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.