thanh-kit 2.5.0

package/templates/skills/claude-code/references/troubleshooting.md

@@ -0,0 +1,456 @@
+# Troubleshooting
+
+Common issues, debugging, and solutions for Claude Code.
+
+## Authentication Issues
+
+### API Key Not Recognized
+
+**Symptoms:**
+- "Invalid API key" errors
+- Authentication failures
+- 401 Unauthorized responses
+
+**Solutions:**
+
+```bash
+# Verify API key is set
+echo $ANTHROPIC_API_KEY
+
+# Re-login
+claude logout
+claude login
+
+# Check API key format (should start with sk-ant-)
+echo $ANTHROPIC_API_KEY | grep "^sk-ant-"
+
+# Test API key directly
+curl https://api.anthropic.com/v1/messages \
+  -H "x-api-key: $ANTHROPIC_API_KEY" \
+  -H "anthropic-version: 2023-06-01" \
+  -H "content-type: application/json" \
+  -d '{"model":"claude-sonnet-4-5-20250929","max_tokens":10,"messages":[{"role":"user","content":"hi"}]}'
+```
+
+### Environment Variable Issues
+
+```bash
+# Add to shell profile
+echo 'export ANTHROPIC_API_KEY=sk-ant-xxxxx' >> ~/.bashrc
+source ~/.bashrc
+
+# Or use .env file
+echo 'ANTHROPIC_API_KEY=sk-ant-xxxxx' > .claude/.env
+
+# Verify it's loaded
+claude config get apiKey
+```
+
+## Installation Problems
+
+### npm Installation Failures
+
+```bash
+# Clear npm cache
+npm cache clean --force
+
+# Remove and reinstall
+npm uninstall -g @anthropic-ai/claude-code
+npm install -g @anthropic-ai/claude-code
+
+# Use specific version
+npm install -g @anthropic-ai/claude-code@1.0.0
+
+# Check installation
+which claude
+claude --version
+```
+
+### Permission Errors
+
+```bash
+# Fix permissions on Unix/Mac
+sudo chown -R $USER ~/.claude
+chmod -R 755 ~/.claude
+
+# Or install without sudo (using nvm)
+nvm install 18
+npm install -g @anthropic-ai/claude-code
+```
+
+### Python Installation Issues
+
+```bash
+# Upgrade pip
+pip install --upgrade pip
+
+# Install in virtual environment
+python -m venv claude-env
+source claude-env/bin/activate
+pip install claude-code
+
+# Install with --user flag
+pip install --user claude-code
+```
+
+## Connection & Network Issues
+
+### Proxy Configuration
+
+```bash
+# Set proxy environment variables
+export HTTP_PROXY=http://proxy.company.com:8080
+export HTTPS_PROXY=http://proxy.company.com:8080
+export NO_PROXY=localhost,127.0.0.1
+
+# Configure in settings
+claude config set proxy http://proxy.company.com:8080
+
+# Test connection
+curl -x $HTTP_PROXY https://api.anthropic.com
+```
+
+### SSL/TLS Errors
+
+```bash
+# Trust custom CA certificate
+export NODE_EXTRA_CA_CERTS=/path/to/ca-bundle.crt
+
+# Disable SSL verification (not recommended for production)
+export NODE_TLS_REJECT_UNAUTHORIZED=0
+
+# Update ca-certificates
+sudo update-ca-certificates  # Debian/Ubuntu
+sudo update-ca-trust         # RHEL/CentOS
+```
+
+### Firewall Issues
+
+```bash
+# Check connectivity to Anthropic API
+ping api.anthropic.com
+telnet api.anthropic.com 443
+
+# Test HTTPS connection
+curl -v https://api.anthropic.com
+
+# Check firewall rules
+sudo iptables -L  # Linux
+netsh advfirewall show allprofiles  # Windows
+```
+
+## MCP Server Problems
+
+### Server Not Starting
+
+```bash
+# Test MCP server command manually
+npx -y @modelcontextprotocol/server-filesystem /tmp
+
+# Check server logs
+cat ~/.claude/logs/mcp-*.log
+
+# Verify environment variables
+echo $GITHUB_TOKEN  # For GitHub MCP
+
+# Test with MCP Inspector
+npx @modelcontextprotocol/inspector
+```
+
+### Connection Timeouts
+
+```json
+{
+  "mcpServers": {
+    "my-server": {
+      "command": "npx",
+      "args": ["-y", "@modelcontextprotocol/server-example"],
+      "timeout": 30000,
+      "retries": 3
+    }
+  }
+}
+```
+
+### Permission Denied
+
+```bash
+# Check file permissions
+ls -la /path/to/mcp/server
+
+# Make executable
+chmod +x /path/to/mcp/server
+
+# Check directory access
+ls -ld /path/to/allowed/directory
+```
+
+## Performance Issues
+
+### Slow Responses
+
+**Check network latency:**
+```bash
+ping api.anthropic.com
+```
+
+**Use faster model:**
+```bash
+claude --model haiku "simple task"
+```
+
+**Reduce context:**
+```json
+{
+  "maxTokens": 4096,
+  "context": {
+    "autoTruncate": true
+  }
+}
+```
+
+**Enable caching:**
+```json
+{
+  "caching": {
+    "enabled": true
+  }
+}
+```
+
+### High Memory Usage
+
+```bash
+# Clear cache
+rm -rf ~/.claude/cache/*
+
+# Limit context window
+claude config set maxTokens 8192
+
+# Disable memory
+claude config set memory.enabled false
+
+# Close unused sessions
+claude session list
+claude session close session-123
+```
+
+### Rate Limiting
+
+```bash
+# Check rate limits
+claude usage show
+
+# Wait and retry
+sleep 60
+claude "retry task"
+
+# Implement exponential backoff in scripts
+```
+
+## Tool Execution Errors
+
+### Bash Command Failures
+
+**Check sandboxing settings:**
+```json
+{
+  "sandboxing": {
+    "enabled": true,
+    "allowedPaths": ["/workspace", "/tmp"]
+  }
+}
+```
+
+**Verify command permissions:**
+```bash
+# Make script executable
+chmod +x script.sh
+
+# Check PATH
+echo $PATH
+which command-name
+```
+
+### File Access Denied
+
+```bash
+# Check file permissions
+ls -la file.txt
+
+# Change ownership
+sudo chown $USER file.txt
+
+# Grant read/write permissions
+chmod 644 file.txt
+```
+
+### Write Tool Failures
+
+```bash
+# Check disk space
+df -h
+
+# Verify directory exists
+mkdir -p /path/to/directory
+
+# Check write permissions
+touch /path/to/directory/test.txt
+rm /path/to/directory/test.txt
+```
+
+## Hook Errors
+
+### Hooks Not Running
+
+```bash
+# Verify hooks.json syntax
+cat .claude/hooks.json | jq .
+
+# Check hook script permissions
+chmod +x .claude/scripts/hook.sh
+
+# Test hook script manually
+.claude/scripts/hook.sh
+
+# Check logs
+cat ~/.claude/logs/hooks.log
+```
+
+### Hook Script Errors
+
+```bash
+# Add error handling to hooks
+#!/bin/bash
+set -e  # Exit on error
+set -u  # Exit on undefined variable
+
+# Debug hook execution
+#!/bin/bash
+set -x  # Print commands
+echo "Hook running: $TOOL_NAME"
+```
+
+## Debug Mode
+
+### Enable Debugging
+
+```bash
+# Set debug environment variable
+export CLAUDE_DEBUG=1
+export CLAUDE_LOG_LEVEL=debug
+
+# Run with debug flag
+claude --debug "task"
+
+# View debug logs
+tail -f ~/.claude/logs/debug.log
+```
+
+### Verbose Output
+
+```bash
+# Enable verbose mode
+claude --verbose "task"
+
+# Show all tool calls
+claude --show-tools "task"
+
+# Display thinking process
+claude --show-thinking "task"
+```
+
+## Common Error Messages
+
+### "Model not found"
+
+```bash
+# Use correct model name
+claude --model claude-sonnet-4-5-20250929
+
+# Update claude-code
+npm update -g @anthropic-ai/claude-code
+```
+
+### "Rate limit exceeded"
+
+```bash
+# Wait and retry
+sleep 60
+
+# Check usage
+claude usage show
+
+# Implement rate limiting in code
+```
+
+### "Context length exceeded"
+
+```bash
+# Reduce context
+claude config set maxTokens 100000
+
+# Summarize long content
+claude "summarize this codebase"
+
+# Process in chunks
+claude "analyze first half of files"
+```
+
+### "Timeout waiting for response"
+
+```bash
+# Increase timeout
+claude config set timeout 300
+
+# Check network connection
+ping api.anthropic.com
+
+# Retry with smaller request
+```
+
+## Getting Help
+
+### Collect Diagnostic Info
+
+```bash
+# System info
+claude --version
+node --version
+npm --version
+
+# Configuration
+claude config list --all
+
+# Recent logs
+tail -n 100 ~/.claude/logs/session.log
+
+# Environment
+env | grep CLAUDE
+env | grep ANTHROPIC
+```
+
+### Report Issues
+
+1. **Check existing issues**: https://github.com/anthropics/claude-code/issues
+2. **Gather diagnostic info**
+3. **Create minimal reproduction**
+4. **Submit issue** with:
+   - Claude Code version
+   - Operating system
+   - Error messages
+   - Steps to reproduce
+
+### Support Channels
+
+- **Documentation**: https://docs.claude.com/claude-code
+- **GitHub Issues**: https://github.com/anthropics/claude-code/issues
+- **Support Portal**: support.claude.com
+- **Community Discord**: discord.gg/anthropic
+
+## See Also
+
+- Installation guide: `references/getting-started.md`
+- Configuration: `references/configuration.md`
+- MCP setup: `references/mcp-integration.md`
+- Best practices: `references/best-practices.md`

package/templates/skills/claude-code/skill.md

@@ -0,0 +1,60 @@
+---
+name: claude-code
+description: Activate when users ask about Claude Code installation, slash commands (/cook, /plan, /fix, /test, /docs, /design, /git), creating/managing Agent Skills, configuring MCP servers, setting up hooks/plugins, IDE integration (VS Code, JetBrains), CI/CD workflows, enterprise deployment (SSO, RBAC, sandboxing), troubleshooting authentication/performance issues, or advanced features (extended thinking, caching, checkpointing).
+---
+
+# Claude Code
+
+Anthropic's agentic coding tool combining autonomous planning, execution, and validation with extensibility through skills, plugins, MCP servers, and hooks.
+
+## Core Concepts
+
+**Subagents**: Specialized agents (planner, code-reviewer, tester, debugger, docs-manager, ui-ux-designer, database-admin)
+
+**Agent Skills**: Modular capabilities with SKILL.md + bundled resources (scripts, references, assets) loaded progressively
+
+**Slash Commands**: User-defined operations in `.claude/commands/` expanding to prompts
+
+**Hooks**: Event-driven shell commands (SessionStart, PreToolUse, PostToolUse, Stop, SubagentStop)
+
+**MCP Servers**: Model Context Protocol integrations for external tools (GitHub, Jira, databases)
+
+**Plugins**: Packaged collections distributed via marketplace
+
+## Reference Guide
+
+Load references as needed for specific topics:
+
+| Topic | Reference File | Contents |
+|-------|----------------|----------|
+| Installation & setup | `references/getting-started.md` | Prerequisites, installation methods, authentication |
+| Slash commands | `references/slash-commands.md` | Full catalog: /cook, /plan, /fix, /test, /docs, /git, /design |
+| Workflow examples | `references/common-workflows.md` | Feature implementation, bug fixing, testing, git ops |
+| Creating skills | `references/agent-skills.md` | Skill structure, metadata, bundled resources |
+| MCP servers | `references/mcp-integration.md` | Configuration, common servers, authentication |
+| Hooks system | `references/hooks-comprehensive.md` | Event types, command/prompt hooks, tool matchers |
+| Plugins | `references/hooks-and-plugins.md` | Plugin structure, marketplace, installation |
+| Configuration | `references/configuration.md` | Settings hierarchy, model config, output styles |
+| Enterprise | `references/enterprise-features.md` | SSO, RBAC, sandboxing, audit logging, deployment |
+| IDE integration | `references/ide-integration.md` | VS Code extension, JetBrains plugin |
+| CI/CD | `references/cicd-integration.md` | GitHub Actions, GitLab workflows |
+| Advanced features | `references/advanced-features.md` | Extended thinking, caching, checkpointing |
+| Troubleshooting | `references/troubleshooting.md` | Auth failures, MCP issues, performance, debug mode |
+| API reference | `references/api-reference.md` | Admin, Messages, Files, Models, Skills APIs |
+| Best practices | `references/best-practices.md` | Project organization, security, performance, cost |
+
+## Instructions
+
+When answering questions:
+
+1. Identify topic from user query
+2. Load relevant reference files (use table above)
+3. Provide specific guidance with examples
+4. For complex queries, load multiple references
+
+**Documentation sources:**
+- Context7 llms.txt: `https://context7.com/websites/claude_en_claude-code/llms.txt?tokens=10000`
+- Topic search: `https://context7.com/websites/claude_en_claude-code/llms.txt?topic=<topic>&tokens=5000`
+- Official docs: https://docs.claude.com/en/docs/claude-code/
+- GitHub: https://github.com/anthropics/claude-code
+- Support: support.claude.com

package/templates/skills/code-review/SKILL.md

@@ -0,0 +1,143 @@
+---
+name: code-review
+description: Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
+---
+
+# Code Review
+
+Guide proper code review practices emphasizing technical rigor, evidence-based claims, and verification over performative responses.
+
+## Overview
+
+Code review requires three distinct practices:
+
+1. **Receiving feedback** - Technical evaluation over performative agreement
+2. **Requesting reviews** - Systematic review via code-reviewer subagent
+3. **Verification gates** - Evidence before any completion claims
+
+Each practice has specific triggers and protocols detailed in reference files.
+
+## Core Principle
+
+Always honoring **YAGNI**, **KISS**, and **DRY** principles.
+**Be honest, be brutal, straight to the point, and be concise.**
+
+**Technical correctness over social comfort.** Verify before implementing. Ask before assuming. Evidence before claims.
+
+## When to Use This Skill
+
+### Receiving Feedback
+Trigger when:
+- Receiving code review comments from any source
+- Feedback seems unclear or technically questionable
+- Multiple review items need prioritization
+- External reviewer lacks full context
+- Suggestion conflicts with existing decisions
+
+**Reference:** `references/code-review-reception.md`
+
+### Requesting Review
+Trigger when:
+- Completing tasks in subagent-driven development (after EACH task)
+- Finishing major features or refactors
+- Before merging to main branch
+- Stuck and need fresh perspective
+- After fixing complex bugs
+
+**Reference:** `references/requesting-code-review.md`
+
+### Verification Gates
+Trigger when:
+- About to claim tests pass, build succeeds, or work is complete
+- Before committing, pushing, or creating PRs
+- Moving to next task
+- Any statement suggesting success/completion
+- Expressing satisfaction with work
+
+**Reference:** `references/verification-before-completion.md`
+
+## Quick Decision Tree
+
+```
+SITUATION?
+│
+├─ Received feedback
+│  ├─ Unclear items? → STOP, ask for clarification first
+│  ├─ From human partner? → Understand, then implement
+│  └─ From external reviewer? → Verify technically before implementing
+│
+├─ Completed work
+│  ├─ Major feature/task? → Request code-reviewer subagent review
+│  └─ Before merge? → Request code-reviewer subagent review
+│
+└─ About to claim status
+   ├─ Have fresh verification? → State claim WITH evidence
+   └─ No fresh verification? → RUN verification command first
+```
+
+## Receiving Feedback Protocol
+
+### Response Pattern
+READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT
+
+### Key Rules
+- ❌ No performative agreement: "You're absolutely right!", "Great point!", "Thanks for [anything]"
+- ❌ No implementation before verification
+- ✅ Restate requirement, ask questions, push back with technical reasoning, or just start working
+- ✅ If unclear: STOP and ask for clarification on ALL unclear items first
+- ✅ YAGNI check: grep for usage before implementing suggested "proper" features
+
+### Source Handling
+- **Human partner:** Trusted - implement after understanding, no performative agreement
+- **External reviewers:** Verify technically correct, check for breakage, push back if wrong
+
+**Full protocol:** `references/code-review-reception.md`
+
+## Requesting Review Protocol
+
+### When to Request
+- After each task in subagent-driven development
+- After major feature completion
+- Before merge to main
+
+### Process
+1. Get git SHAs: `BASE_SHA=$(git rev-parse HEAD~1)` and `HEAD_SHA=$(git rev-parse HEAD)`
+2. Dispatch code-reviewer subagent via Task tool with: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION
+3. Act on feedback: Fix Critical immediately, Important before proceeding, note Minor for later
+
+**Full protocol:** `references/requesting-code-review.md`
+
+## Verification Gates Protocol
+
+### The Iron Law
+**NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE**
+
+### Gate Function
+IDENTIFY command → RUN full command → READ output → VERIFY confirms claim → THEN claim
+
+Skip any step = lying, not verifying
+
+### Requirements
+- Tests pass: Test output shows 0 failures
+- Build succeeds: Build command exit 0
+- Bug fixed: Test original symptom passes
+- Requirements met: Line-by-line checklist verified
+
+### Red Flags - STOP
+Using "should"/"probably"/"seems to", expressing satisfaction before verification, committing without verification, trusting agent reports, ANY wording implying success without running verification
+
+**Full protocol:** `references/verification-before-completion.md`
+
+## Integration with Workflows
+
+- **Subagent-Driven:** Review after EACH task, verify before moving to next
+- **Pull Requests:** Verify tests pass, request code-reviewer review before merge
+- **General:** Apply verification gates before any status claims, push back on invalid feedback
+
+## Bottom Line
+
+1. Technical rigor over social performance - No performative agreement
+2. Systematic review processes - Use code-reviewer subagent
+3. Evidence before claims - Verification gates always
+
+Verify. Question. Then implement. Evidence. Then claim.