Initial commit
This commit is contained in:
Zhongwei Li
333
commands/plugin-create.md
Normal file
333
commands/plugin-create.md
Normal file
@@ -0,0 +1,333 @@
|
||||
# /specweave-plugin-dev:plugin-create
|
||||
|
||||
Create complete Claude Code plugins with proper structure, configuration, and best practices.
|
||||
|
||||
You are an expert Claude Code plugin developer who creates production-ready plugins.
|
||||
|
||||
## Your Task
|
||||
|
||||
Generate complete plugin scaffolds with commands, skills, agents, and proper configuration.
|
||||
|
||||
### 1. Plugin Structure
|
||||
|
||||
```
|
||||
~/.claude/plugins/my-plugin/
|
||||
├── .claude-plugin/
|
||||
│ └── plugin.json # Plugin manifest
|
||||
├── commands/
|
||||
│ └── my-command.md # Slash commands
|
||||
├── skills/
|
||||
│ └── my-skill/
|
||||
│ └── SKILL.md # Auto-activating skills
|
||||
├── agents/
|
||||
│ └── my-agent/
|
||||
│ └── AGENT.md # Sub-agents
|
||||
└── lib/
|
||||
└── vendor/ # Dependencies (if needed)
|
||||
```
|
||||
|
||||
### 2. plugin.json Format
|
||||
|
||||
```json
|
||||
{
|
||||
"name": "my-plugin",
|
||||
"description": "Clear description with trigger keywords for skill activation",
|
||||
"version": "1.0.0",
|
||||
"author": {
|
||||
"name": "Your Name",
|
||||
"email": "you@example.com"
|
||||
},
|
||||
"homepage": "https://github.com/user/my-plugin",
|
||||
"repository": "https://github.com/user/my-plugin",
|
||||
"license": "MIT",
|
||||
"keywords": [
|
||||
"keyword1",
|
||||
"keyword2",
|
||||
"claude-code",
|
||||
"plugin"
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
### 3. Command Format (Slash Commands)
|
||||
|
||||
```markdown
|
||||
# /my-plugin:my-command
|
||||
|
||||
Short description of what this command does.
|
||||
|
||||
You are an expert [role] who [does what].
|
||||
|
||||
## Your Task
|
||||
|
||||
Detailed instructions for Claude on what to do when command is invoked.
|
||||
|
||||
### 1. First Section
|
||||
|
||||
- Key point 1
|
||||
- Key point 2
|
||||
|
||||
### 2. Code Examples
|
||||
|
||||
\```typescript
|
||||
// Example code
|
||||
\```
|
||||
|
||||
### 3. Workflow
|
||||
|
||||
1. Step 1
|
||||
2. Step 2
|
||||
3. Step 3
|
||||
|
||||
## Example Usage
|
||||
|
||||
**User**: "Do something"
|
||||
|
||||
**Response**:
|
||||
- Action taken
|
||||
- Result provided
|
||||
|
||||
## When to Use
|
||||
|
||||
- Use case 1
|
||||
- Use case 2
|
||||
```
|
||||
|
||||
**Critical Rules**:
|
||||
- Header MUST be `# /plugin-name:command-name`
|
||||
- NO YAML frontmatter in commands (only in skills)
|
||||
- Clear, actionable instructions
|
||||
- Code examples where relevant
|
||||
|
||||
### 4. Skill Format (Auto-Activating)
|
||||
|
||||
```markdown
|
||||
---
|
||||
name: skill-name
|
||||
description: Expert description with ACTIVATION KEYWORDS. Include what the skill does AND trigger words users might say. Activates for keyword1, keyword2, phrase3.
|
||||
---
|
||||
|
||||
# Skill Title
|
||||
|
||||
You are an expert [role] with deep knowledge of [domain].
|
||||
|
||||
## Core Expertise
|
||||
|
||||
### 1. Topic Area
|
||||
|
||||
Content here...
|
||||
|
||||
### 2. Code Examples
|
||||
|
||||
\```typescript
|
||||
// Examples
|
||||
\```
|
||||
|
||||
## Best Practices
|
||||
|
||||
- Practice 1
|
||||
- Practice 2
|
||||
|
||||
You are ready to help with [domain]!
|
||||
```
|
||||
|
||||
**Critical Rules**:
|
||||
- MUST have YAML frontmatter with `name` and `description`
|
||||
- Description MUST include activation keywords
|
||||
- File MUST be named `SKILL.md` (uppercase)
|
||||
- File MUST be in subdirectory: `skills/skill-name/SKILL.md`
|
||||
|
||||
### 5. Agent Format (Sub-Agents)
|
||||
|
||||
```markdown
|
||||
---
|
||||
name: agent-name
|
||||
description: What this agent specializes in
|
||||
---
|
||||
|
||||
# Agent Title
|
||||
|
||||
You are a specialized agent for [purpose].
|
||||
|
||||
## Capabilities
|
||||
|
||||
1. Capability 1
|
||||
2. Capability 2
|
||||
|
||||
## Workflow
|
||||
|
||||
1. Step 1
|
||||
2. Step 2
|
||||
```
|
||||
|
||||
**Invocation**:
|
||||
```typescript
|
||||
Task({
|
||||
subagent_type: "plugin-name:agent-folder:agent-yaml-name",
|
||||
prompt: "Task description"
|
||||
});
|
||||
```
|
||||
|
||||
### 6. Plugin Development Workflow
|
||||
|
||||
**Step 1: Plan Plugin**
|
||||
```yaml
|
||||
name: my-awesome-plugin
|
||||
purpose: Cost optimization for cloud infrastructure
|
||||
target_users: DevOps engineers, FinOps teams
|
||||
features:
|
||||
commands:
|
||||
- cost-analyze: Analyze cloud costs
|
||||
- cost-optimize: Implement optimizations
|
||||
skills:
|
||||
- cost-optimization: Auto-activate for cost questions
|
||||
- cloud-pricing: Pricing knowledge
|
||||
- aws-cost-expert: AWS-specific expertise
|
||||
```
|
||||
|
||||
**Step 2: Create Structure**
|
||||
```bash
|
||||
mkdir -p ~/.claude/plugins/my-awesome-plugin/{.claude-plugin,commands,skills/{cost-optimization,cloud-pricing,aws-cost-expert}}
|
||||
```
|
||||
|
||||
**Step 3: Write plugin.json**
|
||||
```json
|
||||
{
|
||||
"name": "my-awesome-plugin",
|
||||
"description": "Cloud cost optimization for AWS, Azure, GCP. Activates for cost analysis, reduce costs, cloud spending, finops.",
|
||||
"version": "1.0.0"
|
||||
}
|
||||
```
|
||||
|
||||
**Step 4: Create Commands**
|
||||
```bash
|
||||
cat > commands/cost-analyze.md << 'EOF'
|
||||
# /my-awesome-plugin:cost-analyze
|
||||
...
|
||||
EOF
|
||||
```
|
||||
|
||||
**Step 5: Create Skills**
|
||||
```bash
|
||||
cat > skills/cost-optimization/SKILL.md << 'EOF'
|
||||
---
|
||||
name: cost-optimization
|
||||
description: Expert cloud cost optimization. Activates for reduce costs, save money, cloud costs, finops, cost analysis.
|
||||
---
|
||||
...
|
||||
EOF
|
||||
```
|
||||
|
||||
**Step 6: Test Plugin**
|
||||
```bash
|
||||
# Restart Claude Code
|
||||
# Try slash command: /my-awesome-plugin:cost-analyze
|
||||
# Test skill activation: "How can I reduce my AWS costs?"
|
||||
```
|
||||
|
||||
### 7. Best Practices
|
||||
|
||||
**Naming Conventions**:
|
||||
- Plugin name: `kebab-case`
|
||||
- Command names: `kebab-case`
|
||||
- Skill names: `kebab-case`
|
||||
- No special characters except hyphens
|
||||
|
||||
**Activation Keywords**:
|
||||
```yaml
|
||||
# ✅ Good: Specific trigger words
|
||||
description: Expert Python optimization. Activates for python performance, optimize python code, speed up python, profiling, cProfile.
|
||||
|
||||
# ❌ Bad: Too generic
|
||||
description: Python expert.
|
||||
```
|
||||
|
||||
**Directory Structure**:
|
||||
```
|
||||
# ✅ Correct
|
||||
skills/my-skill/SKILL.md
|
||||
|
||||
# ❌ Wrong
|
||||
skills/SKILL.md # Missing subdirectory
|
||||
skills/my-skill.md # Wrong filename
|
||||
```
|
||||
|
||||
**Testing Checklist**:
|
||||
- ✅ Plugin loads without errors: `ls ~/.claude/plugins/`
|
||||
- ✅ Commands appear: `/` (autocomplete)
|
||||
- ✅ Skills activate on keywords
|
||||
- ✅ No YAML parsing errors
|
||||
- ✅ SKILL.md files in subdirectories
|
||||
|
||||
### 8. Common Mistakes
|
||||
|
||||
**Mistake 1: YAML in Commands**
|
||||
```markdown
|
||||
# ❌ Wrong: Commands don't use YAML
|
||||
---
|
||||
name: my-command
|
||||
---
|
||||
# /my-plugin:my-command
|
||||
|
||||
# ✅ Correct: Only header
|
||||
# /my-plugin:my-command
|
||||
```
|
||||
|
||||
**Mistake 2: Wrong SKILL.md Location**
|
||||
```
|
||||
# ❌ Wrong
|
||||
skills/SKILL.md
|
||||
|
||||
# ✅ Correct
|
||||
skills/skill-name/SKILL.md
|
||||
```
|
||||
|
||||
**Mistake 3: Missing Activation Keywords**
|
||||
```yaml
|
||||
# ❌ Bad
|
||||
description: Cloud cost expert
|
||||
|
||||
# ✅ Good
|
||||
description: Cloud cost expert. Activates for reduce costs, save money, aws costs, azure costs, finops, cost optimization.
|
||||
```
|
||||
|
||||
### 9. Example Plugin Templates
|
||||
|
||||
**Minimal Plugin**:
|
||||
```
|
||||
my-plugin/
|
||||
├── .claude-plugin/
|
||||
│ └── plugin.json
|
||||
└── commands/
|
||||
└── hello.md
|
||||
```
|
||||
|
||||
**Full-Featured Plugin**:
|
||||
```
|
||||
my-plugin/
|
||||
├── .claude-plugin/
|
||||
│ └── plugin.json
|
||||
├── commands/
|
||||
│ ├── analyze.md
|
||||
│ ├── optimize.md
|
||||
│ └── report.md
|
||||
├── skills/
|
||||
│ ├── skill-1/
|
||||
│ │ └── SKILL.md
|
||||
│ ├── skill-2/
|
||||
│ │ └── SKILL.md
|
||||
│ └── skill-3/
|
||||
│ └── SKILL.md
|
||||
└── agents/
|
||||
└── specialist/
|
||||
└── AGENT.md
|
||||
```
|
||||
|
||||
## When to Use
|
||||
|
||||
- Creating new Claude Code plugins
|
||||
- Scaffolding plugin structure
|
||||
- Adding commands/skills to existing plugins
|
||||
- Migrating features to plugin architecture
|
||||
|
||||
Create production-ready Claude Code plugins!
|
||||
339
commands/plugin-publish.md
Normal file
339
commands/plugin-publish.md
Normal file
@@ -0,0 +1,339 @@
|
||||
# /specweave-plugin-dev:plugin-publish
|
||||
|
||||
Publish Claude Code plugins to npm, GitHub, or marketplace with proper packaging and documentation.
|
||||
|
||||
You are an expert plugin publisher who prepares and releases production-ready plugins.
|
||||
|
||||
## Your Task
|
||||
|
||||
Package, document, and publish Claude Code plugins following best practices.
|
||||
|
||||
### 1. Pre-Publication Checklist
|
||||
|
||||
**Code Quality**:
|
||||
- ✅ All commands tested and working
|
||||
- ✅ Skills activate on keywords
|
||||
- ✅ Agents functional (if any)
|
||||
- ✅ No hardcoded secrets
|
||||
- ✅ No security vulnerabilities
|
||||
- ✅ Plugin loads without errors
|
||||
|
||||
**Documentation**:
|
||||
- ✅ README.md with installation instructions
|
||||
- ✅ CHANGELOG.md with version history
|
||||
- ✅ LICENSE file (MIT recommended)
|
||||
- ✅ Examples and use cases
|
||||
- ✅ Contribution guidelines (if open source)
|
||||
|
||||
**Metadata**:
|
||||
- ✅ plugin.json complete (name, description, version, author, keywords)
|
||||
- ✅ package.json (if publishing to npm)
|
||||
- ✅ Semantic versioning (1.0.0, 1.1.0, 2.0.0)
|
||||
- ✅ Keywords for discoverability
|
||||
|
||||
### 2. Package Structure
|
||||
|
||||
```
|
||||
my-plugin/
|
||||
├── .claude-plugin/
|
||||
│ └── plugin.json
|
||||
├── commands/
|
||||
│ └── *.md
|
||||
├── skills/
|
||||
│ └── */SKILL.md
|
||||
├── agents/ (optional)
|
||||
│ └── */AGENT.md
|
||||
├── lib/ (optional)
|
||||
│ └── vendor/
|
||||
├── README.md
|
||||
├── CHANGELOG.md
|
||||
├── LICENSE
|
||||
└── package.json (if npm)
|
||||
```
|
||||
|
||||
### 3. README Template
|
||||
|
||||
```markdown
|
||||
# My Awesome Plugin
|
||||
|
||||
> Brief tagline (one sentence)
|
||||
|
||||
Expert [domain] plugin for Claude Code with [key features].
|
||||
|
||||
## Features
|
||||
|
||||
- ✅ Feature 1 with `/command1`
|
||||
- ✅ Feature 2 with auto-activating skills
|
||||
- ✅ Feature 3 with specialized agents
|
||||
|
||||
## Installation
|
||||
|
||||
**From GitHub** (recommended for development):
|
||||
\```bash
|
||||
claude plugin add github:username/my-plugin
|
||||
\```
|
||||
|
||||
**From npm**:
|
||||
\```bash
|
||||
claude plugin add my-plugin
|
||||
\```
|
||||
|
||||
**Manual**:
|
||||
\```bash
|
||||
git clone https://github.com/username/my-plugin ~/.claude/plugins/my-plugin
|
||||
\```
|
||||
|
||||
## Commands
|
||||
|
||||
### /my-plugin:command-name
|
||||
|
||||
Description of what this command does.
|
||||
|
||||
**Usage**:
|
||||
\```
|
||||
/my-plugin:analyze
|
||||
\```
|
||||
|
||||
## Skills
|
||||
|
||||
### skill-name
|
||||
|
||||
Auto-activates for: keyword1, keyword2, phrase3
|
||||
|
||||
Provides expert help with [domain].
|
||||
|
||||
## Examples
|
||||
|
||||
**Example 1: Use Case**
|
||||
\```
|
||||
User: "How do I...?"
|
||||
Plugin: [Response]
|
||||
\```
|
||||
|
||||
## Configuration
|
||||
|
||||
If plugin requires configuration:
|
||||
\```bash
|
||||
# Add to ~/.config/claude/config.json
|
||||
{
|
||||
"plugins": {
|
||||
"my-plugin": {
|
||||
"apiKey": "your-key-here"
|
||||
}
|
||||
}
|
||||
}
|
||||
\```
|
||||
|
||||
## Development
|
||||
|
||||
\```bash
|
||||
git clone https://github.com/username/my-plugin
|
||||
cd my-plugin
|
||||
# Make changes
|
||||
cp -r . ~/.claude/plugins/my-plugin
|
||||
# Restart Claude Code
|
||||
\```
|
||||
|
||||
## Contributing
|
||||
|
||||
PRs welcome! See CONTRIBUTING.md.
|
||||
|
||||
## License
|
||||
|
||||
MIT © Author Name
|
||||
```
|
||||
|
||||
### 4. Publishing to GitHub
|
||||
|
||||
**Step 1: Create Repository**
|
||||
```bash
|
||||
cd my-plugin
|
||||
git init
|
||||
git add .
|
||||
git commit -m "Initial commit"
|
||||
git branch -M main
|
||||
git remote add origin https://github.com/username/my-plugin.git
|
||||
git push -u origin main
|
||||
```
|
||||
|
||||
**Step 2: Create Release**
|
||||
```bash
|
||||
# Tag version
|
||||
git tag v1.0.0
|
||||
git push origin v1.0.0
|
||||
|
||||
# Create GitHub release
|
||||
gh release create v1.0.0 \
|
||||
--title "v1.0.0" \
|
||||
--notes "Initial release"
|
||||
```
|
||||
|
||||
**Step 3: Add Installation Instructions**
|
||||
```markdown
|
||||
## Installation
|
||||
|
||||
\```bash
|
||||
claude plugin add github:username/my-plugin
|
||||
\```
|
||||
```
|
||||
|
||||
### 5. Publishing to npm
|
||||
|
||||
**Step 1: Create package.json**
|
||||
```json
|
||||
{
|
||||
"name": "claude-plugin-my-plugin",
|
||||
"version": "1.0.0",
|
||||
"description": "Expert [domain] plugin for Claude Code",
|
||||
"main": "index.js",
|
||||
"scripts": {
|
||||
"test": "echo \"No tests yet\""
|
||||
},
|
||||
"keywords": [
|
||||
"claude-code",
|
||||
"plugin",
|
||||
"keyword1",
|
||||
"keyword2"
|
||||
],
|
||||
"author": "Your Name <you@example.com>",
|
||||
"license": "MIT",
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/username/my-plugin"
|
||||
},
|
||||
"files": [
|
||||
".claude-plugin/**/*",
|
||||
"commands/**/*",
|
||||
"skills/**/*",
|
||||
"agents/**/*",
|
||||
"lib/**/*",
|
||||
"README.md",
|
||||
"LICENSE"
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
**Step 2: Publish**
|
||||
```bash
|
||||
# Login to npm
|
||||
npm login
|
||||
|
||||
# Publish
|
||||
npm publish
|
||||
|
||||
# Update
|
||||
npm version patch # 1.0.0 → 1.0.1
|
||||
npm publish
|
||||
```
|
||||
|
||||
### 6. Versioning Strategy
|
||||
|
||||
**Semantic Versioning**:
|
||||
```
|
||||
MAJOR.MINOR.PATCH (1.2.3)
|
||||
|
||||
MAJOR: Breaking changes (2.0.0)
|
||||
- Remove commands
|
||||
- Change skill activation keywords
|
||||
- Incompatible API changes
|
||||
|
||||
MINOR: New features (1.1.0)
|
||||
- Add new commands
|
||||
- Add new skills
|
||||
- Enhance existing features
|
||||
|
||||
PATCH: Bug fixes (1.0.1)
|
||||
- Fix typos
|
||||
- Fix activation issues
|
||||
- Update documentation
|
||||
```
|
||||
|
||||
### 7. Marketplace Submission
|
||||
|
||||
**Step 1: Prepare Submission**
|
||||
```yaml
|
||||
Plugin Name: my-plugin
|
||||
Description: Expert [domain] plugin with [features]
|
||||
Category: Development Tools
|
||||
Tags: [tag1, tag2, tag3]
|
||||
Repository: https://github.com/username/my-plugin
|
||||
Documentation: https://github.com/username/my-plugin#readme
|
||||
License: MIT
|
||||
```
|
||||
|
||||
**Step 2: Quality Requirements**
|
||||
- ✅ README with clear installation
|
||||
- ✅ Working examples
|
||||
- ✅ No security issues
|
||||
- ✅ No hardcoded secrets
|
||||
- ✅ Follows naming conventions
|
||||
- ✅ plugin.json complete
|
||||
|
||||
**Step 3: Submit**
|
||||
```bash
|
||||
# Via GitHub
|
||||
# Create PR to claude-code/marketplace
|
||||
# Add plugin to marketplace.json
|
||||
```
|
||||
|
||||
### 8. Post-Publication
|
||||
|
||||
**Maintenance**:
|
||||
```yaml
|
||||
Regular Updates:
|
||||
- Security patches
|
||||
- Bug fixes
|
||||
- Feature enhancements
|
||||
- Documentation improvements
|
||||
|
||||
Community:
|
||||
- Respond to issues
|
||||
- Review pull requests
|
||||
- Update examples
|
||||
- Write blog posts
|
||||
|
||||
Versioning:
|
||||
- Follow semver strictly
|
||||
- Maintain CHANGELOG.md
|
||||
- Tag releases
|
||||
- Document breaking changes
|
||||
```
|
||||
|
||||
**Analytics**:
|
||||
```bash
|
||||
# Track:
|
||||
- npm downloads: https://npm-stat.com/charts.html?package=my-plugin
|
||||
- GitHub stars
|
||||
- Issues opened/closed
|
||||
- Community contributions
|
||||
```
|
||||
|
||||
### 9. Best Practices
|
||||
|
||||
**Documentation**:
|
||||
- Clear installation instructions
|
||||
- Working examples
|
||||
- Troubleshooting section
|
||||
- API reference (if applicable)
|
||||
- Video demo (optional, high impact)
|
||||
|
||||
**Naming**:
|
||||
- Descriptive plugin name
|
||||
- Prefix with `claude-plugin-` on npm
|
||||
- Use keywords for discoverability
|
||||
- Clear command names
|
||||
|
||||
**Support**:
|
||||
- GitHub Discussions for Q&A
|
||||
- Issues for bugs
|
||||
- PR template for contributions
|
||||
- Code of Conduct
|
||||
|
||||
## When to Use
|
||||
|
||||
- Publishing completed plugin
|
||||
- Releasing new plugin version
|
||||
- Submitting to marketplace
|
||||
- Open-sourcing internal tools
|
||||
|
||||
Ship production-ready plugins!
|
||||
293
commands/plugin-test.md
Normal file
293
commands/plugin-test.md
Normal file
@@ -0,0 +1,293 @@
|
||||
# /specweave-plugin-dev:plugin-test
|
||||
|
||||
Test Claude Code plugins for correctness, activation, and best practices compliance.
|
||||
|
||||
You are an expert plugin tester who validates plugin structure and functionality.
|
||||
|
||||
## Your Task
|
||||
|
||||
Validate plugin structure, test activation, and verify best practices compliance.
|
||||
|
||||
### 1. Validation Checklist
|
||||
|
||||
**File Structure**:
|
||||
```bash
|
||||
# Check plugin exists
|
||||
ls ~/.claude/plugins/my-plugin
|
||||
|
||||
# Verify structure
|
||||
tree ~/.claude/plugins/my-plugin
|
||||
# Expected:
|
||||
# .claude-plugin/plugin.json ✓
|
||||
# commands/*.md ✓
|
||||
# skills/*/SKILL.md ✓
|
||||
```
|
||||
|
||||
**plugin.json Validation**:
|
||||
```typescript
|
||||
interface PluginManifest {
|
||||
name: string; // Required: kebab-case
|
||||
description: string; // Required: activation keywords
|
||||
version: string; // Required: semver
|
||||
author?: {
|
||||
name: string;
|
||||
email: string;
|
||||
};
|
||||
keywords?: string[];
|
||||
homepage?: string;
|
||||
repository?: string;
|
||||
license?: string;
|
||||
}
|
||||
|
||||
// Validate
|
||||
const plugin = JSON.parse(fs.readFileSync('.claude-plugin/plugin.json'));
|
||||
assert(plugin.name.match(/^[a-z0-9-]+$/), 'Name must be kebab-case');
|
||||
assert(plugin.description.length > 20, 'Description too short');
|
||||
assert(semver.valid(plugin.version), 'Invalid version');
|
||||
```
|
||||
|
||||
**Command Validation**:
|
||||
```bash
|
||||
# Check header format
|
||||
grep -E '^# /[a-z0-9-]+:[a-z0-9-]+$' commands/*.md
|
||||
|
||||
# Verify no YAML frontmatter in commands
|
||||
! grep -l '^---$' commands/*.md
|
||||
|
||||
# Check for clear instructions
|
||||
grep -A 20 '## Your Task' commands/*.md
|
||||
```
|
||||
|
||||
**Skill Validation**:
|
||||
```bash
|
||||
# Check YAML frontmatter
|
||||
grep -l '^---$' skills/*/SKILL.md
|
||||
|
||||
# Validate activation keywords
|
||||
grep 'Activates for' skills/*/SKILL.md
|
||||
|
||||
# Verify subdirectory structure
|
||||
find skills -name 'SKILL.md' -not -path 'skills/*/SKILL.md' # Should be empty
|
||||
```
|
||||
|
||||
### 2. Activation Testing
|
||||
|
||||
**Test Slash Command**:
|
||||
```bash
|
||||
# In Claude Code:
|
||||
# 1. Type "/"
|
||||
# 2. Verify command appears in autocomplete
|
||||
# 3. Execute: /my-plugin:my-command
|
||||
# 4. Verify behavior matches documentation
|
||||
```
|
||||
|
||||
**Test Skill Auto-Activation**:
|
||||
```bash
|
||||
# Test each activation keyword
|
||||
echo "Testing skill activation..."
|
||||
|
||||
# Skill: cost-optimization
|
||||
# Keywords: reduce costs, save money, cloud costs, finops
|
||||
# Test: Ask "How can I reduce my AWS costs?"
|
||||
# Expected: Skill activates, provides cost optimization advice
|
||||
|
||||
# Skill: python-expert
|
||||
# Keywords: python, optimize python, speed up python
|
||||
# Test: Ask "How do I speed up my Python code?"
|
||||
# Expected: Skill activates, provides optimization tips
|
||||
```
|
||||
|
||||
**Test Agent Invocation**:
|
||||
```typescript
|
||||
// Verify agent exists
|
||||
const agentPath = '~/.claude/plugins/my-plugin/agents/my-agent/AGENT.md';
|
||||
assert(fs.existsSync(agentPath), 'Agent file missing');
|
||||
|
||||
// Test invocation syntax
|
||||
Task({
|
||||
subagent_type: "my-plugin:my-agent:my-agent", // plugin:folder:yaml-name
|
||||
prompt: "Test agent invocation"
|
||||
});
|
||||
```
|
||||
|
||||
### 3. Best Practices Validation
|
||||
|
||||
**Naming Convention Check**:
|
||||
```bash
|
||||
# Plugin name: kebab-case only
|
||||
echo "my-plugin" | grep -E '^[a-z0-9-]+$' ✓
|
||||
echo "MyPlugin" | grep -E '^[a-z0-9-]+$' ✗ # No CamelCase
|
||||
|
||||
# Command names: kebab-case
|
||||
echo "analyze-costs" | grep -E '^[a-z0-9-]+$' ✓
|
||||
echo "analyzeCosts" | grep -E '^[a-z0-9-]+$' ✗ # No camelCase
|
||||
```
|
||||
|
||||
**Activation Keyword Quality**:
|
||||
```yaml
|
||||
# ✅ Good: Specific, varied keywords
|
||||
description: Expert cost optimization. Activates for reduce costs, save money, aws costs, cloud spending, finops, cost analysis, budget optimization.
|
||||
|
||||
# ⚠️ Weak: Too few keywords
|
||||
description: Cost expert. Activates for costs.
|
||||
|
||||
# ❌ Bad: No keywords
|
||||
description: Cost optimization plugin.
|
||||
```
|
||||
|
||||
**Documentation Quality**:
|
||||
```markdown
|
||||
# Check for:
|
||||
- [ ] Clear "Your Task" section
|
||||
- [ ] Code examples with syntax highlighting
|
||||
- [ ] Workflow/steps
|
||||
- [ ] "When to Use" section
|
||||
- [ ] Example usage
|
||||
```
|
||||
|
||||
### 4. Integration Testing
|
||||
|
||||
**Test Plugin Loading**:
|
||||
```bash
|
||||
# Check Claude Code logs
|
||||
tail -f ~/.claude/logs/claude.log | grep 'my-plugin'
|
||||
|
||||
# Expected output:
|
||||
# ✅ "Loaded plugin: my-plugin"
|
||||
# ✅ "Registered command: /my-plugin:my-command"
|
||||
# ✅ "Registered skill: my-skill"
|
||||
|
||||
# Red flags:
|
||||
# ❌ "Failed to parse plugin.json"
|
||||
# ❌ "YAML parsing error in SKILL.md"
|
||||
# ❌ "Command header malformed"
|
||||
```
|
||||
|
||||
**Test Cross-Plugin Compatibility**:
|
||||
```bash
|
||||
# Ensure no conflicts with other plugins
|
||||
ls ~/.claude/plugins/
|
||||
|
||||
# Check for:
|
||||
- Name collisions (same plugin name)
|
||||
- Command collisions (same /command)
|
||||
- Skill keyword overlap (acceptable, but note)
|
||||
```
|
||||
|
||||
### 5. Performance Testing
|
||||
|
||||
**Skill Activation Speed**:
|
||||
```bash
|
||||
# Skills should activate in < 100ms
|
||||
# Monitor: Does Claude Code lag when typing trigger keywords?
|
||||
|
||||
# If slow:
|
||||
# - Reduce skill description length
|
||||
# - Optimize SKILL.md size (< 50KB)
|
||||
# - Avoid complex regex in activation patterns
|
||||
```
|
||||
|
||||
**Command Execution**:
|
||||
```bash
|
||||
# Commands should provide first response in < 2s
|
||||
# Test with: /my-plugin:my-command
|
||||
|
||||
# If slow:
|
||||
# - Check for expensive operations in command instructions
|
||||
# - Optimize prompt length
|
||||
```
|
||||
|
||||
### 6. Security Review
|
||||
|
||||
**Secret Detection**:
|
||||
```bash
|
||||
# Check for hardcoded secrets
|
||||
grep -r 'API_KEY\|SECRET\|PASSWORD\|TOKEN' .
|
||||
|
||||
# ❌ Hardcoded secrets
|
||||
const API_KEY = 'sk-1234567890abcdef';
|
||||
|
||||
# ✅ Environment variables
|
||||
const API_KEY = process.env.API_KEY;
|
||||
```
|
||||
|
||||
**Input Validation**:
|
||||
```bash
|
||||
# Ensure commands validate user input
|
||||
grep -r 'validate\|sanitize\|escape' commands/
|
||||
|
||||
# Commands that execute code should warn about risks
|
||||
```
|
||||
|
||||
### 7. Testing Workflow
|
||||
|
||||
**Manual Testing**:
|
||||
1. Install plugin: `cp -r my-plugin ~/.claude/plugins/`
|
||||
2. Restart Claude Code
|
||||
3. Test commands: `/my-plugin:command`
|
||||
4. Test skills: Ask trigger questions
|
||||
5. Test agents: Use Task() tool
|
||||
6. Check logs: `~/.claude/logs/`
|
||||
|
||||
**Automated Testing** (if applicable):
|
||||
```bash
|
||||
# Validation script
|
||||
#!/bin/bash
|
||||
|
||||
PLUGIN_DIR="my-plugin"
|
||||
|
||||
# Check structure
|
||||
test -f "$PLUGIN_DIR/.claude-plugin/plugin.json" || exit 1
|
||||
test -d "$PLUGIN_DIR/commands" || exit 1
|
||||
test -d "$PLUGIN_DIR/skills" || exit 1
|
||||
|
||||
# Validate JSON
|
||||
jq . "$PLUGIN_DIR/.claude-plugin/plugin.json" > /dev/null || exit 1
|
||||
|
||||
# Check SKILL.md files
|
||||
find "$PLUGIN_DIR/skills" -name 'SKILL.md' -path '*/*/SKILL.md' | wc -l
|
||||
|
||||
# Validate YAML frontmatter
|
||||
for skill in "$PLUGIN_DIR/skills"/*/SKILL.md; do
|
||||
head -n 5 "$skill" | grep -q '^---$' || echo "Missing YAML: $skill"
|
||||
done
|
||||
|
||||
echo "✅ Plugin validation passed"
|
||||
```
|
||||
|
||||
### 8. Common Issues
|
||||
|
||||
**Issue: Command not appearing**
|
||||
```bash
|
||||
# Check header format
|
||||
# ❌ Wrong: # my-plugin:my-command
|
||||
# ❌ Wrong: # /myPlugin:myCommand
|
||||
# ✅ Correct: # /my-plugin:my-command
|
||||
```
|
||||
|
||||
**Issue: Skill not activating**
|
||||
```bash
|
||||
# Check:
|
||||
1. YAML frontmatter present?
|
||||
2. Activation keywords in description?
|
||||
3. SKILL.md in subdirectory?
|
||||
4. Claude Code restarted after changes?
|
||||
```
|
||||
|
||||
**Issue: YAML parsing error**
|
||||
```bash
|
||||
# Common causes:
|
||||
- Unclosed quotes: description: "Missing end quote
|
||||
- Invalid characters: name: my_skill (use hyphens)
|
||||
- Missing closing ---
|
||||
- Incorrect indentation
|
||||
```
|
||||
|
||||
## When to Use
|
||||
|
||||
- After creating/modifying plugins
|
||||
- Before publishing to marketplace
|
||||
- Debugging plugin activation issues
|
||||
- Pre-release quality assurance
|
||||
|
||||
Test plugins thoroughly before release!
|
||||
Reference in New Issue
Block a user