Initial commit
This commit is contained in:
Zhongwei Li
563
skills/engineer-skill-creator/SKILL.md
Normal file
563
skills/engineer-skill-creator/SKILL.md
Normal file
@@ -0,0 +1,563 @@
|
||||
---
|
||||
name: engineer-skill-creator
|
||||
description: Transform extracted engineer expertise into an actionable skill with progressive disclosure, allowing agents to find and apply relevant patterns for specific tasks.
|
||||
---
|
||||
|
||||
# Engineer Skill Creator
|
||||
|
||||
Transform extracted engineer profiles into ready-to-use skills with progressive disclosure, enabling AI agents to efficiently find and apply the right expertise for any coding task.
|
||||
|
||||
## What This Skill Does
|
||||
|
||||
Takes the output from **engineer-expertise-extractor** and creates a structured, queryable skill that:
|
||||
- **Organizes expertise by task type** - Find relevant patterns quickly
|
||||
- **Uses progressive disclosure** - Show only what's needed for current task
|
||||
- **Provides contextual examples** - Real code samples for specific scenarios
|
||||
- **Guides agents intelligently** - Help find the right expertise at the right time
|
||||
- **Enables task-specific queries** - "How would they handle authentication?"
|
||||
|
||||
## The Two-Step Process
|
||||
|
||||
### Step 1: Extract (engineer-expertise-extractor)
|
||||
```bash
|
||||
./extract_engineer.sh senior_dev
|
||||
# Output: engineer_profiles/senior_dev/
|
||||
```
|
||||
|
||||
### Step 2: Create Skill (THIS SKILL)
|
||||
```bash
|
||||
./create_expert_skill.sh senior_dev
|
||||
# Output: expert-skills/senior-dev-mentor/
|
||||
```
|
||||
|
||||
**Result:** A ready-to-use skill that agents can query for specific guidance.
|
||||
|
||||
## Why Progressive Disclosure Matters
|
||||
|
||||
**Without progressive disclosure:**
|
||||
- Agent gets all expertise at once (overwhelming)
|
||||
- Hard to find relevant information
|
||||
- Context limits reached quickly
|
||||
- Inefficient and slow
|
||||
|
||||
**With progressive disclosure:**
|
||||
- Agent asks specific question
|
||||
- Gets only relevant expertise
|
||||
- Focused, actionable guidance
|
||||
- Efficient use of context
|
||||
- Faster, better results
|
||||
|
||||
## Output Structure
|
||||
|
||||
When you create a skill from an engineer profile, you get:
|
||||
|
||||
```
|
||||
expert-skills/
|
||||
└── [engineer-name]-mentor/
|
||||
├── SKILL.md (skill documentation)
|
||||
├── query_expertise.sh (interactive query tool)
|
||||
├── expertise/
|
||||
│ ├── by_task/
|
||||
│ │ ├── authentication.md
|
||||
│ │ ├── api_design.md
|
||||
│ │ ├── database_design.md
|
||||
│ │ ├── error_handling.md
|
||||
│ │ └── testing.md
|
||||
│ ├── by_language/
|
||||
│ │ ├── typescript.md
|
||||
│ │ ├── python.md
|
||||
│ │ └── go.md
|
||||
│ ├── by_pattern/
|
||||
│ │ ├── dependency_injection.md
|
||||
│ │ ├── repository_pattern.md
|
||||
│ │ └── factory_pattern.md
|
||||
│ └── quick_reference/
|
||||
│ ├── coding_style.md
|
||||
│ ├── naming_conventions.md
|
||||
│ └── best_practices.md
|
||||
└── examples/
|
||||
├── authentication_service.ts
|
||||
├── api_controller.ts
|
||||
└── test_example.spec.ts
|
||||
```
|
||||
|
||||
## Progressive Disclosure System
|
||||
|
||||
### Query by Task
|
||||
|
||||
**Agent asks:** "How would they implement user authentication?"
|
||||
|
||||
**Skill provides:**
|
||||
1. Relevant patterns from `by_task/authentication.md`
|
||||
2. Code examples from their auth PRs
|
||||
3. Their testing approach for auth
|
||||
4. Security considerations they use
|
||||
5. Related best practices
|
||||
|
||||
**NOT provided (yet):**
|
||||
- Unrelated patterns
|
||||
- Database design details
|
||||
- Payment processing approach
|
||||
- Everything else
|
||||
|
||||
### Query by Language
|
||||
|
||||
**Agent asks:** "Show me their TypeScript coding style"
|
||||
|
||||
**Skill provides:**
|
||||
1. TypeScript-specific conventions
|
||||
2. Type usage patterns
|
||||
3. Interface design approach
|
||||
4. Error handling in TS
|
||||
5. Real TS examples
|
||||
|
||||
### Query by Pattern
|
||||
|
||||
**Agent asks:** "How do they implement dependency injection?"
|
||||
|
||||
**Skill provides:**
|
||||
1. DI pattern from their code
|
||||
2. Constructor injection examples
|
||||
3. IoC container setup
|
||||
4. Testing with DI
|
||||
5. When they use it vs when they don't
|
||||
|
||||
## Skill Usage by Agents
|
||||
|
||||
### Basic Query
|
||||
```
|
||||
"Using the skill expert-skills/senior-dev-mentor/, show me how to
|
||||
implement authentication"
|
||||
```
|
||||
|
||||
**Skill responds with:**
|
||||
- Authentication patterns they use
|
||||
- Real code examples
|
||||
- Testing approach
|
||||
- Security practices
|
||||
- Step-by-step guidance
|
||||
|
||||
### Language-Specific Query
|
||||
```
|
||||
"Using expert-skills/senior-dev-mentor/, write a TypeScript service
|
||||
following their style"
|
||||
```
|
||||
|
||||
**Skill provides:**
|
||||
- TypeScript coding conventions
|
||||
- Class structure patterns
|
||||
- Type definitions approach
|
||||
- Import organization
|
||||
- Testing patterns for services
|
||||
|
||||
### Pattern-Specific Query
|
||||
```
|
||||
"Using expert-skills/senior-dev-mentor/, implement the repository
|
||||
pattern as they would"
|
||||
```
|
||||
|
||||
**Skill provides:**
|
||||
- Their repository pattern implementation
|
||||
- Interface definitions
|
||||
- Concrete implementation example
|
||||
- Testing approach
|
||||
- When to use this pattern
|
||||
|
||||
## Created Skill Features
|
||||
|
||||
### 1. Task-Based Navigation
|
||||
Expertise organized by common development tasks:
|
||||
- Authentication & Authorization
|
||||
- API Design
|
||||
- Database Design
|
||||
- Error Handling
|
||||
- Testing Strategies
|
||||
- Performance Optimization
|
||||
- Security Practices
|
||||
- Code Review Guidelines
|
||||
|
||||
### 2. Language-Specific Guidance
|
||||
Separate docs for each language they use:
|
||||
- Naming conventions per language
|
||||
- Language-specific patterns
|
||||
- Idiomatic code examples
|
||||
- Framework preferences
|
||||
|
||||
### 3. Pattern Library
|
||||
Design patterns they commonly use:
|
||||
- When to apply each pattern
|
||||
- Implementation examples
|
||||
- Testing approach
|
||||
- Common pitfalls to avoid
|
||||
|
||||
### 4. Quick Reference
|
||||
Fast access to essentials:
|
||||
- Coding style at a glance
|
||||
- Naming conventions cheat sheet
|
||||
- Common commands/snippets
|
||||
- Review checklist
|
||||
|
||||
### 5. Interactive Query Tool
|
||||
Script that helps find expertise:
|
||||
```bash
|
||||
./query_expertise.sh
|
||||
|
||||
What are you working on?
|
||||
1) Authentication
|
||||
2) API Design
|
||||
3) Database
|
||||
4) Testing
|
||||
5) Custom query
|
||||
|
||||
Select: 1
|
||||
|
||||
=== Authentication Expertise ===
|
||||
|
||||
[Shows relevant patterns, examples, best practices]
|
||||
```
|
||||
|
||||
## How Skills Are Created
|
||||
|
||||
### Input
|
||||
Engineer profile from extractor:
|
||||
```
|
||||
engineer_profiles/senior_dev/
|
||||
├── coding_style/
|
||||
├── patterns/
|
||||
├── best_practices/
|
||||
├── architecture/
|
||||
├── code_review/
|
||||
└── examples/
|
||||
```
|
||||
|
||||
### Process
|
||||
1. **Analyze profile structure**
|
||||
2. **Categorize by task** - Group related expertise
|
||||
3. **Extract examples** - Pull relevant code samples
|
||||
4. **Create navigation** - Build progressive disclosure system
|
||||
5. **Generate queries** - Create query tool
|
||||
6. **Package skill** - Ready-to-use skill structure
|
||||
|
||||
### Output
|
||||
Skill with progressive disclosure:
|
||||
```
|
||||
expert-skills/senior-dev-mentor/
|
||||
├── SKILL.md
|
||||
├── query_expertise.sh
|
||||
├── expertise/
|
||||
│ ├── by_task/
|
||||
│ ├── by_language/
|
||||
│ ├── by_pattern/
|
||||
│ └── quick_reference/
|
||||
└── examples/
|
||||
```
|
||||
|
||||
## Example Created Skill
|
||||
|
||||
### Authentication Task Doc
|
||||
|
||||
**File:** `expertise/by_task/authentication.md`
|
||||
|
||||
```markdown
|
||||
# Authentication - Senior Dev's Approach
|
||||
|
||||
## Overview
|
||||
How senior_dev implements authentication based on 15 PRs analyzed.
|
||||
|
||||
## Preferred Approach
|
||||
- JWT-based authentication
|
||||
- Refresh token rotation
|
||||
- HttpOnly cookies for web
|
||||
- Token in headers for mobile/API
|
||||
|
||||
## Implementation Pattern
|
||||
|
||||
### Service Structure
|
||||
[Code example from their PR #1234]
|
||||
|
||||
### Token Generation
|
||||
[Code example from their PR #5678]
|
||||
|
||||
### Token Validation
|
||||
[Code example from their PR #9012]
|
||||
|
||||
## Testing Approach
|
||||
- Unit tests for token generation
|
||||
- Integration tests for auth flow
|
||||
- Security tests for token validation
|
||||
|
||||
[Test examples from their code]
|
||||
|
||||
## Security Considerations
|
||||
From their code reviews:
|
||||
- Always validate token signature
|
||||
- Check expiration
|
||||
- Implement rate limiting
|
||||
- Use secure random for secrets
|
||||
|
||||
## Common Pitfalls They Avoid
|
||||
- Storing tokens in localStorage (XSS risk)
|
||||
- Not rotating refresh tokens
|
||||
- Weak secret keys
|
||||
- Missing token expiration
|
||||
|
||||
## Related Patterns
|
||||
- Error handling for auth failures
|
||||
- Middleware pattern for auth checks
|
||||
- Repository pattern for user lookup
|
||||
|
||||
## Examples
|
||||
See: examples/authentication_service.ts
|
||||
```
|
||||
|
||||
## Use Cases
|
||||
|
||||
### 1. Consistent Code Generation
|
||||
|
||||
**Problem:** AI generates code that doesn't match team style
|
||||
|
||||
**Solution:**
|
||||
```
|
||||
"Using expert-skills/senior-dev-mentor/, write a user service"
|
||||
```
|
||||
|
||||
**Result:** Code matching senior dev's exact style and patterns
|
||||
|
||||
### 2. Task-Specific Guidance
|
||||
|
||||
**Problem:** How would senior dev approach this specific problem?
|
||||
|
||||
**Solution:**
|
||||
```
|
||||
"Using expert-skills/tech-lead-mentor/, how do I handle rate limiting?"
|
||||
```
|
||||
|
||||
**Result:** Their specific approach, examples, and reasoning
|
||||
|
||||
### 3. Code Review Training
|
||||
|
||||
**Problem:** Learn what experienced engineer looks for
|
||||
|
||||
**Solution:**
|
||||
```
|
||||
"Using expert-skills/architect-mentor/, review this code"
|
||||
```
|
||||
|
||||
**Result:** Review following their standards and priorities
|
||||
|
||||
### 4. Onboarding
|
||||
|
||||
**Problem:** New engineer needs to learn team conventions
|
||||
|
||||
**Solution:** Give them access to expert-skills
|
||||
|
||||
**Result:** Learn from real examples, specific to their tasks
|
||||
|
||||
## Skill Query Examples
|
||||
|
||||
### Example 1: Authentication
|
||||
```bash
|
||||
./query_expertise.sh
|
||||
> Working on: Authentication
|
||||
> Language: TypeScript
|
||||
|
||||
Output:
|
||||
=== Authentication in TypeScript ===
|
||||
|
||||
Preferred approach: JWT with refresh tokens
|
||||
|
||||
[Shows specific auth pattern]
|
||||
[Provides TS code example]
|
||||
[Testing strategy]
|
||||
[Security checklist]
|
||||
|
||||
Related: error_handling.md, api_design.md
|
||||
```
|
||||
|
||||
### Example 2: Database Design
|
||||
```bash
|
||||
./query_expertise.sh
|
||||
> Working on: Database design
|
||||
> Database: PostgreSQL
|
||||
|
||||
Output:
|
||||
=== Database Design - PostgreSQL ===
|
||||
|
||||
Schema design approach:
|
||||
- Normalized tables
|
||||
- Foreign keys enforced
|
||||
- Indexes on lookups
|
||||
- Migrations for changes
|
||||
|
||||
[Shows migration example]
|
||||
[Query optimization patterns]
|
||||
[Testing approach]
|
||||
```
|
||||
|
||||
### Example 3: Error Handling
|
||||
```bash
|
||||
./query_expertise.sh
|
||||
> Working on: Error handling
|
||||
> Language: Python
|
||||
|
||||
Output:
|
||||
=== Error Handling in Python ===
|
||||
|
||||
Pattern: Custom exception classes + global handler
|
||||
|
||||
[Shows exception hierarchy]
|
||||
[Handler implementation]
|
||||
[Logging approach]
|
||||
[User-facing messages]
|
||||
```
|
||||
|
||||
## Creating a Skill
|
||||
|
||||
### Basic Usage
|
||||
```bash
|
||||
cd engineer-skill-creator
|
||||
./scripts/create_expert_skill.sh [engineer-username]
|
||||
```
|
||||
|
||||
### Advanced Usage
|
||||
```bash
|
||||
./scripts/create_expert_skill.sh [engineer-username] --focus api,testing
|
||||
```
|
||||
|
||||
Limits skill to specific focus areas.
|
||||
|
||||
### What Gets Generated
|
||||
|
||||
**Automatic categorization:**
|
||||
- Groups related patterns
|
||||
- Organizes by common tasks
|
||||
- Separates by language
|
||||
- Highlights best practices
|
||||
|
||||
**Query system:**
|
||||
- Interactive CLI tool
|
||||
- Smart search
|
||||
- Related content linking
|
||||
- Example suggestions
|
||||
|
||||
**Documentation:**
|
||||
- Task-specific guides
|
||||
- Language references
|
||||
- Pattern library
|
||||
- Quick reference cards
|
||||
|
||||
## Integration with Development Workflow
|
||||
|
||||
### In Claude Code
|
||||
```
|
||||
"Load the expert-skills/senior-dev-mentor/ skill and help me
|
||||
implement this feature following their approach"
|
||||
```
|
||||
|
||||
### In Code Review
|
||||
```
|
||||
"Using expert-skills/tech-lead-mentor/, review this PR for:
|
||||
- Code style compliance
|
||||
- Pattern usage
|
||||
- Best practices
|
||||
- Security considerations"
|
||||
```
|
||||
|
||||
### In Architecture Decisions
|
||||
```
|
||||
"Using expert-skills/architect-mentor/, how would they design
|
||||
this microservice?"
|
||||
```
|
||||
|
||||
## Skill Maintenance
|
||||
|
||||
### Updating Skills
|
||||
When engineer profile is updated:
|
||||
```bash
|
||||
./scripts/update_expert_skill.sh senior-dev
|
||||
```
|
||||
|
||||
Re-generates skill with new expertise.
|
||||
|
||||
### Version Control
|
||||
Each skill generation includes:
|
||||
- Source profile version
|
||||
- Generation date
|
||||
- Expertise count
|
||||
- Last PR analyzed
|
||||
|
||||
## Best Practices
|
||||
|
||||
### When Creating Skills
|
||||
|
||||
**DO:**
|
||||
- ✅ Create skills for different expertise areas
|
||||
- ✅ Update skills regularly (quarterly)
|
||||
- ✅ Test queries before deploying
|
||||
- ✅ Document what the skill covers
|
||||
|
||||
**DON'T:**
|
||||
- ❌ Create skills from insufficient data (< 20 PRs)
|
||||
- ❌ Mix multiple engineers in one skill
|
||||
- ❌ Ignore profile updates
|
||||
- ❌ Over-categorize (keep it simple)
|
||||
|
||||
### When Using Skills
|
||||
|
||||
**DO:**
|
||||
- ✅ Ask specific questions
|
||||
- ✅ Provide context (language, task)
|
||||
- ✅ Reference examples
|
||||
- ✅ Combine with your judgment
|
||||
|
||||
**DON'T:**
|
||||
- ❌ Blindly copy patterns
|
||||
- ❌ Skip understanding reasoning
|
||||
- ❌ Ignore project context
|
||||
- ❌ Treat as inflexible rules
|
||||
|
||||
## Limitations
|
||||
|
||||
**What Skills Can Do:**
|
||||
- ✅ Provide proven patterns
|
||||
- ✅ Show real examples
|
||||
- ✅ Guide implementation
|
||||
- ✅ Explain reasoning
|
||||
- ✅ Surface best practices
|
||||
|
||||
**What Skills Cannot Do:**
|
||||
- ❌ Make decisions for you
|
||||
- ❌ Understand your specific context
|
||||
- ❌ Replace senior engineer judgment
|
||||
- ❌ Guarantee correctness
|
||||
- ❌ Adapt to new technologies automatically
|
||||
|
||||
## Summary
|
||||
|
||||
The Engineer Skill Creator transforms extracted expertise into actionable, queryable skills:
|
||||
|
||||
**Input:** Engineer profile (from extractor)
|
||||
**Process:** Categorize, organize, create query system
|
||||
**Output:** Progressive disclosure skill
|
||||
|
||||
**Benefits:**
|
||||
- Find expertise fast
|
||||
- Get task-specific guidance
|
||||
- Learn from real examples
|
||||
- Maintain consistency
|
||||
- Scale knowledge
|
||||
|
||||
**Use with agents:**
|
||||
```
|
||||
"Using expert-skills/[engineer]-mentor/, [task description]"
|
||||
```
|
||||
|
||||
**The complete workflow:**
|
||||
1. Extract expertise: `extract_engineer.sh username`
|
||||
2. Create skill: `create_expert_skill.sh username`
|
||||
3. Use with agents: Reference skill in prompts
|
||||
4. Get consistent, expert-level results
|
||||
|
||||
---
|
||||
|
||||
**"Progressive disclosure: Show only what's needed, when it's needed."**
|
||||
579
skills/engineer-skill-creator/scripts/create_expert_skill.sh
Executable file
579
skills/engineer-skill-creator/scripts/create_expert_skill.sh
Executable file
@@ -0,0 +1,579 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Engineer Skill Creator
|
||||
# Transform extracted engineer expertise into progressive disclosure skill
|
||||
|
||||
set -e
|
||||
|
||||
# Colors
|
||||
GREEN='\033[0;32m'
|
||||
BLUE='\033[0;34m'
|
||||
YELLOW='\033[1;33m'
|
||||
RED='\033[0;31m'
|
||||
MAGENTA='\033[0;35m'
|
||||
CYAN='\033[0;36m'
|
||||
NC='\033[0m'
|
||||
|
||||
echo -e "${BLUE}╔══════════════════════════════════════════════════╗${NC}"
|
||||
echo -e "${BLUE}║ Engineer Skill Creator ║${NC}"
|
||||
echo -e "${BLUE}╚══════════════════════════════════════════════════╝${NC}"
|
||||
echo ""
|
||||
echo -e "${YELLOW}Transform engineer expertise into actionable skill${NC}"
|
||||
echo ""
|
||||
|
||||
# Helper function
|
||||
prompt_input() {
|
||||
local prompt_text="$1"
|
||||
local var_name="$2"
|
||||
local required="$3"
|
||||
|
||||
while true; do
|
||||
echo -e "${CYAN}${prompt_text}${NC}"
|
||||
read -r input
|
||||
|
||||
if [ -n "$input" ]; then
|
||||
eval "$var_name=\"$input\""
|
||||
break
|
||||
elif [ "$required" != "true" ]; then
|
||||
eval "$var_name=\"\""
|
||||
break
|
||||
else
|
||||
echo -e "${RED}This field is required.${NC}"
|
||||
fi
|
||||
done
|
||||
}
|
||||
|
||||
# Check for profile directory
|
||||
PROFILES_DIR="engineer_profiles"
|
||||
|
||||
if [ ! -d "$PROFILES_DIR" ]; then
|
||||
echo -e "${RED}Error: engineer_profiles/ directory not found${NC}"
|
||||
echo "Run engineer-expertise-extractor first to create profiles"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Step 1: Select Engineer Profile
|
||||
echo -e "${MAGENTA}━━━ Step 1: Select Engineer Profile ━━━${NC}"
|
||||
echo ""
|
||||
|
||||
echo "Available engineer profiles:"
|
||||
ls -1 "$PROFILES_DIR" 2>/dev/null | nl || echo "No profiles found"
|
||||
echo ""
|
||||
|
||||
if [ -n "$1" ]; then
|
||||
ENGINEER_USERNAME="$1"
|
||||
else
|
||||
prompt_input "Engineer username:" ENGINEER_USERNAME true
|
||||
fi
|
||||
|
||||
PROFILE_DIR="$PROFILES_DIR/$ENGINEER_USERNAME"
|
||||
|
||||
if [ ! -d "$PROFILE_DIR" ]; then
|
||||
echo -e "${RED}Error: Profile not found: $PROFILE_DIR${NC}"
|
||||
echo "Available profiles:"
|
||||
ls -1 "$PROFILES_DIR"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo -e "${GREEN}✓ Found profile: $ENGINEER_USERNAME${NC}"
|
||||
|
||||
# Read engineer name from profile README
|
||||
if [ -f "$PROFILE_DIR/README.md" ]; then
|
||||
ENGINEER_NAME=$(grep "^**Name:**" "$PROFILE_DIR/README.md" | cut -d: -f2 | xargs || echo "$ENGINEER_USERNAME")
|
||||
else
|
||||
ENGINEER_NAME="$ENGINEER_USERNAME"
|
||||
fi
|
||||
|
||||
echo " Name: $ENGINEER_NAME"
|
||||
echo ""
|
||||
|
||||
# Step 2: Skill Configuration
|
||||
echo -e "${MAGENTA}━━━ Step 2: Skill Configuration ━━━${NC}"
|
||||
echo ""
|
||||
|
||||
# Skill name (sanitized)
|
||||
SKILL_NAME="${ENGINEER_USERNAME}-mentor"
|
||||
SKILL_NAME=$(echo "$SKILL_NAME" | tr '[:upper:]' '[:lower:]' | tr '_' '-')
|
||||
|
||||
prompt_input "Skill name [$SKILL_NAME]:" CUSTOM_SKILL_NAME false
|
||||
SKILL_NAME="${CUSTOM_SKILL_NAME:-$SKILL_NAME}"
|
||||
|
||||
echo ""
|
||||
echo "Focus areas (leave empty for all):"
|
||||
prompt_input "Specific areas to include (e.g., 'api,testing,auth'):" FOCUS_AREAS false
|
||||
|
||||
# Create output directory
|
||||
OUTPUT_DIR="expert-skills/$SKILL_NAME"
|
||||
mkdir -p "$OUTPUT_DIR"
|
||||
mkdir -p "$OUTPUT_DIR/expertise/by_task"
|
||||
mkdir -p "$OUTPUT_DIR/expertise/by_language"
|
||||
mkdir -p "$OUTPUT_DIR/expertise/by_pattern"
|
||||
mkdir -p "$OUTPUT_DIR/expertise/quick_reference"
|
||||
mkdir -p "$OUTPUT_DIR/examples"
|
||||
|
||||
echo ""
|
||||
echo -e "${BLUE}━━━ Creating Skill ━━━${NC}"
|
||||
echo ""
|
||||
|
||||
# Step 3: Create Skill README
|
||||
echo -e "${YELLOW}Generating skill documentation...${NC}"
|
||||
|
||||
cat > "$OUTPUT_DIR/SKILL.md" << EOF
|
||||
---
|
||||
name: $SKILL_NAME
|
||||
description: Expert guidance from $ENGINEER_NAME's coding expertise. Progressive disclosure for task-specific patterns, best practices, and real code examples.
|
||||
---
|
||||
|
||||
# $ENGINEER_NAME - Expert Mentor Skill
|
||||
|
||||
Learn from $ENGINEER_NAME's proven patterns and best practices. This skill provides progressive disclosure of their expertise, showing only what's relevant for your current task.
|
||||
|
||||
## How to Use This Skill
|
||||
|
||||
### Quick Query
|
||||
\`\`\`
|
||||
"Using this skill, how do I implement [feature]?"
|
||||
\`\`\`
|
||||
|
||||
### Task-Specific
|
||||
\`\`\`
|
||||
"Using this skill, show me authentication patterns"
|
||||
"Using this skill, TypeScript coding style"
|
||||
"Using this skill, repository pattern implementation"
|
||||
\`\`\`
|
||||
|
||||
### Code Generation
|
||||
\`\`\`
|
||||
"Using this skill, write a service following their style"
|
||||
"Using this skill, review this code using their standards"
|
||||
\`\`\`
|
||||
|
||||
## Expertise Areas
|
||||
|
||||
Based on analysis of $ENGINEER_NAME's GitHub contributions:
|
||||
|
||||
EOF
|
||||
|
||||
# List expertise areas from profile
|
||||
if [ -d "$PROFILE_DIR/patterns" ]; then
|
||||
echo "### Patterns" >> "$OUTPUT_DIR/SKILL.md"
|
||||
find "$PROFILE_DIR/patterns" -name "*.md" -type f | while read -r file; do
|
||||
basename "$file" .md | sed 's/_/ /g' | sed 's/^/- /' >> "$OUTPUT_DIR/SKILL.md"
|
||||
done
|
||||
echo "" >> "$OUTPUT_DIR/SKILL.md"
|
||||
fi
|
||||
|
||||
if [ -d "$PROFILE_DIR/best_practices" ]; then
|
||||
echo "### Best Practices" >> "$OUTPUT_DIR/SKILL.md"
|
||||
find "$PROFILE_DIR/best_practices" -name "*.md" -type f | while read -r file; do
|
||||
basename "$file" .md | sed 's/_/ /g' | sed 's/^/- /' >> "$OUTPUT_DIR/SKILL.md"
|
||||
done
|
||||
echo "" >> "$OUTPUT_DIR/SKILL.md"
|
||||
fi
|
||||
|
||||
cat >> "$OUTPUT_DIR/SKILL.md" << EOF
|
||||
|
||||
## Structure
|
||||
|
||||
This skill uses **progressive disclosure** - you get only what's needed:
|
||||
|
||||
\`\`\`
|
||||
expertise/
|
||||
├── by_task/ # Query by what you're building
|
||||
│ ├── authentication.md
|
||||
│ ├── api_design.md
|
||||
│ ├── database_design.md
|
||||
│ └── testing.md
|
||||
├── by_language/ # Query by language
|
||||
│ ├── typescript.md
|
||||
│ ├── python.md
|
||||
│ └── [others].md
|
||||
├── by_pattern/ # Query by design pattern
|
||||
│ ├── dependency_injection.md
|
||||
│ ├── repository_pattern.md
|
||||
│ └── [others].md
|
||||
└── quick_reference/ # Quick lookups
|
||||
├── coding_style.md
|
||||
├── naming_conventions.md
|
||||
└── best_practices.md
|
||||
\`\`\`
|
||||
|
||||
## Interactive Query
|
||||
|
||||
Use the query tool for guided navigation:
|
||||
|
||||
\`\`\`bash
|
||||
./query_expertise.sh
|
||||
\`\`\`
|
||||
|
||||
## Examples
|
||||
|
||||
Real code examples from their work:
|
||||
|
||||
\`\`\`
|
||||
examples/
|
||||
├── [language]_examples/
|
||||
└── [pattern]_examples/
|
||||
\`\`\`
|
||||
|
||||
## Quick Reference
|
||||
|
||||
For fast lookups:
|
||||
- **Coding Style:** expertise/quick_reference/coding_style.md
|
||||
- **Naming:** expertise/quick_reference/naming_conventions.md
|
||||
- **Best Practices:** expertise/quick_reference/best_practices.md
|
||||
|
||||
## Source
|
||||
|
||||
Expertise extracted from: \`engineer_profiles/$ENGINEER_USERNAME/\`
|
||||
|
||||
Generated: $(date +%Y-%m-%d)
|
||||
|
||||
---
|
||||
|
||||
**Use this skill to code like $ENGINEER_NAME - progressive, focused, and effective.**
|
||||
EOF
|
||||
|
||||
echo -e "${GREEN}✓ Skill documentation created${NC}"
|
||||
|
||||
# Step 4: Organize by Task
|
||||
echo -e "${YELLOW}Organizing expertise by task...${NC}"
|
||||
|
||||
# Create task-based docs
|
||||
cat > "$OUTPUT_DIR/expertise/by_task/authentication.md" << 'EOF'
|
||||
# Authentication & Authorization
|
||||
|
||||
## Overview
|
||||
Authentication and authorization patterns from analyzed code.
|
||||
|
||||
## Preferred Approach
|
||||
[Extract from profile's architecture/ and patterns/ folders]
|
||||
|
||||
## Implementation
|
||||
[Code examples from examples/ folder]
|
||||
|
||||
## Testing Strategy
|
||||
[From best_practices/testing_approach.md]
|
||||
|
||||
## Security Considerations
|
||||
[From best_practices/security.md]
|
||||
|
||||
## Examples
|
||||
See: ../../examples/
|
||||
|
||||
---
|
||||
**Note:** Populate with specific patterns from engineer profile
|
||||
EOF
|
||||
|
||||
cat > "$OUTPUT_DIR/expertise/by_task/api_design.md" << 'EOF'
|
||||
# API Design
|
||||
|
||||
## Overview
|
||||
API design patterns and conventions.
|
||||
|
||||
## REST API Design
|
||||
[Extract from architecture/ and patterns/]
|
||||
|
||||
## Error Handling
|
||||
[From patterns/error_handling.md]
|
||||
|
||||
## Validation
|
||||
[Input validation patterns]
|
||||
|
||||
## Documentation
|
||||
[API documentation approach]
|
||||
|
||||
## Examples
|
||||
See: ../../examples/
|
||||
|
||||
---
|
||||
**Note:** Populate with specific patterns from engineer profile
|
||||
EOF
|
||||
|
||||
cat > "$OUTPUT_DIR/expertise/by_task/testing.md" << 'EOF'
|
||||
# Testing Approach
|
||||
|
||||
## Overview
|
||||
Testing strategies and patterns.
|
||||
|
||||
## Test Structure
|
||||
[From best_practices/testing_approach.md]
|
||||
|
||||
## Unit Testing
|
||||
[Unit test patterns]
|
||||
|
||||
## Integration Testing
|
||||
[Integration test patterns]
|
||||
|
||||
## Test Coverage
|
||||
[Coverage standards]
|
||||
|
||||
## Examples
|
||||
See: ../../examples/
|
||||
|
||||
---
|
||||
**Note:** Populate with specific patterns from engineer profile
|
||||
EOF
|
||||
|
||||
echo -e "${GREEN}✓ Task-based organization created${NC}"
|
||||
|
||||
# Step 5: Create Quick Reference
|
||||
echo -e "${YELLOW}Creating quick reference guides...${NC}"
|
||||
|
||||
# Copy coding style if available
|
||||
if [ -f "$PROFILE_DIR/coding_style/naming_conventions.md" ]; then
|
||||
cp "$PROFILE_DIR/coding_style/naming_conventions.md" "$OUTPUT_DIR/expertise/quick_reference/"
|
||||
fi
|
||||
|
||||
if [ -f "$PROFILE_DIR/coding_style/code_structure.md" ]; then
|
||||
cp "$PROFILE_DIR/coding_style/code_structure.md" "$OUTPUT_DIR/expertise/quick_reference/"
|
||||
fi
|
||||
|
||||
# Create coding style summary
|
||||
cat > "$OUTPUT_DIR/expertise/quick_reference/coding_style.md" << EOF
|
||||
# Coding Style - Quick Reference
|
||||
|
||||
## Overview
|
||||
Fast reference for $ENGINEER_NAME's coding conventions.
|
||||
|
||||
## Naming Conventions
|
||||
|
||||
$([ -f "$PROFILE_DIR/coding_style/naming_conventions.md" ] && cat "$PROFILE_DIR/coding_style/naming_conventions.md" || echo "See full profile for details")
|
||||
|
||||
## Code Structure
|
||||
|
||||
$([ -f "$PROFILE_DIR/coding_style/code_structure.md" ] && cat "$PROFILE_DIR/coding_style/code_structure.md" || echo "See full profile for details")
|
||||
|
||||
## Source
|
||||
Full details: \`engineer_profiles/$ENGINEER_USERNAME/coding_style/\`
|
||||
|
||||
---
|
||||
Generated: $(date +%Y-%m-%d)
|
||||
EOF
|
||||
|
||||
echo -e "${GREEN}✓ Quick reference created${NC}"
|
||||
|
||||
# Step 6: Create Query Tool
|
||||
echo -e "${YELLOW}Creating interactive query tool...${NC}"
|
||||
|
||||
cat > "$OUTPUT_DIR/query_expertise.sh" << 'QUERYEOF'
|
||||
#!/bin/bash
|
||||
|
||||
# Interactive expertise query tool
|
||||
|
||||
GREEN='\033[0;32m'
|
||||
BLUE='\033[0;34m'
|
||||
CYAN='\033[0;36m'
|
||||
NC='\033[0m'
|
||||
|
||||
echo -e "${BLUE}╔══════════════════════════════════════════════════╗${NC}"
|
||||
echo -e "${BLUE}║ Expert Guidance Query ║${NC}"
|
||||
echo -e "${BLUE}╚══════════════════════════════════════════════════╝${NC}"
|
||||
echo ""
|
||||
|
||||
echo "What are you working on?"
|
||||
echo ""
|
||||
echo "1) Authentication"
|
||||
echo "2) API Design"
|
||||
echo "3) Database Design"
|
||||
echo "4) Testing"
|
||||
echo "5) Error Handling"
|
||||
echo "6) Quick Reference (coding style)"
|
||||
echo "7) Browse all expertise"
|
||||
echo ""
|
||||
|
||||
read -p "Select (1-7): " CHOICE
|
||||
|
||||
case $CHOICE in
|
||||
1)
|
||||
echo ""
|
||||
echo -e "${GREEN}=== Authentication Expertise ===${NC}"
|
||||
cat expertise/by_task/authentication.md
|
||||
;;
|
||||
2)
|
||||
echo ""
|
||||
echo -e "${GREEN}=== API Design Expertise ===${NC}"
|
||||
cat expertise/by_task/api_design.md
|
||||
;;
|
||||
3)
|
||||
echo ""
|
||||
echo -e "${GREEN}=== Database Design Expertise ===${NC}"
|
||||
[ -f expertise/by_task/database_design.md ] && cat expertise/by_task/database_design.md || echo "Not available"
|
||||
;;
|
||||
4)
|
||||
echo ""
|
||||
echo -e "${GREEN}=== Testing Expertise ===${NC}"
|
||||
cat expertise/by_task/testing.md
|
||||
;;
|
||||
5)
|
||||
echo ""
|
||||
echo -e "${GREEN}=== Error Handling Expertise ===${NC}"
|
||||
[ -f expertise/by_task/error_handling.md ] && cat expertise/by_task/error_handling.md || echo "Not available"
|
||||
;;
|
||||
6)
|
||||
echo ""
|
||||
echo -e "${GREEN}=== Quick Reference ===${NC}"
|
||||
cat expertise/quick_reference/coding_style.md
|
||||
;;
|
||||
7)
|
||||
echo ""
|
||||
echo -e "${GREEN}=== All Expertise Areas ===${NC}"
|
||||
find expertise/ -name "*.md" -type f | sort
|
||||
;;
|
||||
*)
|
||||
echo "Invalid selection"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
echo ""
|
||||
echo -e "${CYAN}━━━ Related Resources ━━━${NC}"
|
||||
echo "Examples: ./examples/"
|
||||
echo "Full profile: engineer_profiles/$ENGINEER_USERNAME/"
|
||||
echo ""
|
||||
QUERYEOF
|
||||
|
||||
chmod +x "$OUTPUT_DIR/query_expertise.sh"
|
||||
|
||||
echo -e "${GREEN}✓ Query tool created${NC}"
|
||||
|
||||
# Step 7: Copy Examples
|
||||
echo -e "${YELLOW}Copying code examples...${NC}"
|
||||
|
||||
if [ -d "$PROFILE_DIR/examples" ]; then
|
||||
cp -r "$PROFILE_DIR/examples/"* "$OUTPUT_DIR/examples/" 2>/dev/null || true
|
||||
EXAMPLES_COUNT=$(find "$OUTPUT_DIR/examples" -type f | wc -l)
|
||||
echo -e "${GREEN}✓ Copied $EXAMPLES_COUNT example files${NC}"
|
||||
else
|
||||
echo -e "${YELLOW}⚠ No examples found in profile${NC}"
|
||||
fi
|
||||
|
||||
# Step 8: Create Usage Guide
|
||||
echo -e "${YELLOW}Creating usage guide...${NC}"
|
||||
|
||||
cat > "$OUTPUT_DIR/HOW_TO_USE.md" << EOF
|
||||
# How to Use This Expert Skill
|
||||
|
||||
## For AI Agents
|
||||
|
||||
### Basic Usage
|
||||
\`\`\`
|
||||
"Using the skill at expert-skills/$SKILL_NAME/, help me implement
|
||||
user authentication"
|
||||
\`\`\`
|
||||
|
||||
### Language-Specific
|
||||
\`\`\`
|
||||
"Using expert-skills/$SKILL_NAME/, write a TypeScript service
|
||||
following their coding style"
|
||||
\`\`\`
|
||||
|
||||
### Pattern-Specific
|
||||
\`\`\`
|
||||
"Using expert-skills/$SKILL_NAME/, show me how they implement
|
||||
the repository pattern"
|
||||
\`\`\`
|
||||
|
||||
### Code Review
|
||||
\`\`\`
|
||||
"Using expert-skills/$SKILL_NAME/, review this code using their
|
||||
standards and best practices"
|
||||
\`\`\`
|
||||
|
||||
## For Humans
|
||||
|
||||
### Interactive Query
|
||||
\`\`\`bash
|
||||
cd expert-skills/$SKILL_NAME
|
||||
./query_expertise.sh
|
||||
\`\`\`
|
||||
|
||||
### Browse by Task
|
||||
\`\`\`bash
|
||||
cat expertise/by_task/authentication.md
|
||||
cat expertise/by_task/api_design.md
|
||||
cat expertise/by_task/testing.md
|
||||
\`\`\`
|
||||
|
||||
### Quick Reference
|
||||
\`\`\`bash
|
||||
cat expertise/quick_reference/coding_style.md
|
||||
cat expertise/quick_reference/naming_conventions.md
|
||||
\`\`\`
|
||||
|
||||
### View Examples
|
||||
\`\`\`bash
|
||||
ls examples/
|
||||
cat examples/[filename]
|
||||
\`\`\`
|
||||
|
||||
## Progressive Disclosure
|
||||
|
||||
This skill shows only what you need:
|
||||
|
||||
1. **Ask specific question** → Get specific answer
|
||||
2. **Request by task** → Get task-specific patterns
|
||||
3. **Query by language** → Get language-specific style
|
||||
4. **Search by pattern** → Get pattern implementation
|
||||
|
||||
## Tips
|
||||
|
||||
- Start with quick_reference/ for overview
|
||||
- Use query tool for guided exploration
|
||||
- Reference specific tasks for focused guidance
|
||||
- Check examples/ for real code samples
|
||||
|
||||
## Source Profile
|
||||
|
||||
Full engineer profile: \`engineer_profiles/$ENGINEER_USERNAME/\`
|
||||
|
||||
Last updated: $(date +%Y-%m-%d)
|
||||
EOF
|
||||
|
||||
echo -e "${GREEN}✓ Usage guide created${NC}"
|
||||
|
||||
# Step 9: Generate Summary
|
||||
echo ""
|
||||
echo -e "${BLUE}╔════════════════════════════════════════════════╗${NC}"
|
||||
echo -e "${BLUE}║ Skill Creation Complete! ║${NC}"
|
||||
echo -e "${BLUE}╚════════════════════════════════════════════════╝${NC}"
|
||||
echo ""
|
||||
echo -e "${GREEN}Expert skill created: ${BLUE}$OUTPUT_DIR${NC}"
|
||||
echo ""
|
||||
echo -e "${YELLOW}━━━ Skill Details ━━━${NC}"
|
||||
echo "Skill Name: $SKILL_NAME"
|
||||
echo "Engineer: $ENGINEER_NAME"
|
||||
echo "Source Profile: $PROFILE_DIR"
|
||||
echo ""
|
||||
echo -e "${YELLOW}━━━ Structure Created ━━━${NC}"
|
||||
echo "├── SKILL.md (skill documentation)"
|
||||
echo "├── HOW_TO_USE.md (usage guide)"
|
||||
echo "├── query_expertise.sh (interactive query)"
|
||||
echo "├── expertise/"
|
||||
echo "│ ├── by_task/ (task-specific guidance)"
|
||||
echo "│ ├── by_language/ (language-specific style)"
|
||||
echo "│ ├── by_pattern/ (design patterns)"
|
||||
echo "│ └── quick_reference/ (fast lookups)"
|
||||
echo "└── examples/ (code samples)"
|
||||
echo ""
|
||||
echo -e "${CYAN}━━━ Next Steps ━━━${NC}"
|
||||
echo ""
|
||||
echo "1. Review the skill:"
|
||||
echo -e " ${BLUE}cat $OUTPUT_DIR/SKILL.md${NC}"
|
||||
echo ""
|
||||
echo "2. Test the query tool:"
|
||||
echo -e " ${BLUE}cd $OUTPUT_DIR && ./query_expertise.sh${NC}"
|
||||
echo ""
|
||||
echo "3. Enhance with profile content:"
|
||||
echo " - Populate by_task/ docs with specific patterns"
|
||||
echo " - Add language-specific guides to by_language/"
|
||||
echo " - Document patterns in by_pattern/"
|
||||
echo ""
|
||||
echo "4. Use with AI agents:"
|
||||
echo -e " ${BLUE}\"Using expert-skills/$SKILL_NAME/, implement authentication\"${NC}"
|
||||
echo ""
|
||||
echo -e "${YELLOW}💡 Tip: The skill provides progressive disclosure - agents get only${NC}"
|
||||
echo -e "${YELLOW} what's needed for their specific task${NC}"
|
||||
echo ""
|
||||
echo -e "${GREEN}✅ Skill is ready to use!${NC}"
|
||||
echo ""
|
||||
Reference in New Issue
Block a user