Claude-Code-Workflow/.claude/workflows/cli-templates/prompts/tech/tech-skill-index.txt

Template for generating tech stack SKILL.md index file

## Purpose
Create main SKILL package index with module references and loading recommendations.

## File Location
`.claude/skills/{tech_stack_name}/SKILL.md`

## Template Structure

```markdown
---
name: {TECH_STACK_NAME}
description: {MAIN_TECH} development guidelines from industry standards (Exa research)
version: 1.0.0
generated: {ISO_TIMESTAMP}
source: exa-research
---
# {TechStackTitle} SKILL Package

## Overview

{Brief 1-2 sentence description of the tech stack and purpose of this SKILL package}

**Primary Technology**: {MAIN_TECH}
{IF_COMPOSITE}**Frameworks**: {COMPONENT_LIST}{/IF_COMPOSITE}

## Modular Documentation

### Core Understanding (~8K tokens)
- [Principles](./principles.md) - Core concepts and philosophies
- [Patterns](./patterns.md) - Implementation patterns with examples

### Practical Guidance (~7K tokens)
- [Best Practices](./practices.md) - Do's, don'ts, anti-patterns
- [Testing](./testing.md) - Testing strategies and frameworks

### Configuration & Integration (~7K tokens)
- [Configuration](./config.md) - Setup, tooling, configuration
{IF_COMPOSITE}- [Frameworks](./frameworks.md) - Integration patterns{/IF_COMPOSITE}

## Loading Recommendations

### Quick Reference (~7K tokens)
Load for quick consultation on core concepts:
- principles.md
- practices.md

**Use When**: Need quick reminder of best practices or core principles

### Implementation Focus (~8K tokens)
Load for active development work:
- patterns.md
- config.md

**Use When**: Writing code, setting up projects, implementing features

### Complete Package (~22K tokens)
Load all modules for comprehensive understanding:
- All 5-6 modules

**Use When**: Learning tech stack, architecture reviews, comprehensive reference

## Usage

**Load this SKILL when**:
- Starting new {TECH_STACK} projects
- Reviewing {TECH_STACK} code
- Learning {TECH_STACK} best practices
- Implementing {TECH_STACK} patterns
- Troubleshooting {TECH_STACK} issues

**Auto-triggers on**:
- Keywords: {TECH_KEYWORDS}
- File types: {FILE_EXTENSIONS}

## Research Metadata

- **Generated**: {ISO_TIMESTAMP}
- **Source**: Exa Research (web search + code context)
- **Queries Executed**: {QUERY_COUNT}
- **Sources Consulted**: {SOURCE_COUNT}
- **Research Quality**: {QUALITY_INDICATOR}

## Tech Stack Components

**Primary**: {MAIN_TECH} - {MAIN_TECH_DESCRIPTION}

{IF_COMPOSITE}
**Additional Frameworks**:
{FOR_EACH_COMPONENT}
- **{COMPONENT_NAME}**: {COMPONENT_DESCRIPTION}
{/FOR_EACH_COMPONENT}
{/IF_COMPOSITE}

## Version History

- **v1.0.0** ({DATE}): Initial SKILL package generated from Exa research

---

## Developer Notes

This SKILL package was auto-generated using:
- `/memory:tech-research` command
- Exa AI research APIs (mcp__exa__get_code_context_exa, mcp__exa__web_search_exa)
- Token limit: ~5K per module, ~22K total

To regenerate:
```bash
/memory:tech-research "{tech_stack_name}" --regenerate
```
```

---

## Variable Substitution Guide

### Required Variables
- `{TECH_STACK_NAME}`: Lowercase hyphenated name (e.g., "typescript-react-nextjs")
- `{TechStackTitle}`: Title case display name (e.g., "TypeScript React Next.js")
- `{MAIN_TECH}`: Primary technology (e.g., "TypeScript")
- `{ISO_TIMESTAMP}`: ISO 8601 timestamp (e.g., "2025-11-04T22:00:00Z")
- `{QUERY_COUNT}`: Number of Exa queries executed (e.g., 6)
- `{SOURCE_COUNT}`: Total sources consulted (e.g., 25)

### Conditional Variables
- `{IF_COMPOSITE}...{/IF_COMPOSITE}`: Only include if tech stack has multiple components
- `{COMPONENT_LIST}`: Comma-separated list of framework names
- `{FOR_EACH_COMPONENT}...{/FOR_EACH_COMPONENT}`: Loop through components

### Optional Variables
- `{MAIN_TECH_DESCRIPTION}`: One-line description of primary tech
- `{COMPONENT_DESCRIPTION}`: One-line description per component
- `{TECH_KEYWORDS}`: Comma-separated trigger keywords
- `{FILE_EXTENSIONS}`: File extensions (e.g., ".ts, .tsx, .jsx")
- `{QUALITY_INDICATOR}`: Research quality metric (e.g., "High", "Medium")

---

## Generation Instructions

### Step 1: Read metadata.json
Extract values for variables from metadata.json generated during module creation.

### Step 2: Determine composite status
- Single tech: Omit {IF_COMPOSITE} sections
- Composite: Include frameworks section and integration module reference

### Step 3: Calculate token estimates
- Verify module files exist
- Adjust token estimates based on actual file sizes
- Update loading recommendation estimates

### Step 4: Generate descriptions
- **Overview**: Brief description of tech stack purpose
- **Main tech description**: One-liner for primary technology
- **Component descriptions**: One-liner per additional framework

### Step 5: Build keyword lists
- Extract common keywords from tech stack name
- Add file extensions relevant to tech stack
- Include framework-specific triggers

### Step 6: Format timestamps
- Use ISO 8601 format for all timestamps
- Include timezone (UTC recommended)

### Step 7: Write SKILL.md
- Apply template with all substitutions
- Validate markdown formatting
- Verify all relative paths work

---

## Validation Checklist

- [ ] All module files exist and are referenced
- [ ] Token estimates are reasonably accurate
- [ ] Conditional sections handled correctly (composite vs single)
- [ ] Timestamps in ISO 8601 format
- [ ] All relative paths use ./ prefix
- [ ] Metadata section matches metadata.json
- [ ] Loading recommendations align with actual module sizes
- [ ] Usage section includes relevant trigger keywords