add-search-engine
Integrate a new LLM search provider into Mentha
Best use case
add-search-engine is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Integrate a new LLM search provider into Mentha
Teams using add-search-engine should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/add-search-engine/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How add-search-engine Compares
| Feature / Agent | add-search-engine | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Integrate a new LLM search provider into Mentha
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Add Search Engine Skill
When the user requests to add a new AI search engine (e.g., "Integrate Claude 3", "Add Anthropic"), follow these steps:
## Steps
1. **Create Provider File**
- Create `src/infrastructure/search/{provider-name}.provider.ts`
- Import the `ISearchProvider` interface from `src/domain/search/types.ts`
- Implement all required methods
2. **Provider Template**
```typescript
import { ISearchProvider, SearchOptions, SearchResult } from '../../domain/search/types.js';
import { env } from '../../config/index.js';
export class {ProviderName}Provider implements ISearchProvider {
private readonly apiKey: string;
constructor() {
this.apiKey = env.{PROVIDER}_API_KEY ?? '';
if (!this.apiKey) {
throw new Error('{PROVIDER}_API_KEY is required');
}
}
async search(query: string, options?: SearchOptions): Promise<SearchResult> {
// Implementation
}
}
```
3. **Update Factory**
- Edit `src/infrastructure/search/factory.ts`
- Add the new provider to the `createProvider` function
- Add the provider enum value
4. **Update Environment**
- Add `{PROVIDER}_API_KEY` to `.env.example`
- Add to the env schema in `src/config/env.ts`
5. **Update Schema**
- Add provider to the engines enum in controller schemas
6. **Test**
- Run `npm run typecheck` to verify compilation
- Create a basic integration test
## Validation Checklist
- [ ] Provider implements `ISearchProvider` interface
- [ ] Environment variable documented in `.env.example`
- [ ] Factory updated with new provider
- [ ] Controller enum includes new provider
- [ ] No TypeScript errorsRelated Skills
ml-engineer
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.
llm-application-dev-ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications. Use when: the task directly matches ai engineer responsibilities within plugin llm-application-dev. Do not use when: a more specific framework or task-focused skill is clearly a better match.
gpt-researcher
Run GPT-Researcher multi-agent deep research framework locally using OpenAI GPT-5.2. Replaces ChatGPT Deep Research with local control. Researches 100+ sources in parallel, provides comprehensive citations. Use for Phase 3 industry/technical research or comprehensive synthesis. Takes 6-20 min depending on report type. Supports multiple LLM providers.
flow-engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, Antigravity, OpenAI Codex, OpenCode).
deep-research
Web research with Graph-of-Thoughts for fast-changing topics. Use when user requests research, analysis, investigation, or comparison requiring current information. Features hypothesis testing, source triangulation, claim verification, Red Team, self-critique, and gap analysis. Supports Quick/Standard/Deep/Exhaustive tiers. Creative Mode for cross-industry innovation.
data-engineering-data-pipeline
You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
context-engineering
Use when designing agent system prompts, optimizing RAG retrieval, or when context is too expensive or slow. Reduces tokens while maintaining quality through strategic positioning and attention-aware design.
Build Your Data Engineering Skill
Create your LLMOps data engineering skill in one prompt, then learn to improve it throughout the chapter
brutal-deepresearch
Structured deep research pipeline with confirmation gates and resume support. Generates outline, launches parallel research agents, produces validated JSON results and markdown report.
ai-engineering-skill
Practical guide for building production ML systems based on Chip Huyen's AI Engineering book. Use when users ask about model evaluation, deployment strategies, monitoring, data pipelines, feature engineering, cost optimization, or MLOps. Covers metrics, A/B testing, serving patterns, drift detection, and production best practices.
ai-engineer
Build production-ready LLM applications, advanced RAG systems, and