Merge pull request #186 from SnakeEye-sudo/feat/add-new-skills

feat: add 3 new community skills (gemini-api-integration, llm-prompt-optimizer, saas-mvp-launcher)
2026-03-04 18:04:18 +01:00
parent 38783a36da ff55696e1d
commit 9fc8d14506
3 changed files with 588 additions and 0 deletions
--- a/skills/gemini-api-integration/SKILL.md
+++ b/skills/gemini-api-integration/SKILL.md
@@ -0,0 +1,188 @@
+---
+name: gemini-api-integration
+description: "Use when integrating Google Gemini API into projects. Covers model selection, multimodal inputs, streaming, function calling, and production best practices."
+risk: low
+source: community
+date_added: "2026-03-04"
+---
+
+# Gemini API Integration
+
+## Overview
+
+This skill guides AI agents through integrating Google Gemini API into applications — from basic text generation to advanced multimodal, function calling, and streaming use cases. It covers the full Gemini SDK lifecycle with production-grade patterns.
+
+## When to Use This Skill
+
+- Use when setting up Gemini API for the first time in a Node.js, Python, or browser project
+- Use when implementing multimodal inputs (text + image/audio/video)
+- Use when adding streaming responses to improve perceived latency
+- Use when implementing function calling / tool use with Gemini
+- Use when optimizing model selection (Flash vs Pro vs Ultra) for cost and performance
+- Use when debugging Gemini API errors, rate limits, or quota issues
+
+## Step-by-Step Guide
+
+### 1. Installation & Setup
+
+**Node.js / TypeScript:**
+```bash
+npm install @google/generative-ai
+```
+
+**Python:**
+```bash
+pip install google-generativeai
+```
+
+Set your API key securely:
+```bash
+export GEMINI_API_KEY="your-api-key-here"
+```
+
+### 2. Basic Text Generation
+
+**Node.js:**
+```javascript
+import { GoogleGenerativeAI } from "@google/generative-ai";
+
+const genAI = new GoogleGenerativeAI(process.env.GEMINI_API_KEY);
+const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
+
+const result = await model.generateContent("Explain async/await in JavaScript");
+console.log(result.response.text());
+```
+
+**Python:**
+```python
+import google.generativeai as genai
+import os
+
+genai.configure(api_key=os.environ["GEMINI_API_KEY"])
+model = genai.GenerativeModel("gemini-1.5-flash")
+
+response = model.generate_content("Explain async/await in JavaScript")
+print(response.text)
+```
+
+### 3. Streaming Responses
+
+```javascript
+const result = await model.generateContentStream("Write a detailed blog post about AI");
+
+for await (const chunk of result.stream) {
+  process.stdout.write(chunk.text());
+}
+```
+
+### 4. Multimodal Input (Text + Image)
+
+```javascript
+import fs from "fs";
+
+const imageData = fs.readFileSync("screenshot.png");
+const imagePart = {
+  inlineData: {
+    data: imageData.toString("base64"),
+    mimeType: "image/png",
+  },
+};
+
+const result = await model.generateContent(["Describe this image:", imagePart]);
+console.log(result.response.text());
+```
+
+### 5. Function Calling / Tool Use
+
+```javascript
+const tools = [{
+  functionDeclarations: [{
+    name: "get_weather",
+    description: "Get current weather for a city",
+    parameters: {
+      type: "OBJECT",
+      properties: {
+        city: { type: "STRING", description: "City name" },
+      },
+      required: ["city"],
+    },
+  }],
+}];
+
+const model = genAI.getGenerativeModel({ model: "gemini-1.5-pro", tools });
+const result = await model.generateContent("What's the weather in Mumbai?");
+
+const call = result.response.functionCalls()?.[0];
+if (call) {
+  // Execute the actual function
+  const weatherData = await getWeather(call.args.city);
+  // Send result back to model
+}
+```
+
+### 6. Multi-turn Chat
+
+```javascript
+const chat = model.startChat({
+  history: [
+    { role: "user", parts: [{ text: "You are a helpful coding assistant." }] },
+    { role: "model", parts: [{ text: "Sure! I'm ready to help with code." }] },
+  ],
+});
+
+const response = await chat.sendMessage("How do I reverse a string in Python?");
+console.log(response.response.text());
+```
+
+### 7. Model Selection Guide
+
+| Model | Best For | Speed | Cost |
+|-------|----------|-------|------|
+| `gemini-1.5-flash` | High-throughput, cost-sensitive tasks | Fast | Low |
+| `gemini-1.5-pro` | Complex reasoning, long context | Medium | Medium |
+| `gemini-2.0-flash` | Latest fast model, multimodal | Very Fast | Low |
+| `gemini-2.0-pro` | Most capable, advanced tasks | Slow | High |
+
+## Best Practices
+
+- ✅ **Do:** Use `gemini-1.5-flash` for most tasks — it's fast and cost-effective
+- ✅ **Do:** Always stream responses for user-facing chat UIs to reduce perceived latency
+- ✅ **Do:** Store API keys in environment variables, never hard-code them
+- ✅ **Do:** Implement exponential backoff for rate limit (429) errors
+- ✅ **Do:** Use `systemInstruction` to set persistent model behavior
+- ❌ **Don't:** Use `gemini-pro` for simple tasks — Flash is cheaper and faster
+- ❌ **Don't:** Send large base64 images inline for files > 20MB — use File API instead
+- ❌ **Don't:** Ignore safety ratings in responses for production apps
+
+## Error Handling
+
+```javascript
+try {
+  const result = await model.generateContent(prompt);
+  return result.response.text();
+} catch (error) {
+  if (error.status === 429) {
+    // Rate limited — wait and retry with exponential backoff
+    await new Promise(r => setTimeout(r, 2 ** retryCount * 1000));
+  } else if (error.status === 400) {
+    // Invalid request — check prompt or parameters
+    console.error("Invalid request:", error.message);
+  } else {
+    throw error;
+  }
+}
+```
+
+## Troubleshooting
+
+**Problem:** `API_KEY_INVALID` error
+**Solution:** Ensure `GEMINI_API_KEY` environment variable is set and the key is active in Google AI Studio.
+
+**Problem:** Response blocked by safety filters
+**Solution:** Check `result.response.promptFeedback.blockReason` and adjust your prompt or safety settings.
+
+**Problem:** Slow response times
+**Solution:** Switch to `gemini-1.5-flash` and enable streaming. Consider caching repeated prompts.
+
+**Problem:** `RESOURCE_EXHAUSTED` (quota exceeded)
+**Solution:** Check your quota in Google Cloud Console. Implement request queuing and exponential backoff.
--- a/skills/llm-prompt-optimizer/SKILL.md
+++ b/skills/llm-prompt-optimizer/SKILL.md
@@ -0,0 +1,182 @@
+---
+name: llm-prompt-optimizer
+description: "Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage."
+risk: low
+source: community
+date_added: "2026-03-04"
+---
+
+# LLM Prompt Optimizer
+
+## Overview
+
+This skill transforms weak, vague, or inconsistent prompts into precision-engineered instructions that reliably produce high-quality outputs from any LLM (Claude, Gemini, GPT-4, Llama, etc.). It applies systematic prompt engineering frameworks — from zero-shot to few-shot, chain-of-thought, and structured output patterns.
+
+## When to Use This Skill
+
+- Use when a prompt returns inconsistent, vague, or hallucinated results
+- Use when you need structured/JSON output from an LLM reliably
+- Use when designing system prompts for AI agents or chatbots
+- Use when you want to reduce token usage without sacrificing quality
+- Use when implementing chain-of-thought reasoning for complex tasks
+- Use when prompts work on one model but fail on another
+
+## Step-by-Step Guide
+
+### 1. Diagnose the Weak Prompt
+
+Before optimizing, identify which problem pattern applies:
+
+| Problem | Symptom | Fix |
+|---------|---------|-----|
+| Too vague | Generic, unhelpful answers | Add role + context + constraints |
+| No structure | Unformatted, hard-to-parse output | Specify output format explicitly |
+| Hallucination | Confident wrong answers | Add "say I don't know if unsure" |
+| Inconsistent | Different answers each run | Add few-shot examples |
+| Too long | Verbose, padded responses | Add length constraints |
+
+### 2. Apply the RSCIT Framework
+
+Every optimized prompt should have:
+
+- **R** — **Role**: Who is the AI in this interaction?
+- **S** — **Situation**: What context does it need?
+- **C** — **Constraints**: What are the rules and limits?
+- **I** — **Instructions**: What exactly should it do?
+- **T** — **Template**: What should the output look like?
+
+**Before (weak prompt):**
+```
+Explain machine learning.
+```
+
+**After (optimized prompt):**
+```
+You are a senior ML engineer explaining concepts to a junior developer.
+
+Context: The developer has 1 year of Python experience but no ML background.
+
+Task: Explain supervised machine learning in simple terms.
+
+Constraints:
+- Use an analogy from everyday life
+- Maximum 200 words
+- No mathematical formulas
+- End with one actionable next step
+
+Format: Plain prose, no bullet points.
+```
+
+### 3. Chain-of-Thought (CoT) Pattern
+
+For reasoning tasks, instruct the model to think step-by-step:
+
+```
+Solve this problem step by step, showing your work at each stage.
+Only provide the final answer after completing all reasoning steps.
+
+Problem: [your problem here]
+
+Thinking process:
+Step 1: [identify what's given]
+Step 2: [identify what's needed]
+Step 3: [apply logic or formula]
+Step 4: [verify the answer]
+
+Final Answer:
+```
+
+### 4. Few-Shot Examples Pattern
+
+Provide 2-3 examples to establish the pattern:
+
+```
+Classify the sentiment of customer reviews as POSITIVE, NEGATIVE, or NEUTRAL.
+
+Examples:
+Review: "This product exceeded my expectations!" -> POSITIVE
+Review: "It arrived broken and support was useless." -> NEGATIVE  
+Review: "Product works as described, nothing special." -> NEUTRAL
+
+Now classify:
+Review: "[your review here]" ->
+```
+
+### 5. Structured JSON Output Pattern
+
+```
+Extract the following information from the text below and return it as valid JSON only.
+Do not include any explanation or markdown — just the raw JSON object.
+
+Schema:
+{
+  "name": string,
+  "email": string | null,
+  "company": string | null,
+  "role": string | null
+}
+
+Text: [input text here]
+```
+
+### 6. Reduce Hallucination Pattern
+
+```
+Answer the following question based ONLY on the provided context.
+If the answer is not contained in the context, respond with exactly: "I don't have enough information to answer this."
+Do not make up or infer information not present in the context.
+
+Context:
+[your context here]
+
+Question: [your question here]
+```
+
+### 7. Prompt Compression Techniques
+
+Reduce token count without losing effectiveness:
+
+```
+# Verbose (expensive)
+"Please carefully analyze the following code and provide a detailed explanation of 
+what it does, how it works, and any potential issues you might find."
+
+# Compressed (efficient, same quality)
+"Analyze this code: explain what it does, how it works, and flag any issues."
+```
+
+## Best Practices
+
+- ✅ **Do:** Always specify the output format (JSON, markdown, plain text, bullet list)
+- ✅ **Do:** Use delimiters (```, ---) to separate instructions from content
+- ✅ **Do:** Test prompts with edge cases (empty input, unusual data)
+- ✅ **Do:** Version your system prompts in source control
+- ✅ **Do:** Add "think step by step" for math, logic, or multi-step tasks
+- ❌ **Don't:** Use negative-only instructions ("don't be verbose") — add positive alternatives
+- ❌ **Don't:** Assume the model knows your codebase context — always include it
+- ❌ **Don't:** Use the same prompt across different models without testing — they behave differently
+
+## Prompt Audit Checklist
+
+Before using a prompt in production:
+
+- [ ] Does it have a clear role/persona?
+- [ ] Is the output format explicitly defined?
+- [ ] Are edge cases handled (empty input, ambiguous data)?
+- [ ] Is the length appropriate (not too long/short)?
+- [ ] Has it been tested on 5+ varied inputs?
+- [ ] Is hallucination risk addressed for factual tasks?
+
+## Troubleshooting
+
+**Problem:** Model ignores format instructions
+**Solution:** Move format instructions to the END of the prompt, after examples. Use strong language: "You MUST return only valid JSON."
+
+**Problem:** Inconsistent results between runs
+**Solution:** Lower the temperature setting (0.0-0.3 for factual tasks). Add more few-shot examples.
+
+**Problem:** Prompt works in playground but fails in production
+**Solution:** Check if system prompt is being sent correctly. Verify token limits aren't being exceeded (use a token counter).
+
+**Problem:** Output is too long
+**Solution:** Add explicit word/sentence limits: "Respond in exactly 3 bullet points, each under 20 words."
--- a/skills/saas-mvp-launcher/SKILL.md
+++ b/skills/saas-mvp-launcher/SKILL.md
@@ -0,0 +1,218 @@
+---
+name: saas-mvp-launcher
+description: "Use when planning or building a SaaS MVP from scratch. Provides a structured roadmap covering tech stack, architecture, auth, payments, and launch checklist."
+risk: low
+source: community
+date_added: "2026-03-04"
+---
+
+# SaaS MVP Launcher
+
+## Overview
+
+This skill guides you through building a production-ready SaaS MVP in the shortest time possible. It covers everything from idea validation and tech stack selection to authentication, payments, database design, deployment, and launch — using modern, battle-tested tools.
+
+## When to Use This Skill
+
+- Use when starting a new SaaS product from scratch
+- Use when you need to choose a tech stack for a web application
+- Use when setting up authentication, billing, or database for a SaaS
+- Use when you want a structured launch checklist before going live
+- Use when designing the architecture of a multi-tenant application
+- Use when doing a technical review of an existing early-stage SaaS
+
+## Step-by-Step Guide
+
+### 1. Validate Before You Build
+
+Before writing any code, validate the idea:
+
+```
+Validation checklist:
+- [ ] Can you describe the problem in one sentence?
+- [ ] Who is the exact customer? (not "everyone")
+- [ ] What do they pay for today to solve this?
+- [ ] Have you talked to 5+ potential customers?
+- [ ] Will they pay $X/month for your solution?
+```
+
+**Rule:** If you can't get 3 people to pre-pay or sign a letter of intent, don't build yet.
+
+### 2. Choose Your Tech Stack
+
+Recommended modern SaaS stack (2026):
+
+| Layer | Choice | Why |
+|-------|--------|-----|
+| Frontend | Next.js 15 + TypeScript | Full-stack, great DX, Vercel deploy |
+| Styling | Tailwind CSS + shadcn/ui | Fast, accessible, customizable |
+| Backend | Next.js API Routes or tRPC | Type-safe, co-located |
+| Database | PostgreSQL via Supabase | Reliable, scalable, free tier |
+| ORM | Prisma or Drizzle | Type-safe queries, migrations |
+| Auth | Clerk or NextAuth.js | Social login, session management |
+| Payments | Stripe | Industry standard, great docs |
+| Email | Resend + React Email | Modern, developer-friendly |
+| Deployment | Vercel (frontend) + Railway (backend) | Zero-config, fast CI/CD |
+| Monitoring | Sentry + PostHog | Error tracking + analytics |
+
+### 3. Project Structure
+
+```
+my-saas/
+├── app/                    # Next.js App Router
+│   ├── (auth)/             # Auth routes (login, signup)
+│   ├── (dashboard)/        # Protected app routes
+│   ├── (marketing)/        # Public landing pages
+│   └── api/                # API routes
+├── components/
+│   ├── ui/                 # shadcn/ui components
+│   └── [feature]/          # Feature-specific components
+├── lib/
+│   ├── db.ts               # Database client (Prisma/Drizzle)
+│   ├── stripe.ts           # Stripe client
+│   └── email.ts            # Email client (Resend)
+├── prisma/
+│   └── schema.prisma       # Database schema
+├── .env.local              # Environment variables
+└── middleware.ts           # Auth middleware
+```
+
+### 4. Core Database Schema (Multi-tenant SaaS)
+
+```prisma
+model User {
+  id            String    @id @default(cuid())
+  email         String    @unique
+  name          String?
+  createdAt     DateTime  @default(now())
+  subscription  Subscription?
+  workspaces    WorkspaceMember[]
+}
+
+model Workspace {
+  id        String    @id @default(cuid())
+  name      String
+  slug      String    @unique
+  plan      Plan      @default(FREE)
+  members   WorkspaceMember[]
+  createdAt DateTime  @default(now())
+}
+
+model Subscription {
+  id                 String   @id @default(cuid())
+  userId             String   @unique
+  user               User     @relation(fields: [userId], references: [id])
+  stripeCustomerId   String   @unique
+  stripePriceId      String
+  stripeSubId        String   @unique
+  status             String   # active, canceled, past_due
+  currentPeriodEnd   DateTime
+}
+
+enum Plan {
+  FREE
+  PRO
+  ENTERPRISE
+}
+```
+
+### 5. Authentication Setup (Clerk)
+
+```typescript
+// middleware.ts
+import { clerkMiddleware, createRouteMatcher } from '@clerk/nextjs/server';
+
+const isPublicRoute = createRouteMatcher([
+  '/',
+  '/pricing',
+  '/blog(.*)',
+  '/sign-in(.*)',
+  '/sign-up(.*)',
+  '/api/webhooks(.*)',
+]);
+
+export default clerkMiddleware((auth, req) => {
+  if (!isPublicRoute(req)) {
+    auth().protect();
+  }
+});
+
+export const config = {
+  matcher: ['/((?!.*\\..*|_next).*)', '/', '/(api|trpc)(.*)'],
+};
+```
+
+### 6. Stripe Integration (Subscriptions)
+
+```typescript
+// lib/stripe.ts
+import Stripe from 'stripe';
+export const stripe = new Stripe(process.env.STRIPE_SECRET_KEY!, {
+  apiVersion: '2025-01-27.acacia',
+});
+
+// Create checkout session
+export async function createCheckoutSession(userId: string, priceId: string) {
+  return stripe.checkout.sessions.create({
+    mode: 'subscription',
+    payment_method_types: ['card'],
+    line_items: [{ price: priceId, quantity: 1 }],
+    success_url: `${process.env.NEXT_PUBLIC_URL}/dashboard?success=true`,
+    cancel_url: `${process.env.NEXT_PUBLIC_URL}/pricing`,
+    metadata: { userId },
+  });
+}
+```
+
+### 7. Pre-Launch Checklist
+
+**Technical:**
+- [ ] Authentication works (signup, login, logout, password reset)
+- [ ] Payments work end-to-end (subscribe, cancel, upgrade)
+- [ ] Error monitoring configured (Sentry)
+- [ ] Environment variables documented
+- [ ] Database backups configured
+- [ ] Rate limiting on API routes
+- [ ] Input validation with Zod on all forms
+- [ ] HTTPS enforced, security headers set
+
+**Product:**
+- [ ] Landing page with clear value proposition
+- [ ] Pricing page with 2-3 tiers
+- [ ] Onboarding flow (first value in < 5 minutes)
+- [ ] Email sequences (welcome, trial ending, payment failed)
+- [ ] Terms of Service and Privacy Policy pages
+- [ ] Support channel (email / chat)
+
+**Marketing:**
+- [ ] Domain purchased and configured
+- [ ] SEO meta tags on all pages
+- [ ] Google Analytics or PostHog installed
+- [ ] Social media accounts created
+- [ ] Product Hunt draft ready
+
+## Best Practices
+
+- ✅ **Do:** Ship a working MVP in 4-6 weeks maximum, then iterate based on feedback
+- ✅ **Do:** Charge from day 1 — free users don't validate product-market fit
+- ✅ **Do:** Build the "happy path" first, handle edge cases later
+- ✅ **Do:** Use feature flags for gradual rollouts (e.g., Vercel Edge Config)
+- ✅ **Do:** Monitor user behavior from launch day — not after problems arise
+- ❌ **Don't:** Build every feature before talking to customers
+- ❌ **Don't:** Optimize for scale before reaching $10k MRR
+- ❌ **Don't:** Build a custom auth system — use Clerk, Auth.js, or Supabase Auth
+- ❌ **Don't:** Skip the onboarding flow — it's where most SaaS lose users
+
+## Troubleshooting
+
+**Problem:** Users sign up but don't activate (don't use core feature)
+**Solution:** Reduce steps to first value. Track with PostHog where users drop off in onboarding.
+
+**Problem:** High churn after trial
+**Solution:** Add an exit survey. Most churn is due to lack of perceived value, not price.
+
+**Problem:** Stripe webhook events not received locally
+**Solution:** Use Stripe CLI: `stripe listen --forward-to localhost:3000/api/webhooks/stripe`
+
+**Problem:** Database migrations failing in production
+**Solution:** Always run `prisma migrate deploy` (not `prisma migrate dev`) in production environments.