jeremylongshore

gamma-cost-tuning

@jeremylongshore/gamma-cost-tuning
jeremylongshore
1,004
123 forks
Updated 1/18/2026
View on GitHub

Optimize Gamma usage costs and manage API spending. Use when reducing API costs, implementing usage quotas, or planning for scale with budget constraints. Trigger with phrases like "gamma cost", "gamma billing", "gamma budget", "gamma expensive", "gamma pricing".

Installation

$skills install @jeremylongshore/gamma-cost-tuning
Claude Code
Cursor
Copilot
Codex
Antigravity

Details

Pathplugins/saas-packs/gamma-pack/skills/gamma-cost-tuning/SKILL.md
Branchmain
Scoped Name@jeremylongshore/gamma-cost-tuning

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

skills list

Skill Instructions


name: gamma-cost-tuning description: | Optimize Gamma usage costs and manage API spending. Use when reducing API costs, implementing usage quotas, or planning for scale with budget constraints. Trigger with phrases like "gamma cost", "gamma billing", "gamma budget", "gamma expensive", "gamma pricing". allowed-tools: Read, Write, Edit version: 1.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io

Gamma Cost Tuning

Overview

Optimize Gamma API usage to minimize costs while maintaining functionality.

Prerequisites

  • Active Gamma subscription
  • Access to usage dashboard
  • Understanding of pricing tiers

Gamma Pricing Model

ResourceFreeProTeamEnterprise
Presentations/mo10100500Custom
AI generations550200Unlimited
Exports/mo10100500Unlimited
API calls/min1060200Custom
Storage1GB10GB100GBCustom

Instructions

Step 1: Usage Monitoring

// Track usage per operation
interface UsageTracker {
  presentations: number;
  generations: number;
  exports: number;
  apiCalls: number;
}

const dailyUsage: UsageTracker = {
  presentations: 0,
  generations: 0,
  exports: 0,
  apiCalls: 0,
};

function trackUsage(operation: keyof UsageTracker) {
  dailyUsage[operation]++;

  // Check if approaching limits
  const limits = { presentations: 100, generations: 50, exports: 100, apiCalls: 60 };
  const percentage = (dailyUsage[operation] / limits[operation]) * 100;

  if (percentage >= 80) {
    console.warn(`Warning: ${operation} usage at ${percentage}%`);
    alertOps(`Gamma ${operation} usage high: ${percentage}%`);
  }
}

// Wrap API calls
async function createPresentation(opts: object) {
  trackUsage('apiCalls');
  trackUsage('presentations');
  if (opts.generateAI) trackUsage('generations');

  return gamma.presentations.create(opts);
}

Step 2: Implement Usage Quotas

interface UserQuota {
  userId: string;
  presentationsRemaining: number;
  generationsRemaining: number;
  exportsRemaining: number;
  resetsAt: Date;
}

async function checkQuota(userId: string, operation: string): Promise<boolean> {
  const quota = await getQuota(userId);

  const quotaField = `${operation}Remaining` as keyof UserQuota;
  if (typeof quota[quotaField] === 'number' && quota[quotaField] <= 0) {
    throw new QuotaExceededError(`${operation} quota exceeded`);
  }

  return true;
}

async function consumeQuota(userId: string, operation: string) {
  await db.quotas.update({
    where: { userId },
    data: { [`${operation}Remaining`]: { decrement: 1 } },
  });
}

// Usage in API route
app.post('/api/presentations', async (req, res) => {
  await checkQuota(req.userId, 'presentations');
  const result = await gamma.presentations.create(req.body);
  await consumeQuota(req.userId, 'presentations');
  res.json(result);
});

Step 3: Optimize AI Generation Usage

// Expensive: Full AI generation for each request
const expensive = await gamma.presentations.create({
  prompt: 'Create 20 slides about AI',
  generateAI: true,
  slideCount: 20, // Uses lots of AI credits
});

// Cost-effective: Template + targeted AI
const costEffective = await gamma.presentations.create({
  template: 'business-pitch', // Pre-made structure
  title: 'Our AI Solution',
  slides: [
    { title: 'Introduction', content: predefinedContent },
    { title: 'Problem', generateAI: true }, // AI only where needed
    { title: 'Solution', generateAI: true },
    { title: 'Team', content: teamData }, // No AI needed
    { title: 'Contact', content: contactInfo },
  ],
});

Step 4: Caching to Reduce API Calls

import Redis from 'ioredis';

const redis = new Redis(process.env.REDIS_URL);
const CACHE_TTL = 3600; // 1 hour

async function getCachedOrFetch<T>(
  key: string,
  fetchFn: () => Promise<T>
): Promise<T> {
  // Check cache
  const cached = await redis.get(key);
  if (cached) {
    return JSON.parse(cached);
  }

  // Fetch and cache
  const data = await fetchFn();
  await redis.setex(key, CACHE_TTL, JSON.stringify(data));

  return data;
}

// Usage - reduces repeated API calls
const presentation = await getCachedOrFetch(
  `presentation:${id}`,
  () => gamma.presentations.get(id)
);

Step 5: Batch Operations

// Expensive: Individual operations
for (const item of items) {
  await gamma.presentations.create(item); // N API calls
}

// Cost-effective: Batch operation
await gamma.presentations.createBatch(items); // 1 API call

// Or queue for off-peak processing
await queue.addBulk(items.map(item => ({
  name: 'create-presentation',
  data: item,
  opts: { delay: calculateOffPeakDelay() },
})));

Step 6: Cost Alerts and Budgets

// Set up budget alerts
const budget = {
  monthly: 100, // $100/month
  current: 0,
  alertThresholds: [50, 75, 90, 100],
};

async function recordCost(operation: string, cost: number) {
  budget.current += cost;

  for (const threshold of budget.alertThresholds) {
    const percentage = (budget.current / budget.monthly) * 100;
    if (percentage >= threshold) {
      await sendBudgetAlert(threshold, budget.current);
    }
  }

  if (budget.current >= budget.monthly) {
    await disableNonCriticalFeatures();
  }
}

Cost Reduction Strategies

StrategySavingsImplementation
Caching30-50%Redis/in-memory cache
Batching20-40%Batch API calls
Templates40-60%Reduce AI usage
Off-peak10-20%Queue for low-cost periods
QuotasVariablePer-user limits

Resources

Next Steps

Proceed to gamma-reference-architecture for architecture patterns.

More by jeremylongshore

View all
rabbitmq-queue-setup
1,004

Rabbitmq Queue Setup - Auto-activating skill for Backend Development. Triggers on: rabbitmq queue setup, rabbitmq queue setup Part of the Backend Development skill category.

model-evaluation-suite
1,004

evaluating-machine-learning-models: This skill allows Claude to evaluate machine learning models using a comprehensive suite of metrics. It should be used when the user requests model performance analysis, validation, or testing. Claude can use this skill to assess model accuracy, precision, recall, F1-score, and other relevant metrics. Trigger this skill when the user mentions "evaluate model", "model performance", "testing metrics", "validation results", or requests a comprehensive "model evaluation".

neural-network-builder
1,004

building-neural-networks: This skill allows Claude to construct and configure neural network architectures using the neural-network-builder plugin. It should be used when the user requests the creation of a new neural network, modification of an existing one, or assistance with defining the layers, parameters, and training process. The skill is triggered by requests involving terms like "build a neural network," "define network architecture," "configure layers," or specific mentions of neural network types (e.g., "CNN," "RNN," "transformer").

oauth-callback-handler
1,004

Oauth Callback Handler - Auto-activating skill for API Integration. Triggers on: oauth callback handler, oauth callback handler Part of the API Integration skill category.