CtrlK
BlogDocsLog inGet started
Tessl Logo

gamma-sdk-patterns

Reusable patterns for the Gamma REST API (no SDK exists). Use when building typed wrappers, generation helpers, template factories, or error handling for Gamma. Trigger: "gamma patterns", "gamma client wrapper", "gamma best practices", "gamma API helper", "gamma code structure".

79

Quality

76%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/saas-packs/gamma-pack/skills/gamma-sdk-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Gamma API Patterns

Overview

Gamma has no published SDK — all interaction is via REST at https://public-api.gamma.app/v1.0/. This skill provides production-grade patterns for typed clients, generation helpers, polling, template workflows, and error handling.

Prerequisites

  • Completed gamma-install-auth setup
  • TypeScript project with fetch (Node.js 18+)
  • Understanding of the generate-poll-retrieve workflow

Instructions

Step 1: Typed Client Singleton

// lib/gamma.ts
const GAMMA_BASE = "https://public-api.gamma.app/v1.0";

interface GammaConfig {
  apiKey: string;
  baseUrl?: string;
  timeoutMs?: number;
}

// Types based on actual API responses
interface GenerateRequest {
  content: string;
  outputFormat?: "presentation" | "document" | "webpage" | "social_post";
  themeId?: string;
  exportAs?: "pdf" | "pptx" | "png";
  textMode?: "generate" | "condense" | "preserve";
  textAmount?: "brief" | "medium" | "detailed" | "extensive";
  imageOptions?: { style?: string };
  sharingOptions?: {
    workspaceAccess?: "noAccess" | "view" | "comment" | "edit" | "fullAccess";
    externalAccess?: "noAccess" | "view" | "comment" | "edit" | "fullAccess";
  };
  folderIds?: string[];
}

interface GenerateResult {
  generationId: string;
  status: "in_progress" | "completed" | "failed";
  gammaUrl?: string;
  exportUrl?: string;
  creditsUsed?: number;
}

let instance: ReturnType<typeof createGammaClient> | null = null;

export function getGamma() {
  if (!instance) {
    instance = createGammaClient({
      apiKey: process.env.GAMMA_API_KEY!,
    });
  }
  return instance;
}

export function createGammaClient(config: GammaConfig) {
  const base = config.baseUrl ?? GAMMA_BASE;
  const headers: Record<string, string> = {
    "X-API-KEY": config.apiKey,
    "Content-Type": "application/json",
  };

  async function request<T>(method: string, path: string, body?: unknown): Promise<T> {
    const controller = new AbortController();
    const timeout = setTimeout(() => controller.abort(), config.timeoutMs ?? 30000);
    try {
      const res = await fetch(`${base}${path}`, {
        method,
        headers,
        body: body ? JSON.stringify(body) : undefined,
        signal: controller.signal,
      });
      if (!res.ok) {
        const text = await res.text();
        throw new GammaApiError(res.status, text, path);
      }
      return res.json() as T;
    } finally {
      clearTimeout(timeout);
    }
  }

  return {
    generate: (body: GenerateRequest) =>
      request<{ generationId: string }>("POST", "/generations", body),
    generateFromTemplate: (body: TemplateRequest) =>
      request<{ generationId: string }>("POST", "/generations/from-template", body),
    poll: (id: string) =>
      request<GenerateResult>("GET", `/generations/${id}`),
    getFileUrls: (id: string) =>
      request<{ exportUrl: string }>("GET", `/generations/${id}/files`),
    listThemes: () => request<Theme[]>("GET", "/themes"),
    listFolders: () => request<Folder[]>("GET", "/folders"),
  };
}

Step 2: Custom Error Class

// lib/errors.ts
export class GammaApiError extends Error {
  constructor(
    public status: number,
    public body: string,
    public path: string
  ) {
    super(`Gamma API ${status} on ${path}: ${body}`);
    this.name = "GammaApiError";
  }

  get isRateLimit() { return this.status === 429; }
  get isAuth() { return this.status === 401 || this.status === 403; }
  get isServerError() { return this.status >= 500; }
}

Step 3: Poll-Until-Done Helper

// lib/poll.ts
export async function pollUntilDone(
  gamma: ReturnType<typeof createGammaClient>,
  generationId: string,
  opts = { intervalMs: 5000, timeoutMs: 180000 }
): Promise<GenerateResult> {
  const deadline = Date.now() + opts.timeoutMs;

  while (Date.now() < deadline) {
    const result = await gamma.poll(generationId);

    if (result.status === "completed") return result;
    if (result.status === "failed") {
      throw new Error(`Generation ${generationId} failed`);
    }

    await new Promise((r) => setTimeout(r, opts.intervalMs));
  }

  throw new Error(`Poll timeout for ${generationId} after ${opts.timeoutMs}ms`);
}

Step 4: Generate-and-Wait Convenience

// lib/generate.ts
export async function generateAndWait(
  gamma: ReturnType<typeof createGammaClient>,
  request: GenerateRequest
): Promise<GenerateResult> {
  const { generationId } = await gamma.generate(request);
  console.log(`Generation started: ${generationId}`);
  return pollUntilDone(gamma, generationId);
}

// Usage
const gamma = getGamma();
const result = await generateAndWait(gamma, {
  content: "Quarterly business review for Q1 2026",
  outputFormat: "presentation",
  themeId: "theme_abc123",
  exportAs: "pptx",
  textAmount: "medium",
  imageOptions: { style: "photorealistic corporate" },
});
console.log(`View: ${result.gammaUrl}`);
console.log(`Download: ${result.exportUrl}`);

Step 5: Template-Based Generation

// lib/templates.ts
// Uses POST /v1.0/generations/from-template
// The template gamma must contain exactly one page

interface TemplateRequest {
  gammaId: string;     // Template gamma ID (one-page template)
  prompt: string;      // Content + instructions for the template
  themeId?: string;
  exportAs?: "pdf" | "pptx" | "png";
  imageOptions?: { style?: string };
  sharingOptions?: object;
  folderIds?: string[];
}

export async function generateFromTemplate(
  gamma: ReturnType<typeof createGammaClient>,
  templateId: string,
  prompt: string,
  options: Partial<TemplateRequest> = {}
): Promise<GenerateResult> {
  const { generationId } = await gamma.generateFromTemplate({
    gammaId: templateId,
    prompt,
    ...options,
  });
  return pollUntilDone(gamma, generationId);
}

Step 6: Retry with Backoff

// lib/retry.ts
export async function withRetry<T>(
  fn: () => Promise<T>,
  maxRetries = 3,
  baseDelayMs = 1000
): Promise<T> {
  for (let attempt = 0; attempt <= maxRetries; attempt++) {
    try {
      return await fn();
    } catch (err) {
      if (attempt === maxRetries) throw err;
      if (err instanceof GammaApiError && !err.isRateLimit && !err.isServerError) {
        throw err; // Don't retry auth errors or 4xx
      }
      const delay = baseDelayMs * Math.pow(2, attempt);
      console.warn(`Retry ${attempt + 1}/${maxRetries} in ${delay}ms`);
      await new Promise((r) => setTimeout(r, delay));
    }
  }
  throw new Error("Unreachable");
}

// Usage
const result = await withRetry(() =>
  generateAndWait(gamma, { content: "My deck", outputFormat: "presentation" })
);

API Endpoints Reference

MethodEndpointPurpose
POST/v1.0/generationsGenerate from text content
POST/v1.0/generations/from-templateGenerate from a template gamma
GET/v1.0/generations/{id}Poll generation status
GET/v1.0/generations/{id}/filesGet export file URLs
GET/v1.0/themesList workspace themes
GET/v1.0/foldersList workspace folders

Error Handling

PatternUse Case
GammaApiError classTyped error handling with isRateLimit, isAuth, isServerError
withRetry()Auto-retry on 429/5xx with exponential backoff
pollUntilDone()Timeout-aware polling with configurable interval
Singleton getGamma()Consistent config across modules

Resources

  • Gamma API Reference
  • Generate API Parameters
  • Create from Template

Next Steps

Proceed to gamma-core-workflow-a for content generation workflows.

Repository
jeremylongshore/claude-code-plugins-plus-skills
Last updated
Created

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.