Skill UI

A comprehensive guide to configuring SaaS integrations (like Clay) across development, staging, and production environments. This skill outlines best practices for maintaining environment isolation by using separate tables, managing unique webhook URLs, and implementing environment-aware code guards to prevent data leakage and ensure system stability during deployment.

A comprehensive workflow for production-grade, pre-recorded Speech-to-Text (STT) transcription using the Deepgram API. This skill supports transcribing audio from URLs or local files, offering advanced features such as speaker diarization, automatic summaries, sentiment analysis, and topic detection. It also includes robust batch processing methods for handling large datasets.

A comprehensive guide detailing security best practices for Deepgram API integration. It covers critical topics such as implementing scoped API keys, key rotation strategies, enabling built-in PII redaction for sensitive data, generating temporary client-side keys, and validating audio URLs to prevent SSRF attacks. Use this when building robust, production-grade applications requiring high data security and compliance.

A comprehensive guide containing minimal working examples for all core Exa search operations. It demonstrates basic metadata search, deep content extraction (text, highlights, summary), finding semantically similar pages, and retrieving content for specified URLs. Ideal for developers starting a new Exa integration or learning advanced RAG patterns.

Provides expert guidance on secure and performant file upload mechanisms for cloud environments. Covers best practices for using services like AWS S3 and Cloudflare R2, including implementing presigned URLs, handling large files via streaming, and optimizing images. Crucially emphasizes critical security measures such as validating file types using magic bytes, enforcing size limits, and preventing path traversal attacks.

Firecrawl Automation lets you use Claude Code to scrape pages, crawl sites, batch URLs, extract structured data, and monitor jobs via the Composio integration, ideal for terminal-driven web data pipelines.

This advanced workflow executes sophisticated web data gathering tasks. It supports three primary functions: LLM-powered structured data extraction using custom JSON schemas or prompts; efficient batch scraping of multiple known URLs; and rapid site mapping to discover all reachable URLs on a domain. Use this when you require reliable, typed data structures rather than raw markdown content.

This comprehensive guide details advanced techniques to significantly boost Firecrawl scraping speed and efficiency. Learn how to optimize performance by selecting the most efficient output formats (e.g., Markdown over HTML), implementing URL caching, utilizing batch scraping for multiple URLs, and tuning delay parameters for dynamic Single Page Applications (SPAs). Mastering these methods is crucial for building high-throughput, cost-effective web scraping pipelines.

This guide provides a comprehensive, multi-step technical process for migrating historical meeting recordings and data into the Fireflies.ai ecosystem. It covers various scenarios, including batch uploads from public URLs, importing authenticated files (S3/GCS), direct file uploads, and tracking progress via webhooks, ensuring a robust and validated transition from competitor platforms.

This comprehensive guide details how to configure Fireflies.ai across multiple isolated environments (Development, Staging, and Production). It emphasizes best practices for managing environment-specific secrets, API keys, and webhook URLs. By implementing robust environment separation, you can prevent data leakage and ensure that changes in one environment do not impact the stability or data integrity of others, which is crucial for CI/CD pipelines.

This skill provides a comprehensive guide and multiple code examples (cURL, Node.js, Python) for generating presentations using the Gamma API. It implements the standard asynchronous 'Generate-Poll-Retrieve' pattern: first POST to create the generation job, then GET to poll the status until complete, and finally retrieve the viewable and exportable URLs (PDF/PPTX).

Map web inputs for reflected or stored HTML injection, send crafted tags via URLs, POST bodies, or visible fields, and document appearance/phishing manipulations for authorized security assessments.