AI & ML

Manage design systems in Stitch using MCP tools, including retrieval of assets, creating or updating design systems, and applying them to screens.

Add real-time voice conversations to a custom agent runtime using ElevenLabs Speech Engine, handling WebSocket servers, browser clients, and interruption-aware streaming.

Update ElevenLabs agent skills from a merged weekly changelog, then open a pull request.

Translates Copilot CLI prompts, errors, and technical output into plain English with color-coded risk indicators for non-technical users.

Downloads, exports, and inspects Arize traces and spans to debug LLM application behavior using the ax CLI.

Manage Arize datasets and examples using the ax CLI: create, list, get, export, and append datasets for evaluation and experimentation.

Build and run evaluators for AI/LLM applications using Phoenix, covering error analysis, custom evaluators, experiments, and production monitoring.

Generates comprehensive test strategies, task breakdowns, and quality assurance documentation for GitHub projects using ISTQB and ISO 25010 frameworks.

Instrument LLM applications with OpenInference tracing for Phoenix AI observability, covering setup, custom spans, and production deployment.

Configure and manage GitHub secret scanning, push protection, custom patterns, and alert remediation.

Creates and manages annotation configs and annotation queues on Arize, and applies human annotations to project spans via the Python SDK.

Transforms rough drafts, vague ideas, or task descriptions into polished, ready-to-send prompts for any LLM chat interface, with no placeholders or templates.

Verify supply chain integrity for AI agent plugins, tools, and dependencies by generating SHA-256 manifests, detecting tampered files, auditing dependency pinning, and enforcing promotion gates.

Audit MCP server configurations for security issues including secrets exposure, shell injection, unpinned dependencies, and unapproved servers.

Adds Arize AX tracing to LLM applications using a two-phase agent-assisted flow that analyzes the codebase before implementing instrumentation.

Diagnoses and improves Qdrant search relevance by isolating embedding model, configuration, or query strategy issues.

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks, scanning for controls and generating a compliance report.

Generates a Playwright test from a user-provided scenario by recording browser interactions via Playwright MCP, then saves and runs the test until it passes.

Analyzes and optimizes DAX formulas for better performance, readability, and maintainability in Power BI.

Generate a complete, production-ready MCP server project in Ruby using the official MCP Ruby SDK.

Generates complete, copy-paste ready implementation documentation from a PR plan, including code blocks and verification checklists.

Generates a complete MCP server implementation optimized for Microsoft Copilot Studio, including Power Platform connector schema, custom C# logic, and deployment configuration.

Govern Power Automate flows and Power Apps at scale by classifying business impact, detecting orphaned resources, auditing connectors, enforcing compliance, and computing archive scores — all without Dataverse or the CoE Starter Kit.

Extracts protocol message flow from source code, RFCs, academic papers, pseudocode, or formal models (ProVerif/Tamarin) and generates Mermaid sequence diagrams with cryptographic annotations.

Generate songs, instrumental tracks, and covers using the MiniMax Music API with basic or advanced control modes.

Authenticate AI agents with services using ERC-8004 onchain identity via Sign-In With Agent (SIWA).

Build Django web applications and REST APIs with Django REST Framework, including models, serializers, viewsets, authentication, and testing.

Write, optimize, and debug Apache Spark jobs for high-performance distributed data processing, ETL pipelines, and big data workloads.

Designs, optimizes, and evaluates prompts for LLMs, including structured outputs, chain-of-thought, and evaluation frameworks.

Write robust, maintainable end-to-end tests with Playwright using Page Object Model, proper selectors, auto-waiting, and debugging workflows.

Integrate 250+ AI models into JavaScript/TypeScript apps with streaming, file uploads, and agent tooling.

Generate videos with synchronized audio using ByteDance Seedance 2.0 via the inference.sh CLI, supporting text-to-video, image-to-video, and reference-to-video modes up to 1080p.

Generate images with Google Gemini native image models via the inference.sh CLI, supporting text-to-image, image editing, multi-image input, and various output options.

Convert text to natural speech using multiple TTS models via the inference.sh CLI, with support for emotion steering, voice cloning, and multi-speaker dialogue.

Generate AI avatar and talking head videos using inference.sh CLI with models like P-Video-Avatar, OmniHuman, Fabric, and PixVerse.

Remove backgrounds from images using BiRefNet and edit them with Reve via the inference.sh CLI.