Results for “pr”

Automate Amazon ASIN data lookups and operations through the Asin Data API toolkit via Rube MCP, with dynamic tool discovery and connection management.

Process and analyze large tabular datasets (billions of rows) that exceed available RAM using lazy, out-of-core DataFrames with fast aggregations, visualization, and machine learning integration.

Build and train graph neural networks with PyTorch Geometric, covering node/link/graph classification, message passing layers, heterogeneous graphs, and custom datasets.

Assess and implement the CISA Zero Trust Maturity Model v2.0 across identity, devices, networks, applications, and data pillars to achieve progressive zero trust maturity.

Generate images from text prompts, perform image-to-image translation, inpainting, and build custom diffusion pipelines using Stable Diffusion models via HuggingFace Diffusers.

Model complex UI behavior as finite state machines with states, events, and transitions to eliminate impossible states and make behavior predictable.

Guides the creation of high-quality MCP servers that let LLMs interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation.

Automates the full lifecycle of agent skills: extracts reusable constraints from user feedback, merges preferences with version bumps, and retrieves relevant skills for new tasks.

Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.

Designs and implements big data architectures, processes large-scale datasets with distributed systems, and optimizes data pipelines for throughput using Hadoop, Spark, and cloud platforms.

Use when data operation or statistical analysis tasks do not need full program implementation, and the agent should operate Insyra through CLI/REPL, .isr scripts, or DSL workflows, including environment workflows, reproducible command pipelines, and command selection guidance.

Execute Claude Code commands in the telegram_agent project directory. Use when the user wants to work on the telegram agent itself, fix bugs, add features, or modify the bot code. This is a COMMAND HANDLER, not a script executor.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Agent profile for design AI/ML features, retrieval, model calls, structured outputs, cost controls, evals, and fallbacks. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Agent profile for design and implement backend services, API logic, data access, jobs, auth boundaries, and error handling. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Runs a nightly automated retrospective on autonomous trading strategy performance, computing win rates, fee drag, holding period buckets, direction bias, and producing data-driven improvement suggestions.

This skill should be used when the user asks about "Bankr API", "Bankr Agent API", "how does Bankr work", "Bankr job status", "Bankr response format", or "building on Bankr". Provides endpoint documentation, job patterns, and TypeScript interfaces.

This skill should be used when building the async job workflow, implementing polling loops, handling job status transitions, processing rich data, managing conversation threads, or understanding the full submit-poll-complete lifecycle of the Bankr Agent API.

Design a document set for a document-based lesson — selecting and sequencing sources for analytical tension around a central question. Use when assembling sources for a new lesson or when an existing set produces flat responses.

Drive a planned change to 100% coverage across an entire codebase when a prior agent run stopped early. Use whenever a refactor, migration, rename, rule-application, or sweeping edit was planned and partially executed but left incomplete — i.e.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key. Use when: the user needs model routing, provider setup, or Chinese LLM access guidance.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Publish and manage research papers on Hugging Face Hub, including creating paper pages, linking papers to models and datasets, claiming authorship, and generating professional markdown-based research articles.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Build video analytics pipelines using NVIDIA DeepStream SDK 9.0 with Python pyservicemaker API, including GStreamer-based video processing, TensorRT inference integration, object detection/tracking, and Kafka/message broker integration.

Performs deep root cause analysis on NVIDIA TAO Visual ChangeNet classification experiments, using image-evidence-driven investigation to diagnose model failures and produce actionable reports.

Prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.