AI & LLM Engineering · Python

Render the provided prompt template with Jinja context and send it to the active NPC's LLM.

NPC-Worldwide/npcpy

Profile ExecuTorch model execution. Use when measuring performance, analyzing operator timing, or debugging slow models.

pytorch/executorch

Lists ComfyUI node data types, from IMAGE, MASK and LATENT tensors to model types, with their V3 classes and formats.

jtydhr88/comfyui-custom-node-skills

Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate).

CVCUDA/CV-CUDA

Recover from GPU-busy / GPU-unavailable failures. An agent skill from facebookexperimental/triton.

facebookexperimental/triton

Run offline Python (pydanticevals) or Node.js (logfire/evals) evaluations and review them in Logfire.

pydantic/skills

Design or review specx core scope boundaries in Python services.

maksimzayats/specx

Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.

amd/Quark

Fine-tune LLM models using LoRA on OCI AI Quick Actions (AQUA).

oracle/accelerated-data-science

A skill your agent uses when building an Aegis Stack plugin, a separate package (aegis-stack-<name) that renders files into a project through aegis add <name.

lbedner/aegis-stack

A skill your agent uses when user asks to analyze an image, describe image contents, or answer questions about a picture.

iflytek/iFly-Skills

Find and fix the docs and agent guidance that a branch makes stale - agent skills and their reference files, AGENTS.md and .agents/.md prompts, READMEs, docs/ folders, and code-adjacent docs that…

Kiln-AI/Kiln

Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

amd/skills

Migrate TypeScript Vercel AI SDK or Eve applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness.

pydantic/pydantic-ai

Initialize and configure LangGraph projects with proper structure, langgraph.json configuration, environment variables, and dependency management.

soba-labs/langchain-agent-skills

Add a second-class standalone Swarmauri package under pkgs/community.

swarmauri/swarmauri-sdk

Setup Sentry AI Agent Monitoring in any project. An agent skill from LiorVainer/data-israel.

LiorVainer/data-israel

Builds Agent-to-Agent (A2A) servers and clients following Google's open protocol for agent interoperability.

internet-court/internet-court-skill

Guide to writing JavaScript extensions for the ComfyUI frontend from custom nodes, covering lifecycle hooks, widgets, sidebar tabs, commands, settings, toasts and dialogs.

jtydhr88/comfyui-custom-node-skills

Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.

albumentations-team/albucore

Review a CV-CUDA operator's BENCHMARK coverage — drivers, layout axis, baselines, the basic-tier floor, row counts, and coverage statistics.

CVCUDA/CV-CUDA

Portuguese guide to building a retrieval-augmented generation assistant over a company's documents, with embeddings, section-based chunking, retrieval and a client workflow.

Hermes-brasil/hermes-brasil

Debug Triton compilation by dumping IR at each stage (TTIR, TTGIR, LLVM, PTX).

facebookexperimental/triton

Add Pydantic Logfire observability to application code — traces, logs, metrics, and AI/agent spans.

pydantic/skills

Install or verify the AMD Quark package and its dependencies.

amd/Quark

Builds Opik tracing integrations that live outside the Opik repository, either as standalone opik-* packages or as contributions into projects such as LiteLLM or Dify.

comet-ml/opik

Builds, updates and verifies integrations inside the Opik Python and TypeScript SDKs so users can trace a framework or provider with one call.

comet-ml/opik

Get a typed Python value back from an AG2 beta Agent instead of free text.

ag2ai/build-with-ag2

Anthropic Claude API 的 Python 和 TypeScript 使用模式。涵盖 Messages API、流式处理、工具使用、视觉功能、扩展思维、批量处理、提示缓存和 Claude Agent SDK。适用于使用 Claude API 或 Anthropic SDK 构建应用程序的场景。

loulanyue/awesome-claude-notes

给 FlashRec 引擎接入一个新模型架构（新的 HF checkpoint / 非 Qwen3 结构）。涵盖模型定义、权重合并加载、FP8 双路径、融合 kernel 接线、CUDA graph 兼容、精度校验、以及压测+trace 验证闭环。当用户要"增加/支持/接入新模型"时使用。

sohu-mptc/FlashRec

Oracle Database guidance for SQL, PL/SQL, SQLcl, ORDS, Oracle Vector SDK, administration, app development, performance, security, migrations, and agent-safe database workflows.

oracle/skills

Guidance for using A-Evolve to improve an AI agent automatically, evolving its prompts, skills and memory against a benchmark through solve, observe and evolve cycles.

Orchestra-Research/AI-Research-SKILLs

Shows how to log ML runs, configs, metrics and media with SwanLab and view them in cloud, local or self-hosted dashboards.

Orchestra-Research/AI-Research-SKILLs

Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.

Orchestra-Research/AI-Research-SKILLs

Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX…

dotnet/skills

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang.kernels JIT infrastructure and public operator groups

sgl-project/sglang

EdgeOne Makers platform development router — the single entry point for building, storing data, and deploying on Tencent EdgeOne Makers.

TencentEdgeOne/edgeone-makers-tools

A skill your agent uses when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, or maintained framework integrations, or when explaining Hermes Agent's…

NVIDIA/NeMo-Relay

Estimate peak GPU memory for a DualPipeV training run. An agent skill from mlc-ai/pith-train.

mlc-ai/pith-train

Design state schemas, implement reducers, configure persistence, and debug state issues for LangGraph applications.

soba-labs/langchain-agent-skills

Add or update a Swarmauri SDK core interface in pkgs/core/swarmauricore.

swarmauri/swarmauri-sdk

Audit documentation gaps across the Phoenix repo by analyzing recent commits to main (default: last 7 days).

Arize-ai/phoenix

Create a new built-in classification evaluator for Phoenix evals.

Arize-ai/phoenix

Generates onboarding code snippets for Phoenix tracing integrations and wires them into the project onboarding UI.

Arize-ai/phoenix

Bump the next release-please version for a Phoenix Python package (arize-phoenix, arize-phoenix-client, arize-phoenix-evals, arize-phoenix-otel) by opening a PR with a Release-As commit footer.

Arize-ai/phoenix

Audit recent changes to Phoenix's user-facing surfaces (Python clients, TypeScript clients, CLI, REST/GraphQL APIs) and patch the three external-facing agent skills — phoenix-tracing, phoenix-cli…

Arize-ai/phoenix

Scores news, announcements and macro events with the LLM, stores them in an event CSV and blends the decaying event signal with technical signals in signal_engine.py.

HKUDS/Vibe-Trading

Expert guidance on the Google Agent Development Kit (ADK) for Python.

cnemri/google-genai-skills