AI & LLM Engineering

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

parcadei/Continuous-Claude-v3

포트폴리오 최적화 스킬. An agent skill from thesun4sky/jobstack.

thesun4sky/jobstack

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

davila7/claude-code-templates

A skill your agent uses when adding interactive 3D scenes from Spline.design to web projects, including React embedding and runtime control API.

sickn33/agentic-awesome-skills

Builds focused, single-purpose Stimulus controllers for progressive enhancement.

dilolabs/nosia

A skill your agent uses when integrating Google Gemini API into projects.

sickn33/agentic-awesome-skills

A skill your agent uses when improving prompts for any LLM. An agent skill from sickn33/agentic-awesome-skills.

sickn33/agentic-awesome-skills

Build a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI.

sickn33/agentic-awesome-skills

Validate the Dear Agent TXT input, approval and artifact delivery loop.

ljxpython/ai-agent-platform

Build custom LLM evaluation pipelines using the OpenJudge framework.

agentscope-ai/OpenJudge

do e2e tests, run e2e, validate feature, prove it works, PR proof, frame proof, pnpm evals.

Devin-AXIS/iPolloWork

Manages AI content generation for the ComfyUI template site.

Comfy-Org/workflow_templates

A skill your agent uses for ServiceRadar Elixir, Phoenix, LiveView, Ash/Ecto, migrations, external downloads, Hex dependencies, formatting, or Dialyzer work.

carverauto/serviceradar

Deploy and operate production agent servers with LangSmith Deployment.

soba-labs/langchain-agent-skills

Add a Swarmauri plugin package under pkgs/plugins. An agent skill from swarmauri/swarmauri-sdk.

swarmauri/swarmauri-sdk

A skill your agent uses when the user asks to "check zero-shot", "audit few-shot anchoring", "find example anchoring", or invokes /zero-shot.

jongwony/epistemic-protocols

Run, extend, debug, or review the public edge-e3 bare-metal software harness, including encrypted Verilator builds, hello and tensor examples, all example/llama/model smoke cases, PyTorch BF16…

exeex/edge-cores

A skill your agent uses when composing factcheck or research prompts — IFCN 원칙 기반 검증 워크플로우와 일반 리서치 템플릿을 담은 레퍼런스의 라우팅 인덱스.

treylom/prompt-engineering-skills

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations.

github/awesome-copilot

Debug LLM applications using the Phoenix CLI. An agent skill from github/awesome-copilot.

github/awesome-copilot

📝 Prompt Library workflow skill. An agent skill from diegosouzapw/awesome-omni-skills.

diegosouzapw/awesome-omni-skills

Agent SDK task integration patterns for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection.

javiarmesto/ALDC-AL-Development-Collection

Design system conventions for the Phoenix frontend — layout, dialogs, error display, BEM CSS class naming, and CSS design tokens.

Arize-ai/phoenix

Guide for the phoenix-otel TypeScript package — OTel registration, stack-based global provider management, and provider lifecycle.

Arize-ai/phoenix

REST API development for Phoenix. An agent skill from Arize-ai/phoenix.

Arize-ai/phoenix

Create a LangChain docs integration listing from a structured GitHub issue submission (issue form fields as JSON).

langchain-ai/docs

A skill your agent uses whenever the user asks for a graphical abstract, mechanism illustration, study design schematic, concept explainer, scientific cover art, or any non-data academic image that…

Citrus-bit/Anaxa

Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets.

K-Dense-AI/scientific-agent-skills

把基于 prompts/ 主源的 skill 打包成断网单机可用的离线提示词包。Use when the user wants to export/package offline prompts for disconnected hosts (WebUI、Qwen、AnythingLLM、Claude.ai), generate self-contained systemprompt /…

zhaohui-yang/official-document-drafting

Transcribes a single PCM16 WAV file to plain UTF-8 text locally through a standard-library Python wrapper around native SenseVoice Small F16 GGUF FunASR llama.cpp runtimes, preferring cross-vendor…

godot-fun/gai

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.

sickn33/agentic-awesome-skills

Curated upstream guidance for Huggingface Community Evals; use when the workflow matches the user goal.

sickn33/agentic-awesome-skills

Documentation and capabilities reference for Daily. An agent skill from sickn33/agentic-awesome-skills.

sickn33/agentic-awesome-skills

UiPath API Workflow assistant — author, run, validate, package, publish, deploy, and troubleshoot JSON workflows for uip api-workflow.

UiPath/skills

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

RightNow-AI/openfang

Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps

RightNow-AI/openfang

Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization

RightNow-AI/openfang

Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies

RightNow-AI/openfang

A skill your agent uses when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform.

google/skills

Configure the shared guard against catastrophic shell commands in local AI agents.

davidondrej/skills

Write four distinct prompts for AI image models. An agent skill from davidondrej/skills.

davidondrej/skills

A skill your agent uses when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks.

vibeeval/vibecosystem

Update tools/scripts/generatebinarybuildmatrix.py when a PyTorch release goes live.

pytorch/test-infra

Andrej Karpathy 视角顾问。以 Karpathy 的心智模型和工程师式判断，为 AI 产品经理场景做分析。

SpaceZephyr/career.skill

Starter: frame a decision as a multi-model debate — picks sides, seats providers, and launches /octo:debate with a well-formed motion

nyldn/claude-octopus

Starter: one-screen provider health summary — availability, auth method, version drift, and cost posture for every seatable provider

nyldn/claude-octopus

Rerank retrieved passages by whether each one answers the question, drop the near-misses before they reach the prompt, and check every citation in the answer against the passage it points at.

mrmps/classifier-dev

The ComfyUI node map — which node lives in which standalone repo vs in-tree under customnodes/, where each is symlinked, and the vendor-sync rule for the vendor/ subsets.

sorryhyun/anima_lora