AI & LLM Engineering

Capture Claude Code interaction trajectories in training-friendly formats.

AlexAI-MCP/hermes-CCC

Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and…

Arize-ai/phoenix

Find out what is going wrong in LLM or agent traffic by reading sampled Phoenix traces, spans, or sessions, writing free-form notes (open coding), then grouping the notes into a few narrow…

Arize-ai/phoenix

Create Phoenix release documentation grounded in actual code changes.

Arize-ai/phoenix

Add or modify speech-to-text providers in assistant-api with transport-aware ingestion (WS/SDK/HTTP), transcript packet correctness, and UI/provider wiring.

rapidaai/voice-ai

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders).

microsoft/GitHub-Copilot-for-Azure

当目标为 LLM 应用/Chatbot/智能客服/AI 助手/Copilot/Agent/RAG 知识库/多模态模型，或发现用户输入进入大模型提示、工具调用、知识库检索、对话记忆、文件解析，或需要测试提示词注入/越狱逃逸/System Prompt 泄露/训练数据与敏感信息泄露/RAG 检索污染/Agent 记忆污染/工具滥用与命令执行/SSRF/沙箱逃逸时调用。负责 OWASP LLM…

zhaji2333/CkSKILLS

Feynman Technique for deep learning—explain a concept simply, identify gaps, fill them, then refine.

neurofoo/agent-skills

A skill your agent uses when exploring an unfamiliar codebase, tracing code paths, or answering questions about how the system works.

aiming-lab/MetaClaw

Generate an A2A agent card JSON by analyzing agent source code in a folder or GitHub URL.

agentic-community/mcp-gateway-registry

Build private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp.

dpearson2699/swift-ios-skills

Claude Codeセッションの正式な評価フレームワークで、評価駆動開発（EDD）の原則を実装します. An agent skill from affaan-m/ECC.

affaan-m/ECC

평가 주도 개발(EDD) 원칙을 구현하는 Claude Code 세션용 공식 평가 프레임워크. An agent skill from affaan-m/ECC.

affaan-m/ECC

分析原始提示，识别意图和差距，匹配ECC组件（技能/命令/代理/钩子），并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机：当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发：“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机：当用户希望直接执行任…

affaan-m/ECC

Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs…

amd/skills

A skill your agent uses when certifying mesh-llm KV/cache stability under repeated OpenAI tool-call loops, same-prefix cache reuse, suffix-prefill limits, or native Skippy slot/decode/eviction…

Mesh-LLM/mesh-llm

Reference for launching jobs inside a SLURM allocation via srun (single-node or multi-node).

mlc-ai/pith-train

查询全球任意城市的实时天气和未来天气预报。当用户提到天气、气温、降雨、湿度、风力、穿衣建议、出行建议等天气相关话题时使用此技能。支持中英文城市名。例如：'北京天气怎么样'、'明天上海会下雨吗'、'Tokyo weather forecast'、'这周末适合户外活动吗'。

AgentTeam-TaichuAI/ScienceClaw

NCS(국가직무능력표준) 역량 매핑 스킬. An agent skill from thesun4sky/jobstack.

thesun4sky/jobstack

Implements the state-as-records-not-booleans pattern for rich state tracking.

dilolabs/nosia

Gera imagens em paralelo via OpenRouter a partir de um pedido simples ou de um batch com prompts e filenames definidos.

rtadewald/skills

Automatically evaluate and compare multiple AI models or agents without pre-existing test data.

agentscope-ai/OpenJudge

A skill your agent uses when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory…

soba-labs/langchain-agent-skills

A skill your agent uses when designing, refactoring, or debugging Formax system prompt assembly, system-reminder injection, or skills/deferred-tool prompt exposure semantics; mandatory for any…

yusifeng/formax

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and…

Orchestra-Research/AI-Research-SKILLs

Oracle second-model review: bundle prompts/files, debug, refactor, design.

steipete/agent-scripts

Add an experimental standalone Swarmauri package under pkgs/experimental.

swarmauri/swarmauri-sdk

Develop and profile the edge-e3 PyTorch-to-NNC flow, including nnc/compiler.py lowering and generated ABI, example/llama smoke models, cpp/libnn runtime operators, BF16 correctness checks, and…

exeex/edge-cores

A skill your agent uses when composing prompts targeting GPT-6 Sol (GPT 디폴트), GPT-6 Astra, GPT-6 Luna, GPT-5.6 Sol (직전 디폴트), legacy GPT-5.5/5.4/5.2 — lean outcome-first 7블록 규칙 + LEGACY 섹션(구 XML 스택)을…

treylom/prompt-engineering-skills

Wires xAI's Grok speech-to-text into an app you already have, covering voice input for a message box, captions shown as people talk and batch transcription of audio files.

cursor/plugins

Wires xAI's Grok voice synthesis into an app you already have, so assistant replies get a play button, optional automatic playback, or narration of any text.

cursor/plugins

Browse, filter, and explore a curated library of 2,500+ AI prompts organized by 19 categories, 17 models, and 4 output types.

AgriciDaniel/claude-prompts

Returns typed answers from a decision model, such as a category choice, a score on a labeled scale or a probability, each with confidence, for routing and grading tasks.

YaoApp/yao

Trace, evaluate, and deploy AI agents and LLM applications with LangSmith.

langchain-ai/docs

追蹤並計算當前 session 的 Token 使用量和花費（USD）。產出前後對比報告，幫助使用者了解 workspace 優化的實際效益。

zeuikli/claude-code-workspace

Build production computer vision pipelines for object detection, tracking, and video analysis.

curiositech/some_claude_skills

Tear down a competitor's repo or product into a feature inventory and adoption choices.

boshu2/agentops

Full-stack diagnostic for agent and LLM applications. An agent skill from affaan-m/ECC.

affaan-m/ECC

Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.

affaan-m/ECC

Map a described workflow to the right ECC command group with run-order and stop condition, or browse all command-group recipe families read live from the commands directory.

affaan-m/ECC

Patient safety evaluation harness for healthcare application deployments.

affaan-m/ECC

Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately…

affaan-m/ECC

Use the repo internal/ directory for anything that must not be committed — scratch files, temporary outputs, local demos, Codex artifacts, or one-off scripts.

albumentations-team/AlbumentationsX

A skill your agent uses when defining or enforcing output formatting standards for agent responses in WrongStack.

WrongStack/WrongStack

Required when reviewing, updating, auditing, or creating any concept documentation page.

MicrosoftDocs/semantic-kernel-docs

This skill should be used when a specific quality problem (UX, data, architecture, feature) needs systematic diagnosis and iterative fixing toward a defined target.

jacob-dietle/context-os

Adds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern.

agentsope/SkillAlchemy

A skill your agent uses when working near production, sensitive systems, or destructive operations.

garagon/nanostack