AI & LLM Engineering

對 OpenSpec、Git Diff、frontend、bff、backend、LangGraph、Tool、MCP 與安全邊界進行獨立唯讀審查，輸出 Blocker、Major、Minor 與標準 Verdict。

HsienW/chat-gun

Pin this Codex session to a specific model through the Weave Router.

weave-os/router

Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events.

ascend-ai-coding/awesome-ascend-skills

A skill your agent uses when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt…

NeoLabHQ/context-engineering-kit

Diagnose and fix OCI AI Quick Actions (AQUA) issues including deployment failures, OOM errors, authorization problems, capacity issues, container errors, and policy misconfigurations.

oracle/accelerated-data-science

Find the nearest defender-winning, ASR claim-valid game backward in a WIP-1006 lineage for the proposer and defender recovery-parent flag.

worldcoin/world-chain

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs.

davila7/claude-code-templates

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache…

davila7/claude-code-templates

Check official docs when framework APIs or configuration may be version-sensitive.

KbWen/agentic-os

Expertise in MLIR (Multi-Level Intermediate Representation) and CIR (Clang IR) development for domain-specific compilation and high-level optimizations.

aftermathlabs/llvm-msvc

Creates or changes a druxt.js contributor skill in .agents/skills, with its evals and the tests that gate it.

druxt/druxt.js

A skill your agent uses when draft eval criteria need refining, clustering, and acceptance into the published goldset with an isolated holdout split (goldset.md + goldset.json).

tikalk/adlc-team-skills

Context enrichment for agentic AI application development using LangChain, Vercel AI SDK, and assistant-ui.

rsmdt/the-startup

Add support for a new HuggingFace MLX model to AFM. An agent skill from scouzi1966/maclocal-api.

scouzi1966/maclocal-api

INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents.

langchain-ai/langchain-skills

When you need to call a service the org has a SHARED credential for (a SERP/search key, a paid-API key, a data-vendor feed, a Git remote) — and the platform has told you that credential is available…

yc-software/qm

A skill your agent uses when Token Meter changes or claims need independent source, test, runtime, native, browser, privacy, or platform verification.

splunk/token-meter

Create and test DashClaw guard policies for agent governance

ucsandman/DashClaw

OpenInference semantic conventions and instrumentation for Phoenix AI observability.

github/awesome-copilot

Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script tag or npm package and lets end-users of your site drive the UI with…

Tommy-yw/RunbookHermes

Oracle Enterprise AI guidance for building, deploying, securing, estimating cost for, and integrating AI models, agents, RAG, Responses API workflows, custom or imported models, fine-tuning, model…

oracle/skills

Start, validate, debug, and stop an AReno OpenAI-compatible serving endpoint.

inclusionAI/AReno

Guides creating and editing custom agents for the code-forge application as Markdown files with YAML frontmatter in the project's .forge/agents folder.

tailcallhq/forgecode

Builds a fused row-wise softmax kernel for Triton-Ascend that reads and writes each row once, handling padding, strides and masked loads on Ascend NPUs.

Krusty84/triton-ascend-agent-dev-kit

Checks every subagent prompt before spawning, swapping pasted files and context for paths and short summaries and trimming the brief, to avoid multiplied token cost.

LichAmnesia/lich-skills

Claude Code 設定 Gemini 免費 API。說「設定 Gemini」「Gemini API」時載入. An agent skill from mathruffian-dot/claude-code-lazy-packs.

mathruffian-dot/claude-code-lazy-packs

実 Claude API を叩く総合テスト（全カテゴリ）を実行する。リリース前ではなく、定期的に手動で回して回帰を検出するための skill。yarn dev が起動済みであることが前提。

receptron/mulmoclaude

Design or generate a two-player co-op game menu and opening animation from player names, title, style, and optional identity references.

vllm-project/vllm-omni

Upgrade vllm-omni NPU model runners (OmniNPUModelRunner, NPUARModelRunner, NPUGenerationModelRunner) to align with the latest vllm-ascend NPUModelRunner while preserving omni-specific logic.

vllm-project/vllm-omni

Runs deterministic byte-parity and paired performance campaigns for Dynamo offline KV-aware replay across native-G1 vLLM and SGLang configurations, including forced scheduler-pressure and…

ai-dynamo/dynamo

Summarize or extract text/transcripts from URLs, podcasts, YouTube videos, and local files using the summarize CLI.

swarmclawai/swarmclaw

Expert in designing and building autonomous AI agents. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more.

microsoft/ai-agents-for-beginners

A skill your agent uses when implementing enter and format monetary values.

thedaviddias/ux-patterns-for-developers

Author ComfyUI-LoRA-Manager nodes from the panel. An agent skill from artokun/comfyui-mcp.

artokun/comfyui-mcp

Maintain DomoDomo private local AI features, Ollama connections, browser inference, streaming UX, embeddings, RAG, memory, and agent interfaces.

darknecrocities/DomoDomo---All-in-one-Tool

Train or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.

henryalouf/ruflow

Build voice AI agents with ElevenLabs. An agent skill from elevenlabs/skills.

elevenlabs/skills

Optimize a vague subagent brief into a structured Agent task brief carrying falsifier, invariant, source-citation rule, and concrete-noun anchors.

Cranot/roam-code

Optimize dense matrix multiplication (GEMM) kernels in Triton for NVIDIA and AMD GPUs.

ZJLi2013/awesome-kernel-skills

A standardized CLI wrapper for Uni-Mol molecular ML workflows that handles representation extraction (embeddings), model training (regression/classification), and property prediction with built-in…

jinzhezenggroup/computational-chemistry-agent-skills

Provider-independent production workflow for agents assembling, auditing, executing, and handing off ComfyUI node-graph workflows for image, video, upscale, inpaint, conditioning, and batch media…

calesthio/generative-media-skills

Reference documentation for the Airbyte per-connector typed SDK packages

airbytehq/airbyte-agent-sdk

Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.

openai/openai-guardrails-js

Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server.

vllm-project/vllm-skills

Create or update Plate docs with conversational voice, lane-aware structure, explicit ownership, and code-backed accuracy.

udecode/plate

Search memory using qmd (BM25 + optional vector) and compaction tree traversal.

kevin-hs-sohn/hipocampus

Guidance for improving the Windmill AI chat (copilot), especially global mode — tools, prompts, and context-window discipline.

windmill-labs/windmill