AI & LLM Engineering · DeepSeek

Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.

liustack/modlens

Provides context about the CoStrict evals system structure in this monorepo.

zgsm-ai/costrict

Stands up the Weave model router in Docker Compose and drives it with claude -p against a real or mocked upstream to reproduce and verify routing and streaming behavior.

weave-os/router

Diagnose and configure MemSearch memory behavior. An agent skill from zilliztech/memsearch.

zilliztech/memsearch

TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK.

trypostit/trypost

Plans and audits Day-0 SGLang support for a new model release: scope, architecture gaps, PR order, validation gates and sanitized public evidence.

BBuf/AI-Infra-Auto-Driven-SKILLS

Turn workflows from your MemSearch memory into reusable skills.

zilliztech/memsearch

A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

MigoXLab/dingo

Benchmark a third-party coding-agent harness against FrontierHarness Eval using Runta runtimes.

frontier-harness-eval/eval

LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic.

bitsky-tech/bridgic

Search and recall relevant memories from past sessions via memsearch.

zilliztech/memsearch

Adapt and port new LLM model architectures to this xinfer project.

guoqingbao/xinfer

Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images.

xiincs/claude-code-vision-skill

Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.

BBuf/AI-Infra-Auto-Driven-SKILLS

The user asks a question about a video that was already watched or indexed — "what did they say about X", "what error code appears", "what happens at 2:30", "does the video show Y".

oxbshw/watch-skill

DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw.

dongsheng123132/u-claw

Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares).

zhongkaifu/TensorSharp

用于在 cc-router 仓库新增一个 LLM provider（即在 src-tauri/providers/ 下添加 YAML 描述符并完成配套的同步改动）。当用户说「加 provider」「接入 XX 厂商」「新增订阅源」「provider YAML」「让 cc-router 支持 OpenRouter/Together/Groq/Ollama 之类」时必须触发本…

finch-xu/cc-router

Search and recall relevant memories from past sessions via memsearch.

zilliztech/memsearch

The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models.

oxbshw/watch-skill

Helps show a model provider's usage, balance or quota in PiDeck: checks built-in support, points to the dialog templates, or writes a custom probe entry.

ayuayue/PiDeck

Add new LLM model pricing entries to Litefuse's default-model-prices.json.

litefuse/litefuse

Guidance for using the MMSP Python SDK (mmsp). An agent skill from Prism-Shadow/model-message-stream-protocol.

Prism-Shadow/model-message-stream-protocol

Interact with a Meshtastic LoRa mesh network through MESH-API — list nodes, read messages, send texts, and check connection status.

mr-tbot/mesh-api

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).

Orchestra-Research/AI-Research-SKILLs

Walks through aligning language models with SimPO, a reference-free preference optimization method, using accelerate configs for Mistral 7B, Llama 3 8B and math-focused models.

Orchestra-Research/AI-Research-SKILLs

Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.

Orchestra-Research/AI-Research-SKILLs

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.

mydisha/keirouter

Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action…

Bald0Wang/DeepSeek-Oracle

Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.

amd/skills

Guidance for using the MMSP TypeScript SDK (@prismshadow/mmsp).

Prism-Shadow/model-message-stream-protocol

Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.

mydisha/keirouter

Minimize token consumption & maximize prompt cache hit rate.

lokikill123/codex-token-skills

The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a…

oxbshw/watch-skill

Describes ClawRouter, a local proxy that forwards each LLM request to the blockrun.ai gateway, which routes to a cheaper capable model, paid by USDC wallet or API key credit.

BlockRunAI/ClawRouter

How to dispatch well — choosing flash vs pro, writing self-contained briefs, parallelism, verifying results, and guardrails

ZSeven-W/dsh-crew

Has several open-weight models answer a question, rank each other's anonymized answers, then lets a chairman model write the final response through Fireworks AI.

dair-ai/dair-academy-plugins

Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models.

yzlnew/infra-skills

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime.

Orchestra-Research/AI-Research-SKILLs

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace.

Orchestra-Research/AI-Research-SKILLs

Add new AI models to Kiln's mlmodellist.py and produce a Discord announcement.

Kiln-AI/Kiln

The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's…

oxbshw/watch-skill

This skill should be used when users want to route LLM requests to different AI providers (OpenAI, Grok/xAI, Groq, DeepSeek, OpenRouter) using SwiftOpenAI-CLI.

jamesrochabrun/skills

Breaks LLM torch profiler traces down by forward pass, layer and kernel, with timing tables and Perfetto time ranges for the layers you want to inspect.

BBuf/AI-Infra-Auto-Driven-SKILLS

Set up the minimal set of artifacts (tokenized DCLM corpus shard + released HuggingFace checkpoint converted to DCP) required to benchmark, profile, or regression-test a MoE model in PithTrain.

mlc-ai/pith-train

Persistent global memory across conversations. An agent skill from lokikill123/codex-token-skills.

lokikill123/codex-token-skills

Add or verify a model's chat prompt rendering and tokenization in rust/sglang-processor so it matches SGLang's Python serving path exactly (same prompt text, same token ids).

sgl-project/sglang

LangChain / LangGraph engineering pitfalls and verified fixes.

ob-labs/agentseek