DeepSeek · For developers

Dispatch copy-lead helpers: Tavily, Codex luna/terra, grok/X, OpenCode DeepSeek, Cursor Grok 4.6 medium-fast.

VKirill/claude-lane-stack

Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.

AnastasiyaW/codex-claude-code-config

A skill your agent uses when you need to run a chat, a CLI session, or a subagent on a specific setup — any model you pay for inside any harness (e.g.

arul28/ADE

Installs OpenCode as an optional NanoClaw agent runtime, reaching OpenRouter, OpenAI, Google, DeepSeek and others through OpenCode's own configuration.

nanocoai/nanoclaw

A Watch Skill command failed, video download broke, ffmpeg or yt-dlp is missing, a provider returned an error, local vision stopped, or the user asks "why can't it watch this" or "repair my setup".

oxbshw/watch-skill

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

davila7/claude-code-templates

Write, optimize, and debug high-performance AI compute kernels using TileLang (a Python DSL for GPU programming).

yzlnew/infra-skills

Report local Claude, Codex, Cursor, GitHub Copilot, Grok, Kimi, Z.AI, Alibaba, OpenCode Go, Antigravity, Command Code, MiniMax, MiMo, DeepSeek, OpenRouter, ElevenLabs, Devin, Muse, and Higgsfield…

kunchenguid/quota-axi

A skill your agent uses when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality…

Zhou-Yujing114514/deepseek-harness-linux

YouTube 视频 → 下载 → 转录 → 翻译 → 存为 Markdown. An agent skill from chubbyguan/chubbyskills.

chubbyguan/chubbyskills

One-shot chat completion against DeepSeek's deepseek-chat model via the OpenAI-compatible /v1/chat/completions endpoint.

ruvnet/ruflo

开发、维护、分发和验证 DeepSeek Harness (DSH) 插件的执行型 Skill。覆盖 host/client 形态判断、bundle/profile 契约、Service 与函数插件、工具、HTTP、持久化、slot、Conversation Node、客户端构建、HMR、GitHub 安装和真实组合验证。

NanmiCoder/dsh-auto-mode

Audit the DeepSeek V3 MPK demo + builder chain end-to-end and confirm logical equivalence with vLLM's reference implementation.

mirage-project/mirage

RD-Agent A股因子挖掘端到端流水线：环境 preflight → 启动演化 → 轮询完成 → 批量回测评估 → IC/Sharpe 排序 → explain 解读 → export 入库 → Markdown 报告。在 QuantBot / Claude Code 中挖因子时使用，一条命令跑完整流程。触发词：挖因子、因子挖掘、挖新因子、因子演化、RD-Agent、alpha…

qusong0627/QuantMind

Collect critical feedback from all registered LLMs on an artifact (architecture doc, implementation, plan).

raine/consult-llm

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.).

google/skills

Code review closeout for Claude Code, Codex, OpenCode, DeepSeek TUI, and Antigravity CLI: local dirty changes, branch vs main, parallel tests.

smallnest/goal-workflow

High-throughput LLM inference on NVIDIA GPUs. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Sets up and maintains isolated Claude Code CLI profiles to run Kimi, MiniMax, DeepSeek, GLM, StepFun or Anthropic in separate terminal windows.

daymade/claude-code-skills

A skill your agent uses when developing Node.js backend services or CloudBase cloud functions (Express/Koa/NestJS, serverless, backend APIs) that need AI capabilities.

LeoYeAI/openclaw-master-skills

A skill your agent uses when developing browser/Web applications (React/Vue/Angular, static websites, SPAs) that need AI capabilities.

LeoYeAI/openclaw-master-skills

A skill your agent uses when developing WeChat Mini Programs (小程序, 企业微信小程序, wx.cloud-based apps) that need AI capabilities.

LeoYeAI/openclaw-master-skills

UserPromptSubmit hook pattern that classifies prompts into six cost tiers and delegates to external model CLIs

alinaqi/maggy

9-tier model routing system with cascading classifier fallback and result auto-evaluation

alinaqi/maggy

Low-memory file2file quantization for very large safetensors LLMs that cannot be loaded whole.

amd/Quark

Inspect a target model and prepare metadata for Quark PTQ planning.

amd/Quark

Personal AI Operating System on Base. An agent skill from BankrBot/skills.

BankrBot/skills

Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both lanes, price from…

rlaope/oh-my-hermes

当用户需要生成 GEO 品牌对比内容、品牌替代方案、选型页、竞品对比页、FAQ 对比问答或“某品牌和其他方案怎么选”的内容包时使用，面向 DeepSeek、豆包、千问、Kimi、腾讯元宝生成中文简体、证据绑定、同口径、公平表达的品牌对比报告，并默认交付 Word、PDF、HTML、Markdown 四格式。

yaojingang/yao-geo-skills

A skill your agent uses when designing a GEO Signal Monitor, AI answer monitoring system, citation tracking plan, brand-fact correction loop, GEO monthly report, alert rules, dashboard fields, or…

yaojingang/yao-geo-skills

当用户需要系统、详细、完整地生成一篇可发布的 GEO 科普文章，并附带 How-to 教程、概念解释、购买/选择指南、避坑清单、FAQ、术语表、证据分级、读者场景、决策路径、品牌自然植入建议、真实数据核验附录，以及带固定目录菜单的 HTML 包、Word、PDF 和 Markdown 四格式报告时使用；适配 Kimi、千问、豆包、DeepSeek、元宝等国内 AI…

yaojingang/yao-geo-skills

当用户需要基于品牌 Brief、选题配置、关键词、竞品库和可信来源生成 GEO 榜单评测文章、best/top/alternatives/vs/persona/use-case 意图内容、评选方法、核心对比表、榜单正文、适合人群、FAQ、来源表和 Word/PDF/HTML/Markdown 四格式文章包时使用；适配…

yaojingang/yao-geo-skills

This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax.

dosco/aithy

vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU.

ascend-ai-coding/awesome-ascend-skills

Track daily PRs and Issues from vllm-project/vllm and vllm-project/vllm-ascend, filter by model (DeepSeek/Qwen/GLM/MiniMax/Kimi) and tech topics (PD disaggregation, MTP, quantization, graph mode…

ascend-ai-coding/awesome-ascend-skills

Deploy and maintain image understanding (OCR + local VLM + cloud VL) and image generation for Codex connected to text-only models like DeepSeek.

aiskillstore/marketplace

A skill your agent uses when calling open-weight LLMs on Together AI or Fireworks AI's OpenAI-compatible endpoints — baseurl plus namespaced model id, the cheapest model that clears the bar…

ericrisco/rsc-harness

Autonomous research review loop using any OpenAI-compatible LLM API.

AI4Scientist/nano-scientist

Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

昇腾 NPU 平台 vLLM 大模型推理服务一键部署。触发：用户说'部署 模型名'、'NPU 部署模型'、'vllm serve'。流程：SSH检查 → NPU检查 → 配置发现(必须验证) → 用户确认 → 部署 → cron监控 → 验证。约束：(1) 配置必须从官方文档验证，禁止猜测；(2) 后台启动必须用cron监控，禁止手动轮询。支持…

ascend-ai-coding/awesome-ascend-skills

Select appropriate Ollama models for processing sensitive but legal content.

divinevideo/divine-mobile

A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping.

ericrisco/rsc-harness

Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window.

sundial-org/awesome-openclaw-skills

Reference guide for permanent free-tier LLM APIs with rate limits, model lists, and OpenAI-compatible integration patterns.

LeoYeAI/openclaw-master-skills