AI model or service
DeepSeek agent skills, page 6
DeepSeek skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 241 | Deepseek 联网搜索工具。一键调用 AI 联网搜索能力,快速获取实时信息。当用户需要使用 Deepseek 搜索、联网搜索、AI 搜索获取实时信息时使用。触发词:Deepseek搜索、deepseek websearch、联网搜索、AI搜索、ds搜索。 | redfox-data/ | 425 | — | ~539 | Automated safety check: Pass | No licence | 8 days ago |
| 242 | 242.Geo Analyzer GEO(生成式引擎优化)品牌分析工具。自动向豆包、Kimi、DeepSeek 三个 AI 搜索引擎提问,分析品牌在 AI 回答中的出现率、情绪、信源引用、竞品对比,生成交互式 HTML 报告。当用户需要分析品牌在 AI 搜索引擎中的表现、GEO 优化、AI 搜索品牌监测、品牌 AI 可见度分析时使用。触发词:GEO分析、品牌AI搜索分析、AI搜索引擎优化、品牌可见度、GEO、geo… | redfox-data/ | 425 | — | ~1.7k | Automated safety check: Pass | No licence | 8 days ago |
| 243 | Sets up and maintains isolated Claude Code CLI profiles to run Kimi, MiniMax, DeepSeek, GLM, StepFun or Anthropic in separate terminal windows. | daymade/ | 1.4k | — | ~11k | Automated safety check: Pass | MIT | today |
| 244 | 244.Tensorrt LLM High-throughput LLM inference on NVIDIA GPUs. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 125 | 1 repo | ~1.3k | Automated safety check: Pass | MIT | today |
| 245 | 245.Council Review Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing | alinaqi/ | 707 | — | ~756 | Automated safety check: Notes | MIT | 13 days ago |
| 246 | UserPromptSubmit hook pattern that classifies prompts into six cost tiers and delegates to external model CLIs | alinaqi/ | 707 | — | ~785 | Automated safety check: Pass | MIT | 13 days ago |
| 247 | 247.Model Routing 9-tier model routing system with cascading classifier fallback and result auto-evaluation | alinaqi/ | 707 | — | ~1.5k | Automated safety check: Pass | MIT | 13 days ago |
| 248 | 248.AI Model Nodejs 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. | majiayu000/ | 666 | 2 repos | ~1.7k | Automated safety check: Pass | MIT | today |
| 249 | 249.AI Model Web A skill your agent uses when developing browser/Web applications (React/Vue/Angular, static websites, SPAs) that need AI capabilities. | majiayu000/ | 666 | 2 repos | ~1.2k | Automated safety check: Pass | MIT | today |
| 250 | 250.AI Model Wechat 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. | majiayu000/ | 666 | 2 repos | ~1.4k | Automated safety check: Pass | MIT | today |
| 251 | 251.Mhc Algorithm Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. | benchflow-ai/ | 1.8k | — | ~1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 252 | 252.Aeo Check and improve your brand's visibility across AI search engines (ChatGPT, Perplexity, Gemini, Grok, Claude, DeepSeek). | gooseworks-ai/ | 1.2k | 1 repo | ~2.4k | Automated safety check: Notes | MIT | today |
| 253 | Low-memory file2file quantization for very large safetensors LLMs that cannot be loaded whole. | amd/ | 181 | — | ~2.3k | Automated safety check: Pass | MIT | 9 days ago |
| 254 | Inspect a target model and prepare metadata for Quark PTQ planning. | amd/ | 181 | — | ~2k | Automated safety check: Pass | MIT | 9 days ago |
| 255 | 255.Orlix Personal AI Operating System on Base. An agent skill from BankrBot/skills. | BankrBot/ | 1.2k | — | ~2.7k | Automated safety check: Pass | No licence | 2 days ago |
| 256 | Autonomous research review loop using any OpenAI-compatible LLM API. | AI4Scientist/ | 128 | 4 repos | ~1.8k | Automated safety check: Warn | No licence | 4 mo ago |
| 257 | 257.Model Onboarding 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/ | 3.2k | — | ~1k | Automated safety check: Notes | MIT | today |
| 258 | 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/ | 864 | — | ~988 | Automated safety check: Pass | MIT | 6 days ago |
| 259 | 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/ | 864 | — | ~799 | Automated safety check: Pass | MIT | 6 days ago |
| 260 | 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/ | 864 | — | ~635 | Automated safety check: Pass | MIT | 6 days ago |
| 261 | 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/ | 864 | — | ~681 | Automated safety check: Pass | MIT | 6 days ago |
| 262 | 262.Ax AI This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax. | dosco/ | 107 | — | ~8.2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 263 | 263.Deepseek Use DeepSeek's chat API: list models, run chat completions, check account balance. | Anil-matcha/ | 1.3k | — | ~1.1k | Automated safety check: Pass | MIT | 2 days ago |
| 264 | 264.Vllm Ascend vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. | ascend-ai-coding/ | 174 | — | ~2.7k | Automated safety check: Pass | No licence | today |
| 265 | 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/ | 174 | — | ~731 | Automated safety check: Pass | No licence | today |
| 266 | Deploy and maintain image understanding (OCR + local VLM + cloud VL) and image generation for Codex connected to text-only models like DeepSeek. | aiskillstore/ | 430 | — | ~814 | Automated safety check: Notes | MIT | today |
| 267 | 267.AI Chat Access 50+ LLM models through a unified OpenAI-compatible API via AceDataCloud. | majiayu000/ | 666 | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 268 | 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/ | 156 | — | ~3.3k | Automated safety check: Pass | MIT | today |
| 269 | 269.Deepseek Usage Check DeepSeek API usage (balance, this month's spending, token breakdown by model, daily breakdown, and cache hit rate). | OpenMinis/ | 440 | — | ~2.1k | Automated safety check: Pass | MIT | 2 days ago |
| 270 | 270.Cost Optimizer Smart cost optimization skill for OpenClaw. An agent skill from LeoYeAI/openclaw-master-skills. | LeoYeAI/ | 2.2k | — | ~7k | Automated safety check: Pass | MIT | 2 mo ago |
| 271 | Verify whether an AI agent's decision is well-reasoned before executing. | moonpay/ | 113 | — | ~833 | Automated safety check: Pass | MIT | 27 days ago |
| 272 | 272.Phx Investigate Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix. | oliver-kriska/ | 564 | — | ~1k | Automated safety check: Pass | MIT | 2 days ago |
| 273 | 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/ | 174 | — | ~1.2k | Automated safety check: Pass | No licence | today |
| 274 | Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. | sundial-org/ | 663 | — | ~1.6k | Automated safety check: Pass | No licence | 7 mo ago |
| 275 | Select appropriate Ollama models for processing sensitive but legal content. | divinevideo/ | 265 | — | ~1.3k | Automated safety check: Pass | MPL-2.0 | today |
| 276 | 276.Qiuzhi2046 Skill 秋芝2046(前产品经理,AI Native创作者)的AI科普内容创作思维——爆肝实操导向、痛点前置产品思维、全平台内容矩阵、B站深度+抖音短平快+飞书系统化。 | majiayu000/ | 666 | 1 repo | ~1.9k | Automated safety check: Pass | MIT | today |
| 277 | 277.Open Weights 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/ | 156 | — | ~4.1k | Automated safety check: Pass | MIT | today |
| 278 | 面向真实业务决策的多平台事实核验 Skill。正式支持深知晓、深知晓(深度溯源)、豆包、腾讯元宝、DeepSeek 和通义千问,按用户输入动态选择 N≥1 个平台。完整采集原回答、引用、截图与页面存证,结构化比较关键事实,按需使用可信搜索逐点核验权威证据,并评估各平台表现。权威答案是核验产物之一,原始证据、冲突与证据边界全程可追溯。基础采集与对比无需 API… | aiskillstore/ | 430 | — | ~3.8k | Automated safety check: Pass | Apache-2.0 | today |
| 279 | Reference guide for permanent free-tier LLM APIs with rate limits, model lists, and OpenAI-compatible integration patterns. | LeoYeAI/ | 2.2k | — | ~4.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 280 | AI plugin for Zotero with ChatGPT, Claude, and DeepSeek support | wentorai/ | 298 | 1 repo | ~1.7k | Automated safety check: Pass | MIT | 3 mo ago |
| 281 | 281.Figure Drawing 论文制图工作流——gpt-image-2 生成概念图 → vision 读结构 → 构造带样式 draw.io XML → 验证。Use when 需要论文级架构图/流程/示意图 | Tai609/ | 100 | — | ~2.7k | Automated safety check: Pass | Unknown | 1 mo ago |