Search
DeepSeek
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 193 | 193.Plugin Release Package, publish, and distribute DeepSeek Harness (DSH) plugins — npm pack artifact validation, GitHub/npm/hub release-track selection, tarball overrides installs for the unpublished cohort… | NanmiCoder/ | 164 | 1 repo | ~1.6k | Automated safety check: Warn | MIT | 12 days ago |
| 194 | 194.Dsh Config Show or set this session's DSH worker defaults (tier / effort / mode / timeout / on-off) | ZSeven-W/ | 158 | — | ~252 | Automated safety check: Pass | MIT | 3 days ago |
| 195 | 195.Practice Guide a programming exercise using dsh-tui or a topic the user wants to learn. | ccch1mneyyy/ | 4.3k | — | ~356 | Automated safety check: Pass | MIT | today |
| 196 | 196.Blockrun A skill your agent uses when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e"… | davila7/ | 33k | 7 repos | ~2.2k | Automated safety check: Pass | MIT | today |
| 197 | 197.Cloud Test 用本地前端插件连云端后端做端到端测试 / test the local VS Code extension against the deployed cloud backend. | FreakStudioCN/ | 154 | — | ~1.7k | Automated safety check: Pass | Unknown | 13 days ago |
| 198 | LangChain / LangGraph engineering pitfalls and verified fixes. | ob-labs/ | 195 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 199 | A skill your agent uses when a new Ollama Cloud model is announced or available (e.g. | heypinchy/ | 182 | — | ~3.9k | Automated safety check: Notes | AGPL-3.0 | 20 days ago |
| 200 | 200.Dsh Run Output Internal guidance for presenting DeepSeek Harness bridge results (reviews, critiques, delegated runs) back to the user. | cpj-dev/ | 106 | — | ~411 | Automated safety check: Pass | MIT | 1 mo ago |
| 201 | 当用户需要把 GEO 全景诊断、机会地图、AI 平台采样结论或品牌事实底座转成 30/60/90 天综合实施方案时使用，输出页面技术、内容矩阵、标题体系、知识库、外部证据、监测闭环、角色分工、验收指标和四格式报告；覆盖 DeepSeek、豆包、千问、Kimi、元宝；不用于从零做全景采样诊断或只写单篇内容。 | yaojingang/ | 871 | — | ~646 | Automated safety check: Pass | MIT | 10 days ago |
| 202 | Sends chat completions, streams responses, and opens an interactive REPL against any OmniRoute-routed model provider. | diegosouzapw/ | 75k | — | ~345 | Automated safety check: Pass | MIT | today |
| 203 | Find evidence-backed simplifications in DeepSeek Harness code, APIs, configuration, tests, and prose; write or consolidate proposals, identify small inline cleanups, or assess simplifications from… | Zhou-Yujing114514/ | 120 | — | ~2.6k | Automated safety check: Pass | MIT | 5 days ago |
| 204 | The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. | oxbshw/ | 470 | — | ~380 | Automated safety check: Notes | MIT | 27 days ago |
| 205 | 205.Release Notes Draft user-facing release notes from a verified release range. | ccch1mneyyy/ | 4.3k | — | ~335 | Automated safety check: Pass | MIT | today |
| 206 | 206.Dev Up 启动 Blockless 本地开发栈 / bring up the local dev stack. An agent skill from FreakStudioCN/mpy-hardware-extension. | FreakStudioCN/ | 154 | — | ~1.3k | Automated safety check: Notes | Unknown | 13 days ago |
| 207 | 207.Copy Research Dispatch copy-lead helpers: Tavily, Codex luna/terra, grok/X, OpenCode DeepSeek, Cursor Grok 4.6 medium-fast. | VKirill/ | 122 | — | ~827 | Automated safety check: Pass | MIT | yesterday |
| 208 | Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional… | Tai609/ | 100 | — | ~5k | Automated safety check: Pass | Unknown | 1 mo ago |
| 209 | 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/ | 154 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 210 | 210.Ade Harnesses 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/ | 114 | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | today |
| 211 | Installs OpenCode as an optional NanoClaw agent runtime, reaching OpenRouter, OpenAI, Google, DeepSeek and others through OpenCode's own configuration. | nanocoai/ | 31k | — | ~5k | Automated safety check: Notes | MIT | yesterday |
| 212 | 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/ | 470 | — | ~455 | Automated safety check: Notes | MIT | 27 days ago |
| 213 | 213.Plugin Upgrade A skill your agent uses for DSH plugin compatibility, migration, upgrade, regression, or post-upgrade diagnosis, including read-only review of already-migrated plugin source and version-boundary… | NanmiCoder/ | 164 | 1 repo | ~4.5k | Automated safety check: Warn | MIT | 12 days ago |
| 214 | 214.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。 | momozi1996/ | 920 | — | ~1.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 215 | 215.Add Mpk Model Guide for adding a new model (e.g., Llama4, DeepSeek V3) to the MPK persistent kernel. | mirage-project/ | 2.5k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 216 | Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. | davila7/ | 33k | 2 repos | ~1.2k | Automated safety check: Pass | MIT | today |
| 217 | 217.Dsh Client UI UX Design and review DeepSeek Harness client UI changes — visual token discipline, reuse-before-adding, feedback surfaces (toast vs in-place notice vs empty state), overlay and menu safety, platform… | Zhou-Yujing114514/ | 120 | — | ~1.9k | Automated safety check: Pass | MIT | 5 days ago |
| 218 | Write, optimize, and debug high-performance AI compute kernels using TileLang (a Python DSL for GPU programming). | yzlnew/ | 149 | — | ~2.4k | Automated safety check: Pass | No licence | 3 mo ago |
| 219 | A skill your agent uses whenever the user asks to talk with, roleplay, interview, quote, fact-check, or apply the reasoning of 梁文锋/Liang Wenfeng from the bundled May 20 investor-meeting transcript. | tjxj/ | 548 | — | ~1.4k | Automated safety check: Pass | No licence | 19 days ago |
| 220 | 220.Sharing Results The user wants to share or hand off what was found in a video — "send this analysis to my team", "make a page I can share", "export the findings", "give me something I can attach to the ticket". | oxbshw/ | 470 | — | ~408 | Automated safety check: Notes | MIT | 27 days ago |
| 221 | 221.Quota Axi 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/ | 147 | — | ~547 | Automated safety check: Pass | MIT | 2 days ago |
| 222 | 222.Dsh Code Review 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/ | 120 | — | ~2.1k | Automated safety check: Pass | MIT | 5 days ago |
| 223 | 可独立运行的 GPT-Image 增强版 EPUB2Podcast：在本地把 EPUB 转成双人中文音频、GPT-Image/Smart Slide 视觉页、最终 MP4，并生成 YouTube 发布素材。 | dracohu2025-cloud/ | 227 | — | ~1.9k | Automated safety check: Pass | MIT | 24 days ago |
| 224 | YouTube 视频 → 下载 → 转录 → 翻译 → 存为 Markdown. An agent skill from chubbyguan/chubbyskills. | chubbyguan/ | 1.2k | — | ~706 | Automated safety check: Notes | MIT | 3 days ago |
| 225 | 225.Watch Watch any video (URL, stream, or local path) via Watch Skill. | oxbshw/ | 470 | — | ~1.3k | Automated safety check: Notes | MIT | 27 days ago |
| 226 | Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the… | Zhou-Yujing114514/ | 120 | — | ~2.7k | Automated safety check: Pass | MIT | 5 days ago |
| 227 | Plan and deliver a coordinated runtime-target refresh for every supported Sesori harness: OpenCode, Antigravity, Codex, GitHub Copilot, Cursor, Claude Code, Hermes Agent, Pi, Oh My Pi, DeepSeek, and… | sesori-ai/ | 126 | — | ~5.8k | Automated safety check: Pass | Unknown | 2 days ago |
| 228 | 228.Deepseek Chat One-shot chat completion against DeepSeek's deepseek-chat model via the OpenAI-compatible /v1/chat/completions endpoint. | ruvnet/ | 74k | — | ~564 | Automated safety check: Notes | MIT | yesterday |
| 229 | 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/ | 164 | — | ~3.8k | Automated safety check: Pass | MIT | 12 days ago |
| 230 | Audit the DeepSeek V3 MPK demo + builder chain end-to-end and confirm logical equivalence with vLLM's reference implementation. | mirage-project/ | 2.5k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 231 | DeepSeek Harness 开发文档离线 Wiki，检索导航涵盖的插件开发、工具、配置、生命周期、服务、事件、LLM 适配器和 Cordis 教程。用户询问这些开发主题时使用；不用于日常产品使用、部署运维或完整 API 参考。 | chujianyun/ | 742 | — | ~366 | Automated safety check: Pass | Unknown | 2 days ago |
| 232 | A skill your agent uses when investigating or optimizing DeepSeek Harness performance, designing realistic synthetic benchmarks or CI performance gates, profiling long Sessions or Web… | Zhou-Yujing114514/ | 120 | — | ~3k | Automated safety check: Pass | MIT | 5 days ago |
| 233 | 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/ | 1.7k | — | ~2k | Automated safety check: Notes | AGPL-3.0 | yesterday |
| 234 | 234.Dsh Plugin Dev DeepSeek Harness（DSH）插件的设计、开发、装载验证、版本迁移与发布审查指引（版本感知）。在用户要为 DSH Desktop 开发插件、把 Pi/Hermes 插件迁移到 DSH、做隔离装载实验、排查插件在真实宿主的行为、跟进 DSH 版本升级适配，或在发布前做机械审查与验收（dsh.bundle / dsh.client 双面包工件契约、inject/external… | cat-xierluo/ | 720 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 235 | 235.Review Collect critical feedback from all registered LLMs on an artifact (architecture doc, implementation, plan). | raine/ | 139 | — | ~2.4k | Automated safety check: Notes | MIT | 4 days ago |
| 236 | 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/ | 21k | — | ~9.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 237 | Command-line interface for Novita AI - An OpenAI-compatible AI API client for DeepSeek, GLM, and other models. | HKUDS/ | 52k | — | ~950 | Automated safety check: Pass | Apache-2.0 | 19 days ago |
| 238 | 238.Deepseek Reason Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions. | ruvnet/ | 74k | — | ~626 | Automated safety check: Notes | MIT | yesterday |
| 239 | 239.Review It Code review closeout for Claude Code, Codex, OpenCode, DeepSeek TUI, and Antigravity CLI: local dirty changes, branch vs main, parallel tests. | smallnest/ | 291 | — | ~1.4k | Automated safety check: Pass | MIT | 28 days ago |
| 240 | 240.Tensorrt LLM High-throughput LLM inference on NVIDIA GPUs. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~1.3k | Automated safety check: Pass | MIT | 3 days ago |
