AI model or service
DeepSeek agent skills, page 2
DeepSeek skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network. | Ikalus1988/ | 524 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 50 | 50.Daily Brief Operational knowledge for the daily-brief digest pipeline (this project). | leiting-eric/ | 364 | — | ~3k | Automated safety check: Notes | MIT | yesterday |
| 51 | Propose five DeepSeek Whale-chan comic concepts from text, screenshots, images, chat logs, or reasoning traces, then generate verified comics after the user selects concepts and separately confirms… | Neko3000/ | 222 | — | ~4.4k | Automated safety check: Pass | No licence | 4 days ago |
| 52 | 52.Bridgic LLMs LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic. | bitsky-tech/ | 155 | — | ~839 | Automated safety check: Notes | MIT | 2 mo ago |
| 53 | 53.Apocdata A-share data service with structured announcement parsing: every announcement carries an AI summary, category, importance level and sentiment, fully traceable to source. | ApocData/ | 103 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | 22 days ago |
| 54 | Search and recall relevant memories from past sessions via memsearch. | zilliztech/ | 2.7k | — | ~1k | Automated safety check: Pass | MIT | 13 days ago |
| 55 | 55.LLM Router 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/ | 215 | 1 repo | ~3.3k | Automated safety check: Pass | MIT | 8 mo ago |
| 56 | 56.K8e Sandbox Run a goal end to end inside an isolated K8E sandbox pod (gVisor / Kata / Firecracker) instead of on the host: exec bash / Python / Node / TypeScript, install packages, move files in and out, reuse… | xiaods/ | 499 | — | ~6k | Automated safety check: Pass | Apache-2.0 | 9 days ago |
| 57 | Build a new skin for the dsh-web-ui skin collection (DSH Web GUI) and publish it into the skin-center plugin — scaffold with scripts/dsh-skin-new, author skin.json plus the apply/dispose +… | ningbainb/ | 776 | — | ~1.4k | Automated safety check: Pass | BSD-3-Clause | yesterday |
| 58 | 把带时间戳的 narration.json 合成为中文解说音频。使用 MiMo TTS(mimo-v2.5-tts)或 Fish Audio(s2.1-pro-free)或显式配置的通用 IndexTTS HTTP 服务逐段生成语音, 按时间窗动态适配语速并处理响度;输入输出时间线上的旁白,产出 ttssegments 与 ttsmeta.json。 | zenstory-ai/ | 460 | — | ~1.1k | Automated safety check: Pass | MIT | 4 days ago |
| 59 | 使用此 Skill 创建、检查、编辑和验证 XLSX 工作簿。用户提到 Excel、xlsx、工作簿、工作表、表格,或要求修改、汇总、检查 Excel 文件时使用。只支持基础 XLSX 操作,不处理宏、VBA、图表、数据透视表或外部工作簿引用。 | adongwanai/ | 405 | — | ~597 | Automated safety check: Notes | MIT | yesterday |
| 60 | 60.Find Plugins 用户想给 DeepSeek Harness 找插件时使用:「有没有插件能……」「帮我装个 XX」 「生态里有什么好玩的」。从全 GitHub 的 dsh-plugin topic 发现跨个人与组织的 公开仓库,筛选候选,等用户拍板,先汇报这个插件要什么权限,再从仓库声明判断 安装方式并验证挂载。只负责找和装;开发新插件转 make-dsh-plugin。 | Nagi-ovo/ | 177 | — | ~645 | Automated safety check: Notes | BSD-3-Clause | 1 mo ago |
| 61 | Deploy, configure, verify, upgrade, and troubleshoot DeepSeek Harness with the community Docker, Docker Compose, rootless Podman, and Helm runtime, including the built-in Chromium/noVNC browser… | runzhliu/ | 109 | — | ~2.7k | Automated safety check: Notes | MIT | 2 days ago |
| 62 | Search the EvalDock dsh-Top100 catalog and recommend suitable DeepSeek Harness plugins or Skills. | evaldock-account/ | 495 | — | ~583 | Automated safety check: Pass | MIT | 2 days ago |
| 63 | Render Markdown manuals into polished per-page PNG images and PDF deliverables. | BigStrongSun/ | 122 | — | ~589 | Automated safety check: Pass | MIT | 3 days ago |
| 64 | A skill your agent uses when the user asks about dsh-tui itself (usage, shortcuts, config, themes, migration, VS Code). | ccch1mneyyy/ | 4.1k | — | ~310 | Automated safety check: Pass | MIT | today |
| 65 | 使用隔离的 Chrome DevTools MCP 从博客、新闻、公众号等网页提取正文,返回结构化内容,或保存 Markdown 和远程图片。用户要求提取文章、抓取网页正文、保存为 Markdown、下载文章图片或排查正文选择器时调用。 | dongbeixiaohuo/ | 435 | — | ~740 | Automated safety check: Pass | MIT | 4 days ago |
| 66 | A skill your agent uses when one or more photographs must become adaptive photo-plus-abstraction editorial compositions while source facts, spatial relationships, and strict photo preservation… | kwhi6693-web/ | 111 | — | ~870 | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 67 | Installs, configures and operates BrowserWing, a browser automation platform, covering Chrome setup, LLM provider configuration, and creating or running automation scripts. | MemTensor/ | 12k | — | ~4.1k | Automated safety check: Notes | Apache-2.0 | 9 days ago |
| 68 | 68.Plugin Write A skill your agent uses when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central… | NanmiCoder/ | 165 | 1 repo | ~3.3k | Automated safety check: Pass | MIT | 8 days ago |
| 69 | 69.Md2docx Convert Markdown to Word (DOCX) documents. An agent skill from Yorick-Ryu/deep-share. | Yorick-Ryu/ | 144 | — | ~1.9k | Automated safety check: Pass | Unknown | 3 days ago |
| 70 | Run a Chinese interactive story for adults with a local deterministic engine that keeps characters, relationships, time, events, boundaries, and save slots consistent. | daha1216/ | 125 | — | ~2.3k | Automated safety check: Pass | No licence | yesterday |
| 71 | 71.Add Model Adapt and port new LLM model architectures to this xinfer project. | guoqingbao/ | 333 | — | ~4.2k | Automated safety check: Notes | MIT | 28 days ago |
| 72 | 72.Vision Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images. | xiincs/ | 170 | — | ~1.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 73 | 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/ | 1k | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 74 | 使用完整动画工程包,把新口播、文案与自有素材制作成可编辑动效视频和 60fps MP4;也支持轻量 TPL、手绘续接、字幕与改旧片。支持 Windows、macOS、Linux,以及 Codex、Claude Code、豆包、DeepSeek、WorkBuddy 等可读写文件并运行命令的助手。 | adunext/ | 166 | — | ~2.3k | Automated safety check: Pass | MIT | yesterday |
| 75 | Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. | shengsheng90/ | 331 | — | ~885 | Automated safety check: Pass | Apache-2.0 | 7 days ago |
| 76 | 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/ | 900 | — | ~1.2k | Automated safety check: Pass | No licence | 2 days ago |
| 77 | 77.Obelisk Search and query past Claude Code, Codex, Kimi Code, OMP, and Pi session history. | tommy0103/ | 567 | — | ~6.7k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 78 | 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/ | 452 | — | ~550 | Automated safety check: Notes | MIT | 23 days ago |
| 79 | Create, update, import, or validate Emperor Skills (SKILL.md folders with optional scripts, references, and assets). | TheSyart/ | 195 | — | ~2k | Automated safety check: Pass | MIT | 8 days ago |
| 80 | 80.PR Open or update a pull request in this repository, including writing or rewriting its description. | ccch1mneyyy/ | 4.1k | — | ~601 | Automated safety check: Pass | MIT | today |
| 81 | 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/ | 1.8k | — | ~367 | Automated safety check: Pass | MIT | yesterday |
| 82 | 82.Datamoat Back up, analyze, and reuse ChatGPT | Claude | Codex | Cursor | DeepSeek | Qwen | Openclaw data + skills + attachments locally | max-ng/ | 210 | — | ~307 | Automated safety check: Pass | MIT | 3 mo ago |
| 83 | 面向中国 AI / ML 研究者,主投 Nature Machine Intelligence、次投 Nature Communications / Nature Computational Science、必要时冲刺 Nature 的论文写作技能(craft + taste + story-craft)。v5 在 v4 拆分版上吸收了 8 篇 2024–2026 NMI/NC/Nature… | SyntaxSmith/ | 156 | — | ~4.2k | Automated safety check: Pass | No licence | 5 mo ago |
| 84 | 84.Go Idiomatic Go - package and interface design, error wrapping, table-driven tests, generics, the modern standard library (slices/maps/cmp/errors.Join), current syntax, and logging discipline. | inference-gateway/ | 214 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 85 | 85.Engramory Curated, file-based long-term memory for an AI agent. An agent skill from tinqiao-oss/engramory. | tinqiao-oss/ | 192 | — | ~8.3k | Automated safety check: Pass | MIT | 14 days ago |
| 86 | Prefer the hosting AI Agent to write narration into input.txt from crawl JSON (no external LLM). | szhshp/ | 290 | — | ~1.5k | Automated safety check: Notes | No licence | 1 mo ago |
| 87 | 87.Omnisci Run OmniScientist end to end in the OmniScientist CLI using DeepSeek V4 Flash. | Omni-Scientist/ | 165 | — | ~5.1k | Automated safety check: Pass | MIT | 11 days ago |
| 88 | 88.Summary Use this for a quick summary of a research paper's core ideas and key points. | alaliqing/ | 344 | — | ~2k | Automated safety check: Notes | MIT | 1 mo ago |
| 89 | Search, browse, select, import, review, publish, and materialize reusable scientific-figure assets through Scientific Figure Library. | xuzhougeng/ | 105 | — | ~1.9k | Automated safety check: Pass | MIT | 4 days ago |
| 90 | 90.Normify Gen Analyze one or more code repositories and produce a Normify module-tree structure database (per-module Markdown files with strict YAML frontmatter), then validate, build, and render it into an… | yan-mc/ | 103 | — | ~4k | Automated safety check: Pass | MIT | 24 days ago |
| 91 | 91.Market Data Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares). | zhongkaifu/ | 553 | — | ~1k | Automated safety check: Pass | BSD-3-Clause | today |
| 92 | A skill your agent uses when adding or publishing an AI API public-benefit or relay-site listing from promotional copy in this repository, including validating the referral link, regenerating the… | bubblevv/ | 100 | — | ~959 | Automated safety check: Pass | No licence | 1 mo ago |
| 93 | Interprets vague, conversational, or intuition-led product, software, AI, and feature ideas as a precise, checkable requirements draft, maps rough descriptions to useful professional terms, exposes… | bydtesla1609/ | 126 | — | ~2.3k | Automated safety check: Pass | MIT | yesterday |
| 94 | 94.Subagent Fan out a one-shot or flat parallel batch of cc-fleet PROVIDER subagents (headless cc-fleet subagent) that return a result — DeepSeek / GLM / Kimi / Qwen / MiniMax, or a Codex/Claude subscription. | ethanhq/ | 215 | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 95 | 95.New Provider 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/ | 270 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 96 | Build or run a FAITHFUL in-MPK per-task latency gate (slowCTA at the production grid + cos) for a DeepSeek-V3 MPK decode kernel or shape. | mirage-project/ | 2.5k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |