AI model or service
DeepSeek agent skills, page 3
DeepSeek skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 97 | 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 | today |
| 98 | Search and recall relevant memories from past sessions via memsearch. | zilliztech/ | 2.7k | — | ~807 | Automated safety check: Pass | MIT | 14 days ago |
| 99 | 99.Muse Muse · Catch — AI 灵感捕手。浏览器插件 + 任意 Agent(Telegram/WhatsApp/Discord…)一键捕获灵感,AI自动提炼,Web Dashboard浏览。分级LLM路由:Agent内置LLM隐私分析 + TokenRouter云端分布式调用。当用户说「灵感」「捕获」「Muse」「Catch」「记下来」「收藏」「稍后读」时自动触发。 | KevPH2026/ | 128 | — | ~1.6k | Automated safety check: Notes | AGPL-3.0 | 1 mo ago |
| 100 | 100.Brewreel 精酿 · BrewReel:三种玩法。宣传片:做竖版产品宣传短片(1080x1920,15–45 秒,抖音/视频号/小红书)。用户要做产品宣传片、推广短视频、App 介绍视频、功能演示视频、上新短片、带货片头时使用。支持软件、餐饮、电商实物、教培、美业、文旅住宿六个行业,支持中英双语。你只写 storyboard.json,校验拦规则和行业合规,一条命令出片。口播配画面:用户有… | Finderchangchang/ | 139 | — | ~6.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 101 | Run and strongly accept Jacky Creator's branch-to-release workflow: verify feature branches, merge approved changes, synchronize every version surface, build one immutable artifact, publish… | Jackywxsz/ | 110 | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 102 | Release and publish the dsh-web-ui monorepo (DSH Web GUI plugin family + skin collection) — bump all packages to one unified version, commit and tag, push the vX.Y.Z tag that triggers the GitHub… | ningbainb/ | 781 | — | ~1.4k | Automated safety check: Warn | BSD-3-Clause | yesterday |
| 103 | 103.Web Design A skill your agent uses when building any web page, HTML artifact, landing page, dashboard, slide deck, report, email, or UI component the user will look at. | drewnekota/ | 146 | — | ~2.1k | Automated safety check: Pass | MIT | 3 days ago |
| 104 | 104.Tabbit Control Tabbit Browser in a task-isolated Playwright workspace; never switch browser backends. | Tabbit-Browser/ | 103 | — | ~780 | Automated safety check: Pass | MIT | today |
| 105 | 写或修改 CHANGELOG.md(待发布条目、版本亮点段、GitHub Release 说明)时使用。含按改动性质分组落位、中英双语体例、发版前的两道门禁(三处版本号同步 + 亮点段抽取会 fail-fast)与写后自检命令。 | xiajiajun516/ | 164 | — | ~805 | Automated safety check: Pass | MIT | today |
| 106 | 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/ | 460 | — | ~509 | Automated safety check: Notes | MIT | 23 days ago |
| 107 | 107.Vuln Check Check resolved dependencies and relevant code paths for security vulnerabilities. | ccch1mneyyy/ | 4.2k | — | ~467 | Automated safety check: Pass | MIT | today |
| 108 | 108.Agentic Search 当用户提问需要联网检索(最新新闻、技术资料、人物事件等)或明确说"搜一下/查一下/帮我找…"时触发。本技能会自动改写 query 并通过 DuckDuckGo 检索,再用 DeepSeek 综合回答,引用来源序号。 | benchen4395/ | 486 | — | ~140 | Automated safety check: Pass | No licence | 22 days ago |
| 109 | Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). | Orchestra-Research/ | 13k | 5 repos | ~2.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 110 | 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/ | 13k | 5 repos | ~1.5k | Automated safety check: Pass | MIT | 3 mo ago |
| 111 | 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/ | 13k | 5 repos | ~2.8k | Automated safety check: Pass | MIT | 3 mo ago |
| 112 | YouTube 视频 → 下载 → 转录 → 翻译 → 存为 Markdown. An agent skill from chubbyguan/chubbyskills. | chubbyguan/ | 1.2k | 1 repo | ~706 | Automated safety check: Notes | MIT | 2 days ago |
| 113 | 113.Add Model Price Add new LLM model pricing entries to Litefuse's default-model-prices.json. | litefuse/ | 100 | — | ~3.6k | Automated safety check: Pass | Unknown | 15 days ago |
| 114 | Build evidence-backed GEO brand knowledge bases from official sites, product pages, help centers, white papers, sales materials, media releases, certifications, and trusted third-party sources. | yaojingang/ | 868 | — | ~1.8k | Automated safety check: Pass | MIT | 7 days ago |
| 115 | 115.Go Concurrency Idiomatic Go concurrency - sync primitives, channel semantics, the select statement, and the standard channel patterns (cancellation/done-channel, fan-out/fan-in, pipeline, or-done, context… | inference-gateway/ | 214 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 116 | 116.Mmsp Python Guidance for using the MMSP Python SDK (mmsp). An agent skill from Prism-Shadow/model-message-stream-protocol. | Prism-Shadow/ | 113 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 117 | 117.Mesh API Interact with a Meshtastic LoRa mesh network through MESH-API — list nodes, read messages, send texts, and check connection status. | mr-tbot/ | 180 | — | ~1.8k | Automated safety check: Pass | GPL-3.0 | 2 mo ago |
| 118 | Release browser extensions or similar small packaged apps by upgrading a semantic version, packaging build artifacts, creating a git commit and tag, pushing to the remote, and publishing a GitHub… | Yorick-Ryu/ | 144 | — | ~1.3k | Automated safety check: Pass | Unknown | 3 days ago |
| 119 | 119.Cloudbase A skill your agent uses when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects — Web, 微信小程序, 小程序, uni-app, mobile (iOS, Android… | TencentCloudBase/ | 1.1k | 1 repo | ~4.7k | Automated safety check: Pass | MIT | yesterday |
| 120 | Plan-first, one-time human plan approval; batched execution in either Gated (human confirms between batches) or Auto-loop (continuous run after plan approval); strict task-state updates; automatic… | AlephantAI/ | 114 | — | ~2.7k | Automated safety check: Pass | GPL-3.0 | 3 mo ago |
| 121 | 121.Research A skill your agent uses for web searches and current information lookups, finding sources, fact-checking, researching questions, comparing sources, or summarising web pages. | zhongkaifu/ | 557 | — | ~2.3k | Automated safety check: Warn | BSD-3-Clause | today |
| 122 | How to operate a pi-dispatch deployment through its tools, and how to use the operator-confirm gates on the write tools (changing limits, adding/editing/deleting triggers). | edgehero/ | 178 | — | ~7.6k | Automated safety check: Notes | MIT | today |
| 123 | Runs a staged workflow for math modeling contests such as CUMCM and MCM/ICM, with checkpoints, verified solver code and a LaTeX paper, on DeepSeek Harness. | RealSeaberry/ | 257 | — | ~2.3k | Automated safety check: Pass | MIT | 27 days ago |
| 124 | 124.Grix Code Review Audit Grix diffs and pull requests for correctness, regressions, security, lifecycle safety, and cross-component contract consistency. | askie/ | 153 | — | ~799 | Automated safety check: Pass | Unknown | today |
| 125 | 125.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 |
| 126 | 126.Release Prep cc-router 发版准备一条龙:升版本号 → 根据上一个 tag 以来的提交写 release-notes/<版本/ 的中英日三份更新内容 → 校验 → 给用户审 → 本地提交「Bump version to X.Y.Z」,停在打 tag 之前。当用户说「准备发版」「发个版」「发 6.1.0」「写发版说明 / 更新内容 / release notes」「bump 版本」时必须走本… | finch-xu/ | 272 | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 127 | 127.Blockrun Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key. | BlockRunAI/ | 392 | — | ~2.7k | Automated safety check: Pass | MIT | today |
| 128 | 128.Keirouter Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. | mydisha/ | 147 | — | ~995 | Automated safety check: Pass | MIT | 27 days ago |
| 129 | 129.Dsh Web Web QA A skill your agent uses to validate a dsh-web client or skin change in the real DeepSeek Harness Web GUI, including build readiness, responsive rendering, interaction checks, and evidence capture. | zhu1090093659/ | 8.5k | — | ~920 | Automated safety check: Pass | Apache-2.0 | today |
| 130 | Premium judgment; cheap repository specialists; deterministic helpers for objective integrity. | frozenpepper/ | 152 | — | ~1.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 131 | 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/ | 187 | — | ~551 | Automated safety check: Pass | No licence | 7 mo ago |
| 132 | 132.The Loop The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does… | oxbshw/ | 460 | — | ~622 | Automated safety check: Notes | MIT | 23 days ago |
| 133 | 133.Dotnet Csharp Work on this repository's .NET/C SDK code, including API models, HTTP behavior, Microsoft.Extensions.AI adapters, ASP.NET Core DI, builds, and tests. | niltor/ | 122 | — | ~669 | Automated safety check: Pass | MIT | 26 days ago |
| 134 | Hands a bounded repository task to the DeepSeek Harness CLI (dsh) in headless mode, then checks the exit code and the diff before reporting back. | CherryHQ/ | 52k | 1 repo | ~359 | Automated safety check: Pass | AGPL-3.0 | today |
| 135 | 135.Clawhub Search, install and manage skills from ClawdHub. An agent skill from oujingzhou/openmozi. | oujingzhou/ | 188 | — | ~291 | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 136 | [MASTER ENTRY POINT] 需要多阶段产物的中文长文、公众号文章与观点文工作流总导演. An agent skill from dongbeixiaohuo/writing-agent. | dongbeixiaohuo/ | 434 | — | ~1.6k | Automated safety check: Pass | MIT | 4 days ago |
| 137 | 137.Cdesktop Operate the cdesktop coding-session environment — agent teams, session management, file conventions. | cdesktop-ai/ | 157 | — | ~697 | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 138 | Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills. | amd/ | 398 | — | ~4k | Automated safety check: Notes | MIT | today |
| 139 | 139.Go Spec Reviewer Review a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces… | inference-gateway/ | 214 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 140 | 140.Mako Lore 穗织世界观、神话与诅咒、身边人物、API速查表——常陆茉子的背景知识库,自动加载. An agent skill from liebaojun/MakoCode. | liebaojun/ | 155 | — | ~692 | Automated safety check: Pass | Unknown | 1 mo ago |
| 141 | 141.Computer Use Operate web pages in Emperor's built-in browser with the browser tools, and macOS app windows with the desktop tools — open or bind a target, read it, fill, click or type, and verify the result. | TheSyart/ | 195 | — | ~2.6k | Automated safety check: Pass | MIT | 8 days ago |
| 142 | 深色/浅色主题下 DeepSeek Harness for VS Code 原生工作台 webview 前端的跨平台(Windows / macOS)样式与功能一致性规范。当修改 media/chat.css、media/chat-responsive.css、src/webview/chat/.ts、src/webview/composer-configuration/.ts 或… | skymecode/ | 154 | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 143 | 143.Diagnose Disciplined diagnosis for hard bugs and performance regressions. | zmy15/ | 108 | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 144 | Internal contract for calling the dsh bridge from commands and the dsh-delegate agent — subcommands, flags, environment, and failure handling. | cpj-dev/ | 106 | — | ~834 | Automated safety check: Pass | MIT | 1 mo ago |