最高评分
社区最喜爱的高星技能，质量有保障。
tencent-upload
dreammis
使用 social-auto-upload 的 sau tencent 登录视频号并发布或定时发布视频、保存草稿。Use when 用户要向微信视频号发布视频或检查视频号账号状态。
tiktok-upload
dreammis
使用仓库现有 Patchright/Playwright Chrome 上传器登录并发布 TikTok 视频。Use when 用户要发布 TikTok 视频，且当前环境可访问本仓库及其本地 Chrome 配置。
weibo-upload
dreammis
使用 social-auto-upload 的 sau weibo 登录微博并发布视频，可指定封面。Use when 用户要向微博发布视频或检查微博账号状态。
xiaohongshu-upload
dreammis
当 agent 需要通过已安装的 sau CLI 完成小红书登录、cookie 校验、视频上传或图文发布时使用这个 skill。该 skill 适用于已经安装 social-auto-upload 且可调用 sau 命令的环境。优先使用这个 skill 进行稳定的命令式小红书工作流，而不是一开始就阅读 uploader 源码。
xueqiu-upload
dreammis
通过 social-auto-upload 的 sau CLI 登录和核验雪球账号，发布 HTML、Markdown 或 TXT 长文，保留原稿段间配图、原生文字结构与独立封面，并查询原作品确认结果。适用于雪球创作者平台，不支持定时或视频。
youtube-upload
dreammis
使用 social-auto-upload 的 sau youtube 登录 YouTube 并上传、安排定时或设置视频可见范围。Use when 用户要向 YouTube 发布或定时发布视频，或检查 Google/YouTube 登录状态。
zhihu-upload
dreammis
使用 social-auto-upload 的 sau CLI 登录知乎、发布文章或视频，并按作品链接核对结果；支持原稿位置配图与视频领域、声明选项。
ml-engineering
stas00
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/stas00/ml-engineering/blob/master/skills/ml-engineering/SKILL.md
Machine Learning Engineering skill
stas00
Canonical URL: https://github.com/stas00/ml-engineering/blob/master/skills/ml-engineering/SKILL.md
lark-apps
larksuite
"妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用协作者与协作权限设置、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要开发/新建一个系统·工具·平台·应用，或要本地开发 / 云端开发 / 修改 / 部署 / 发布 / 上线 / 拿可分享链接，或用 HTML 做页面·网站·部署到妙搭，或要设计 / design / mockup / prototype / wireframe / 做 PPT / deck / 视觉探索，或提到妙搭/Spark/Miaoda（应用运行时域名形如 *.aiforce.cloud）、应用数据库、应用文件存储、开放 API Key、可见范围、应用协作者/开发权限、应用角色/角色成员、线上日志、接口请求量、错误量、延迟、访问量、环境变量、给妙搭应用配自动化任务/定时触发/审批通过后自动触发时使用。不负责普通云盘文件上传（lark-drive）、飞书文档编辑（lark-doc）、原生幻灯片创建（lark-slides）。"
lark-doc
larksuite
"飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。"
ray-train
Orchestra-Research
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
torchforge-rl-training
Orchestra-Research
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
llamaguard
Orchestra-Research
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
elizaos
elizaOS
"Use when the task involves elizaOS core runtime concepts, plugins, actions, providers, evaluators, services, memories, state composition, or upstream elizaOS development. Covers the main abstractions and the TypeScript runtime mental model."
skill-creator
elizaOS
Creates, updates, and packages AgentSkills with proper SKILL.md frontmatter, bundled scripts, references, and assets. Provides guidance on skill naming, progressive disclosure, and context-efficient design. Use when building a new skill from scratch, restructuring an existing skill, writing or improving SKILL.md files, organizing skill resources into scripts/references/assets folders, packaging skills for distribution, or iterating on skill quality after testing.
imsg
elizaOS
iMessage/SMS CLI for listing chats, fetching history, watching conversations, and sending messages on macOS via the Messages app. Use when the user wants to send a text message, read iMessages, check recent texts, reply to a conversation, send an SMS, or interact with the Messages app from the terminal. Supports texting contacts by phone number or email, attaching files, and streaming incoming messages in real time.
mashup-mods
rehan-remade
Build cross-game mashups and total conversions, the "Minecraft inside Elden Ring" or "skateboarding in MW2" kind. Covers passthrough mods (two games running at once and exchanging state, rendering and collision), porting one game's content or mechanics into another, embedding a decompiled game as a library, and clean reimplementations that read the user's own game files. Use when the user wants to combine two games, bring an enemy, mechanic or world from one game into another, or rebuild a game's runtime, or reimplement the guest's rules headless inside a real host.
publish-mod
rehan-remade
Package and release a finished game mod. Covers the pre-release lint (no game files, decompiled code or leaked keys), README and install steps, credits and AI disclosure, versioning, where to upload (Nexus Mods, Steam Workshop, Thunderstore, mod.io, GitHub releases), and the post with a video. Use when the user wants to ship, share, upload, release or post a mod.
reverse-engineering
rehan-remade
Read how a game actually works so a mod can hook it. Decompile .NET/Mono (ILSpy), IL2CPP (Cpp2IL, Il2CppDumper), Java (Vineflower) and native code (Ghidra, IDA, via MCP servers); dump data and asset formats; reverse-engineer a binary file format and prove it with a round trip; read live memory (Cheat Engine, Frida, x64dbg); find render passes (RenderDoc). Use when a mod needs game internals, e.g. "how does the boss AI work", "find the damage function", "what format is this .sld/.pak/.dat", "where is the player position in memory".
share-field-notes
rehan-remade
Search and contribute to the shared AI-modding knowledge base, where field notes record how specific games were modded, decompiled or reverse-engineered (exact versions, route, engine facts, verification, gotchas). Use before starting work on a game ("has anyone modded X?"), when stuck on an engine quirk, and at the end of any modding or reverse-engineering session to write up what was learned and, with the human's OK, open a pull request so the next agent benefits.
fal-assets
rehan-remade
Generate game assets with fal (fal.ai) through the fal MCP server, the um fal CLI (REST) or fal api. Covers sprites and icons with transparent backgrounds, consistent variants and animation frames, pixel art, seamless textures, PBR material maps, image-to-3D models, remeshing, auto-rigging, sound effects, music, voice lines, and trailer or cutscene video. Use whenever a mod needs new art, audio or 3D models, or the user mentions fal, generating sprites, textures, models, SFX or music for a game.
asset-pipeline
rehan-remade
Turn generated or hand-made art into exactly what a game engine loads. Covers sprite cutout, trim and nearest-neighbour fitting to frame sizes, pixelation to a palette, sprite sheets and strips, player/team-colour masks, seamless textures, and rendering a 3D model into sprite frames from the game's own camera (isometric/RTS 8 or 16 headings, side view, top-down) with Blender. Use after generating assets, or when the user asks to make sprites, sprite sheets, animation frames, isometric unit sprites or icons for a game.
game-recon
rehan-remade
Figure out how a specific installed game can be modded, before writing any mod code. Covers where it's installed, the engine and version, managed vs native code, anti-cheat, loaders already present, save and config folders, and the community's modding route. Use when the user asks "can I mod <game>?", "what engine is <game>", "how do people mod <game>", or at the start of any modding task. Produces MODDING_PLAN.md.