293 个 · 按相关度排序
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
中文简介正在准备中。当前显示原文说明。
AI language tutor for learning ANY language through conversation, vocab drills, grammar lessons, flashcards, and immersive practice. Use when the user wants to: learn a new language, practice vocabulary, study grammar, do flashcard drills, translate phrases, practice conversation, prepare for travel, learn slang/idioms, or improve pronunciation. Supports ALL languages including Spanish, French, German, Japanese, Chinese (Mandarin/Cantonese), Korean, Arabic, Hindi, Bengali/Bangla, Portuguese, Russian, Italian, Turkish, Vietnamese, Thai, Swahili, Hebrew, Polish, Dutch, Greek, and 100+ more.
中文简介正在准备中。当前显示原文说明。
帮助构建定期采集公开网站或API中职位、价格、新闻等信息的系统，设计AI摘要、分类、评分和存储流程，并将用户的采纳或拒绝记录用于后续评分。
将claude-flow改为基于agentic-flow@alpha的扩展，减少重复实现，通过适配层分阶段迁移代理管理和任务执行，并验证兼容性。
Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.
中文简介正在准备中。当前显示英语简介。
Review website animations against users’ reduced motion preferences, a setting that requests less movement. Check flashing content, scrolling effects, alternative transitions, pause controls, and advance warnings, and identify changes needed in rendered pages and interactive states.
中文简介正在准备中。当前显示英语简介。
Review the loading order of CSS and JavaScript to address rendering delays and flashes of unstyled content. Suggest changes to the document head, script loading, and critical styles, while checking layouts across screen sizes and interaction states.
中文简介正在准备中。当前显示英语简介。
Generate video clips from text descriptions or reference images through multiple API services. Compare available providers by cost and task needs, choose aspect ratios, track generation progress, and refine existing clips through conversational editing with Gemini Omni.
中文简介正在准备中。当前显示英语简介。
Generate and edit images and videos through Atlas Cloud using one API key across multiple model families. Choose supported models for each task, download the results, and retain details about the model, inputs, and estimated cost.
中文简介正在准备中。当前显示英语简介。
Organize cmux windows, workspaces, and split panes so an agent can target the right terminal reliably. Create terminals with startup commands, move or reorder panels, change focus, and flash a panel to identify it.
中文简介正在准备中。当前显示英语简介。
Plan security testing for IoT and embedded devices, from circuit board inspection and firmware analysis to wireless links, companion apps, and cloud APIs. Includes tools, investigation checklists, and guidance for documenting findings.
中文简介正在准备中。当前显示英语简介。
Refactor claude-flow into an extension of agentic-flow@alpha to reduce duplicate implementations. Plan adapter layers, migrate agent and task management, and connect learning, shared memory, and tools while checking compatibility with existing functionality.
中文简介正在准备中。当前显示英语简介。
Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.
中文简介正在准备中。当前显示原文说明。
All-in-one image generation with Gemini models. Supports Nano Banana (3.1 Flash), Nano Banana Pro (3 Pro), and Nano Banana 2 (2.5 Flash). Triggers on "generate image", "image generation", "nano banana", "edit image".
中文简介正在准备中。当前显示原文说明。
将约 5 秒口播文稿、观点句或抽象概念做成高级 editorial halftone paper-collage / 半调纸拼贴 B-roll。用户说“collage b-roll”“纸拼贴 b-roll”“半调拼贴”“拼贴风格配画面”“用这段文稿做拼贴动画”“gbro-collage-broll”，或希望把一句文稿转成拼贴视觉隐喻时，必须使用此 skill。强制采用三阶段审批：先只提视觉隐喻，用户确认后才生成彩色拼贴静帧，静帧再次确认后才默认调用 Gemini Omni Flash 生成首尾帧组装动画。默认视频模型固定为 gemini-omni-flash-preview，不再默认使用 Veo；只有用户明确指定其他模型时才切换。
中文简介正在准备中。当前显示原文说明。
Use when generating or editing images with Google's Gemini image models (Nano Banana) on Scenario via MCP: text-to-image, natural-language instruction editing, identity locking or style transfer from reference images, multi-image fusion, pulling stills from a video clip, Google Search grounding, thinking level tuning, 512 to 4K output, or choosing between Flash, Pro, and Lite. Keywords: Gemini 3.1 Flash, Gemini 3.0 Pro, Gemini 3.1 Lite, Nano Banana 2, Nano Banana Pro, txt2img, img2img.
中文简介正在准备中。当前显示原文说明。
Use when generating, extending, or editing video with Gemini Omni models on Scenario via MCP: text-to-video, image-to-video from a first frame, reference-to-video keeping a character, product, or place consistent, appending footage to a clip, restyling footage by prompt (season, wardrobe, art style), native audio with dialogue and ambience, or picking between first-frame and reference conditioning. Keywords: Gemini Omni Flash, 1.1 Flash, Google, T2V, I2V, V2V, extend, subject consistency.
中文简介正在准备中。当前显示原文说明。
Flash — a drop-in CSS keyframe animation from Animate.css (Hippocratic-2.1, © Daniel Eden). No JS required. Honors prefers-reduced-motion. Use restrained; attribute Animate.css.
中文简介正在准备中。当前显示原文说明。
Plan and execute substantial multi-file builds, features, migrations, and refactors with Astra as orchestrator and DeepSeek V4.1 Flash as the native Codex implementation worker. Use for phased planning and delegated build execution, including existing Superpowers or GSD plans. Skip trivial edits and explicitly single-agent tasks. Worker children must not invoke this orchestration skill.
中文简介正在准备中。当前显示原文说明。
Keil MDK 工程构建工具，用于扫描 .uvprojx/.uvproj/.uvmpw 工程、枚举 Target、执行 build/rebuild/clean 并解析构建日志，返回可供 jlink/openocd 复用的产物路径。 flash 子命令仅作为兼容入口保留。当用户提到 Keil、MDK、uVision、UV4、 Target 枚举、编译、重建、清理、烧录、下载固件、flash 时自动触发，也兼容 /keil 显式调用。 即使用户只是说"编译一下"或"烧录到板子上"，只要上下文涉及嵌入式 Keil 工程就应触发此 skill。
中文简介正在准备中。当前显示原文说明。
OpenOCD 下载与调试工具，用于探针探测、固件烧录、Flash 擦除、GDB Server 启动、目标复位控制、 Telnet 在线调试（halt/resume/step/寄存器/内存/断点）、GDB 源码级调试，以及 Semihosting/ITM 输出捕获和底层查询。 当用户提到 OpenOCD、ST-Link、CMSIS-DAP、DAPLink、FTDI、烧录固件、擦除 Flash、GDB Server、 reset、interface/target/board 配置、openocd.cfg、在线调试、单步、断点、寄存器查看、 内存读写、semihosting 时自动触发，也兼容 /openocd 显式调用。 即使用户只是说"烧录一下"、"启动 GDB Server"、"擦除芯片"、"看看寄存器"、"单步调试" 或"抓一下 semihosting"，只要上下文涉及 OpenOCD 支持的开源调试器就应触发此 skill。
中文简介正在准备中。当前显示原文说明。
embeddedskills 的薄编排层，用于在当前 workspace 中发现工程、选择 build/flash/debug/observe 后端、串联 .embeddedskills/state.json，并聚合底层 skill 的结果。 当用户明确输入以下命令之一："一键构建烧录"、"自动诊断"、"串起 build -> flash -> debug -> observe" 或显式调用 /workflow 时触发。
中文简介正在准备中。当前显示原文说明。
Extract key concepts from any content and create spaced-repetition flashcards. Multiple formats: Anki-compatible, printable PDFs, interactive web.
中文简介正在准备中。当前显示原文说明。
メールとSlackから返信すべき項目・タスクを抽出する統合型スキル。 Gemini 3.0 Flashで文脈判定し、優先度と返信ドラフトを生成。 「受信箱チェック」「TODO確認」「返信すべきメッセージ」「メール確認」等のリクエストで発動。
中文简介正在准备中。当前显示原文说明。