Loading...
Loading...
Found 2,026 Skills
Baidu FaMou algorithm skills for efficient algorithm self-evolution. Provides experiment management and visualization capabilities to help optimize complex algorithms. Use when user needs algorithm optimization or experiment management.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Generate new screens from text prompts or images, edit existing screens with prompts and design system tokens, and generate design variants using Stitch MCP. Includes prompt enhancement pipeline, design mappings, professional UI/UX terminology, design tokens and theme system capabilities.
Extract self-contained static HTML from a built web application or React components by inlining CSS and images. Use this skill whenever you need to capture a specific UI state, share a static version of a page, or prepare assets for Stitch upload, even if the user just asks to 'save the HTML' or 'mock the view'.
Generate or update project memory for AI agents — default to AGENTS.md, support agent-specific targets such as CLAUDE.md, and keep sibling memory files synchronized while capturing stable architecture, conventions, and operational knowledge
Huawei Ascend NPU natural language management skill, supporting both local direct connection and SSH remote modes. Provides comprehensive npu-smi command capabilities including device queries, configuration management, firmware upgrade, vNPU virtualization, certificate management, and compute power testing (FLOPS). Enables remote management and monitoring of Ascend NPU devices with real-time metrics tracking. Use this skill when the user wants to: (1) query NPU device status and health, (2) monitor temperature, power, memory/HBM utilization, (3) configure ECC settings and fan modes, (4) perform firmware upgrades, (5) manage vNPU virtualization, (6) run compute power tests, (7) check certificate information. Trigger: user mentionsnpu', 'ascend', 'NPU', 'Ascend', 'temperature', 'power', 'HBM', 'firmware', 'upgrade', 'vNPU', 'virtualization', 'certificate', 'FLOPS', 'compute', 'health', 'memory', 'utilization', 'ECC', 'fan', '昇腾', '昇腾卡', '昇腾状态', '显存', '算力', '设备查询', 'NPU监控'"
拆解对标账号 / 竞品内容——丢一个链接进来,自动识别平台(抖音/小红书/B站/YouTube/公众号)和粒度(单条 or 整个账号),抓取内容后输出三件套:可复用爆款公式、画面+口播逐段拆解、人设与内容定位,并自动存档到 benchmarks/。短视频自动下载 + 转写口播 + 抽视觉帧(contact sheet 多模态读图),不只看 caption。当用户说「拆解这个账号/视频/笔记」「分析对标/竞品」「这条为什么火」「给链接拆内容」「teardown」「看看别人怎么做的」时使用。抓不到内容会引导粘贴文案/字幕,绝不直接报错。
Use when the user reports connectivity issues, access failures, DNS resolution problems, or any error with Twingate. Activate for: "can't connect", "not working", "resource not found", "access denied", DEAD connector, DNS not resolving, device trust blocking access, security policy issues, P2P failure, or any Twingate troubleshooting or diagnostic request. Also activate for symptom-shaped and error-string queries: exact client error text ("unknown network name", "too many open files", "setup wizard ended prematurely", "unable to join network"), OS-specific client bugs on Windows, macOS, Linux (Fedora, Ubuntu, NixOS), ChromeOS, or Android Auto; client crashes, freezes, or unresponsiveness; version-specific regressions (e.g. a specific client build number misbehaving); TAP adapter or virtual network adapter issues; device posture / screen lock / disk encryption check failures; third-party AV, EDR, VPN, or DNS-filtering software conflicts (CrowdStrike, Zscaler, Elastic AV, Avast, consumer VPNs); packet capture, system report, or client/connector log collection; and engaging or escalating to Twingate technical support.
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
Index and router for the C-level advisory bundle: 33 skills covering 14 C-suite roles, orchestration, cross-cutting capabilities, and culture. Use when exploring what the c-level-advisor bundle contains, deciding which advisor skill fits a question, or finding the entry points (cs-onboard interview, chief-of-staff routing, board-meeting protocol).
Like sp-grill-with-doc (domain-aware grilling, glossary sharpening, inline CONTEXT.md/ADR capture) BUT continues into the superpowers planning pipeline by handing off to sp-writing-plans at the end. Use ONLY when the user wants both the grilling AND a written implementation plan produced afterward; if they want grilling/docs alone, use sp-grill-with-doc instead. The superpowers plugin is needed two hops downstream, by sp-writing-plans' own execution skills, not by this Skill.
Session retrospective that turns THIS session's problems into durable, correctly-routed improvements. Trigger on /reflect, "what did we learn", "retro", "retrospective", "improve our workflow", "how do we not repeat this", or after a painful debugging round. It captures the DELTA (what went wrong, what was slow, what got corrected) and routes each lesson to where it will fire again: an owned skill, a project CLAUDE.md, a cross-project GOTCHAS.md file, or memory. NOT a what-was-done summary (that is invoice-generator) and NOT a single bug's root-cause record (that is post-mortem).