В каталоге 185 367 навыков в 14 категориях.
规范整洁的项目文件夹整理。当任务涉及新建项目、整理已有项目结构、规整文件命名与版本时使用。规划 data、src、models、results、figures、docs、paper、ppt、patent、software-copyright...
Audit, plan, scaffold, and safely migrate research project structures across greenfield, existing Git/non-Git repositori...
Complete guide for Light Protocol on Solana - includes ZK Compression for rent-free compressed tokens and PDAs using zer...
科研伦理、学术规范与风险审查。在所有科研任务中默认检查学术不端、数据造假、图片重复使用、引用不规范、隐私泄露、版权、结论夸大、过度包装、论文代写、专利权属、软著材料不真实等风险(常驻,所有任务后台生效)。对论文、项目、软著、专利与比赛材料做...
Light 科研诚信与伦理全生命周期常驻红线门:在研究分诊、审批、采集、变更、分析、投稿、发布与出版后检查 学术不端/数据造假/统计自洽/结论夸大/幻觉与撤稿 引用/自我抄袭/隐私/版权/署名与 AI 披露/软著专利权属/论文工厂洗稿等风险...
对已确认可行的 idea 制定极其详细的研究方案、实验设计与执行规划。当用户的 idea 已通过 m04 审查、需要把 idea 拆成可执行可复现的完整科研流程时使用。覆盖研究目标、技术路线、数据流程、实验/消融/敏感性/鲁棒性/显著性检验...
Light 科研主线第 5 步·研究方案与实验设计:把 idea-critique 放行的 idea 与 data feasibility 拆成**能真执行、能写进论文、 能复现**的 question/estimand、实验矩阵与预注册包...
对执行出来的结果、实验数据、模型输出、图表结果进行详细专业深入的分析。当用户实验跑完、需要解读数据、问"这些结果说明什么"时使用。不只描述好坏,而是解释为什么、哪些结果证明方法有效、哪些暴露问题、哪些异常需排查、哪些规律可成为论文亮点、哪些...
Light 科研主线第 7 步·结果分析:不描述好坏、解释「为什么」,把每条结论**绑死到 claim + 证据强度**,并防 p-hacking。 何时用:实验跑完要解读结果 / 问「这些数说明什么」/ 要做显著性检验 + 效应量 + 置...
Review an author's completed or near-complete scientific manuscript, figures, tables, and supplements before submission,...
审稿意见模拟与返修回复。当用户需要在投稿前预审论文、或收到真实审稿意见后做返修时使用。模拟顶刊/顶会审稿人严格审稿,给出贡献评价、优点、缺点、必改问题、建议补充实验、拒稿风险、可能追问。收到真实意见后分析审稿人关注点、制定返修策略、逐条撰写...
Build auditable peer-review revision and author-response packages for Light stage 13. Use after receiving reviewer comme...
Use when lighting or rendering a PlayCanvas scene, covering lights, ambient and environment lighting, sky, shadows, tone...
自动反思与自我审查。每次完成任务后自动检查是否存在逻辑漏洞、事实错误、格式问题、表达不清、创新不足、引用不准、结果夸大、审美不统一、重复内容、结构混乱、不可执行等问题(常驻,所有任务收尾时生效)。不一次性给出粗糙结果,而是先自我审查与迭代后...
制作精美 PPT。当用户需要为论文、项目、竞赛、答辩、汇报、路演做幻灯片时使用。设计封面/目录/过渡/内容/图表/流程/时间线/对比/团队/结论/致谢等页。逻辑清晰、排版高级、审美统一、重点突出,按主题选风格(学术/科技/农业/医学/商务/...
Prepare, revise, and check Chinese software copyright registration materials from real software: function descriptions,...
Prepare China software copyright registration material drafts from a real software project: application-field worksheet,...
后端系统设计与数据库能力。当任务涉及系统架构、数据库设计、接口设计、权限/日志/异常/性能/部署时使用。设计 ER 图、数据表结构、接口文档、用户权限、数据流转、模块划分、API 规范、数据库索引、安全策略、部署方案,尤其适合科研系统、管理...
Design or modernize a software system from an evidence-backed current-state inventory through quality attributes, archit...
工具选择与多工具协同。根据任务自动判断适合用什么工具——搜索、Python、R、MATLAB、LaTeX、Word、Excel、PowerPoint、Visio、Origin、数据库、Git、前端/后端框架、绘图工具、文献管理工具等(常驻,...
根据目标期刊/会议/学校/比赛要求做 LaTeX 或 Word 排版并编译导出最终 PDF/Word。当用户需要套模板、排版、解决编译错误、导出论文时使用。处理标题层级、页边距、目录、摘要、关键词、公式、图表、算法伪代码、参考文献、附录、页...
Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11. Use when receiving a paper-writing manuscri...
投稿定位与期刊/会议匹配。当用户问投哪个期刊/会议、要评估录用可能性/录用概率、做投稿规划时使用。根据论文质量、方向、创新程度、实验完整性、语言水平、作者背景和预算,推荐中文/英文期刊、SCI/SSCI/EI/CCF/核心、国际/国内会议。...
Build evidence-bound journal or conference shortlists for Light stage 12. Use after typesetting delivers venue-handoff.j...
将科研方法图、机制图、流程图和模型架构参考图复现为可编辑的 Visio .vsdx,并导出预览、核查连线与文字。适合已有生图结果或论文参考图后的原生形状重建;不负责数据作图或单独生成生图提示词。
Draft, restructure, polish, translate, shorten, or consistency-check scientific manuscripts from author-provided evidenc...
Headless photo/RAW development with LightCraft (Lightroom-style develop controls, presets, export), provisioned on deman...
Lighter — Orderbook DEX on Arbitrum
Use when researching, backtesting, deploying, or running a supported one-time Lighter action through the Superior Trade...
Size verification to the change so results ship. Use when checking has started to loop, when a check is about to re-run...
Use when planning a Robinhood Chain Lighter strategy through Superior Trade, or when a config needs the venue name light...
Step-by-step guide for adding new pages to the Yew frontend
Step-by-step guide for adding new OAuth integrations to Lightfriend
Step-by-step guide for modifying database schema using Diesel migrations
Run Lighthouse audits and implement performance, accessibility, and SEO fixes
Run and interpret Google Lighthouse audits for performance, accessibility, best practices, and SEO; compare reports, dia...
Run Lighthouse performance audits against locally served pages and summarize key metrics. Use when the user asks to chec...
Run Google Lighthouse against a live URL (mobile + desktop), diagnose the performance/accessibility/SEO/best-practices f...
Optimize web applications to achieve 95%+ Lighthouse scores across all categories. Use when optimizing performance, acce...
Configures Lighthouse CI (`@lhci/cli`) to audit Web Vitals (LCP, INP, CLS) on every PR, asserts against canonical thresh...
Use when optimizing website performance. Run Google Lighthouse audits via MCP to measure metrics, identify bottlenecks,...
Runs Google Lighthouse audits using Playwright for SEO, Performance, Accessibility, and Best Practices scoring. Supports...
The Lighthouse User Incubation framework allows product teams within large organizations to operate like "starups" by cr...
Cinematic and game lighting in Blender including three-point lighting, HDRI, horror lighting, volumetrics, rim lighting,...
Light a Three.js WebGPU scene: sun and sky fill, fixtures versus emission, point and spot light budgets, and r187 Cluste...
Check reported lighting quantities and results in supplied simulation PDFs without adding repeated calculation surfaces....
Complete Lightning Network lifecycle. Audits channels, routing, invoices. Plans capacity, executes rebalancing, verifies...
Salesforce Lightning Web Components Winter '26 and 2025 features
Use when implementing Lightning address functionality - provides complete patterns for resolving Lightning addresses to...
Review Bitcoin Lightning Network protocol designs, compare channel factory approaches, and analyze Layer 2 scaling trade...
Technical reference on Lightning Network channel factories, multi-party channels, LSP architectures, and Bitcoin Layer 2...
Explain Bitcoin Lightning channel factories and the SuperScalar protocol — scalable Lightning onboarding using shared UT...
Use when implementing BOLT11 Lightning invoice decoding - provides complete patterns for decoding invoice amounts, valid...
Use when implementing a standalone Lightning wallet using Cashu mints - provides complete patterns for minting (receivin...
Fast headless browser for fetching real web pages and scraping content. 9x less memory than Chrome, instant startup. Use...
Lightpanda browser, drop-in replacement for Chrome and Openclaw default browser - faster and lighter for tasks without g...
Expert skill for Lightpanda — the headless browser built in Zig for AI agents and automation. 9x less memory, 11x faster...
KINTSUGI deconvolution: True lightsheet PSF calculation to fix horizontal banding artifacts. Trigger: deconvolution arti...
Lightweight 3D effects for decorative elements and micro-interactions using Zdog, Vanta.js, and Vanilla-Tilt.js. Use thi...
Efectos 3D ligeros y decorativos con Zdog (pseudo-3D), Vanta.js (fondos animados WebGL) y Vanilla-Tilt (tilt parallax en...
Lightweight Kubernetes provides container orchestration for resource-constrained edge and IoT devices. It uses minimal r...
Add lightweight application monitoring, health checks, and request metrics with minimal dependencies and operational ove...
Build a routed pivot with ligolo-ng: a TLS agent on the foothold connects out to ligolo-proxy, which creates a TUN inter...
离婚协议与冷静期:流程、要点与避坑。精品指南。
李继刚(Prompt布道师/Prompt之神)的AI提示词创作思维——Lisp压缩美学+哲学底色+结构化写作+极简主义。 触发词:「李继刚视角」「像李继刚那样写」「Prompt之神」「汉语新解」「压缩美学」「ljg-skills」「Lisp...
Overlay the branded like/subscribe CTA animation — channel gem avatar + @C0BALT_CUT handle + subscribe/like/bell click c...
Use when phrasing a forward-looking statement, the user asks "how likely is X?" / "what's the likelihood?", or the trade...
Path-grounded multi-agent orchestration using the Liku directory hierarchy (skills.xml inheritance, todo.md + LikuErrors...
李逵(古典虚构)认知与表达框架(压缩蒸馏):黑旋风直球、忠诚与滥杀张力 触发:水浒传 等。反面教材;禁止暴力教唆
Parse a Likutei Peshatim (HTC weekly Torah newsletter) email into calendar events and publish them to /calendars. Use wh...
"Lima in Container Runtime - cloud native architecture, patterns, pitfalls" and best practices
Use this skill when the user mentions LimaCharlie or wants to work with endpoint detection, cloud security monitoring, d...
Use this skill when new users want to get started with LimaCharlie, set up their first organization, or begin collecting...
Use this skill when users need interactive HTML reports, dashboards, charts, or visualizations for LimaCharlie data. You...
Use when using the LimboAI addon — behavior trees and hierarchical state machines (C++ GDExtension) with a visual editor...
Lime design system rules for this project's UI. Use when building or changing any screen, component, form or style, when...
Provides comprehensive guidance for Lime ECharts including chart creation, configuration, data visualization, and intera...
LIME-based local explanation skill for individual predictions across tabular, text, and image data.
Use when working on Limiara's Rust platform kernel, plugin architecture, Contacts plugin, tenancy/RLS security, Wasm plu...
Transform supplied photographs or written scene concepts into quiet, wistful, soft-focus journey photography with cinema...
Installs, configures, and troubleshoots the Limine bootloader on Arch Linux and other Linux systems — limine.conf syntax...
Show Claude and Codex subscription usage windows in one colored screen, live where possible. Use when the user asks "lim...
Develop a limit-based product strategy with convergence milestones, acceleration levers, assumptions, and phased executi...
查询涨跌停池。接口:GET /api/v1/market/data/limit-list。所有请求必须设置 FTSHARE_API_KEY。
利用上限(5 時間の区切り・週の上限・モデル別の上限)で止まったセッションを、解除後に同じ窓で自動再開させる仕組みの状態を見る・止める・説明する。「上限で止まったら再開して」「自動再開の予約を見せて」「自動再開を止めて」「limit-res...
查询涨停简报。接口:GET /api/v3/market/data/limit-up-reports/briefs。所有请求必须设置 FTSHARE_API_KEY。
当有一条公式、标度律或模型结果,想在相信它之前查它在极限下还讲不讲得通时使用。先找出控制参数与无量纲组,挑最小一组有用的极限,在动手算之前先写下物理上应该发生什么,再做数学化简两相对照;专抓在某个极限下发散、变号、或丢掉已知特例的表达式。m...
Use when recalling conversations from Limitless Pendant, finding what was discussed in meetings, searching lifelogs, or...
Query Limitless Pendant lifelogs - conversations, meetings, and ambient recordings
Problem-solving strategies for limits in real analysis
Problem-solving strategies for limits colimits in category theory
Usar al detectar código duplicado que debe consolidarse en una sola implementación
林冲(古典虚构)认知与表达框架(压缩蒸馏):隐忍到爆发、体制内小人物悲剧… 触发:水浒传 等。虚构;非现实报复教程
Use when the user runs /lindir <url> or /lindir approve <url>. Reads a pull request or merge request and renders a five-...
Control and inspect Chrome browser using Chrome DevTools Protocol - navigate pages, debug network requests, analyze perf...
Configure Lindy AI CI/CD integration with GitHub Actions and testing. Use when setting up automated testing, configuring...
Troubleshoot common Lindy AI errors and issues. Use when encountering errors, debugging agent failures, or resolving int...
Core Lindy workflow for creating and configuring AI agents. Use when building new agents, defining agent behaviors, or s...
Core Lindy workflow for automating tasks and scheduling agents. Use when setting up automated workflows, scheduling agen...
Optimize Lindy AI costs and manage usage efficiently. Use when reducing costs, analyzing usage patterns, or optimizing b...