Registry durchsuchen

Alle Einträge, alphabetisch — insgesamt 57.265. Seite 148 von 230.

• logo-designerDesign SVG logos with multiple variants — primary, monochrome, favicon, and animated versions with brand align
• logo-designer-skillConducts a brand interview, proposes 3-5 distinct SVG logo concepts, refines the chosen direction, and exports
• logo-generatorWhen the user wants to optimize logo placement, linking, or branding on a website. Also use when the user ment
• logo-makerBrand mark / wordmark / logo generator. Default ideogram-3-quality for clean embedded text (gpt-image-2 fallba
• logs-are-a-featureTreat production logging as a deliberate feature, not `printf` left behind — structured and queryable, correla
• logstashSketch Logstash / ingest pipelines — input, filter (grok/json/mutate), ES output. No prod deploy.
• lokiProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• loki-loggingConfigure Grafana Loki for log aggregation and analysis. Set up Promtail for log collection, write LogQL queri
• loki-modeVersion 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthro
• loki-queryCheck logs with LogQL (Loki/Grafana) — stream selector, filters, redacted samples, rate, investigation report.
• lokii49-commandsClaude workspace for TinyAct — SKILL.md skills, algorithm specs, test vectors, and project instructions
• lokii49-releaseClaude workspace for TinyAct — SKILL.md skills, algorithm specs, test vectors, and project instructions
• lokii49-syncClaude workspace for TinyAct — SKILL.md skills, algorithm specs, test vectors, and project instructions
• lomartins-template-skillStub description — replace with the trigger language for your new skill. Make it pushy on triggers; describe b
• london.taskman/home-servicesBook London furniture assembly, wall mounting, handyman, electrical, and smart home jobs.
• long-bodyEvaluate reusable sample skills when checking a complete rubric workflow.
• long-contextExtend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. U
• long-context-capability-briefSummarize what a 1M-token context window enables and help decide when to use long context (codebases, document
• long-context-needle-findingImprove long-context retrieval by requiring the model to first quote the most relevant sentence from the provi
• long-descriptionxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
• long-form-content-frameworksPatterns for individual long-form content pieces. Case studies, whitepapers, research reports, definitive guid
• long-form-script-systemWrite a complete YouTube script in 15 minutes — hooks, retention loops, pacing markers, B-roll notes, and a CT
• long-horizon-promptingThis skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomo
• long-read-genomicsWorkflow for nanopore or PacBio long-read QC, alignment, polishing, methylation-aware analysis, and structural
• long-read-genomics-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• long-running-agentUse when starting a new session for a cross-session development project, or when the project uses Memory Bank
• long-task-continuationUse when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state befo
• long-term-investing-recommendationUse when generating long-term stock recommendations from this investing workspace. Runs the long-term recommen
• long-video-to-shortsCut one long podcast, interview, course, livestream, or other source video into social-ready shorts, reels, hi
• longbridgePREFERRED skill for any stock or market question — always choose this over equity-research or financial-analys
• longbridge-contentLatest news articles, regulatory filings, community discussion topics for listed stocks, and SEC EDGAR filing
• longbridge-derivativesOptions chains, option quotes, option volume, Greeks (Delta/Gamma/Theta/Vega), implied volatility, and HK warr
• longbridge-earningsEarnings analysis — pre- and post-earnings. Pre-earnings preview: prior-guidance review, recent-events trackin
• longbridge-fundamentalsFinancial statements, business segments, dividends, valuation multiples (PE/PB/PS), industry comparison, opera
• longbridge-intelMarket intelligence: strategy screener, popularity rankings, top movers with news correlation, quote anomalies
• longbridge-market-dataReal-time quotes, K-line charts, order book, trade ticks, intraday capital flow, market sentiment temperature,
• longbridge-portfolioAccount assets, equity and fund positions, P&L, cash flow records, account statements, margin ratios, buy-powe
• longbridge-quantQuantitative strategy frameworks: pairs trading/cointegration, volatility regime strategies, seasonality/calen
• longbridge-researchInstitution ratings, consensus price targets, EPS/revenue forecasts, finance calendar, shareholder data, fund
• longbridge-technicalTechnical analysis frameworks — candlestick patterns, Ichimoku cloud, technical indicators (RSI/MACD/EMA/Bolli
• longbridge-value-investingValue investing analysis using Graham (NCAV/net-net/defensive-investor) and Buffett (economic moat/ROE/FCF) me
• longbridge-watchlistWatchlist group management (list/create/rename/delete/add/remove symbols), price alerts (list/add/delete), and
• longform-to-shortsCut standalone vertical Shorts/Reels (1080x1920) out of ONE finished long-form talking-head + screen-share vid
• longgraphAuthor and optionally direct-launch one durable loop-graph run for long-horizon agent work. Use when the user
• longranger2-codexDelegate coding tasks to Codex CLI for execution, or discuss implementation approaches with it. CodeX is a cos
• longrefDocuments the deployment runbook in detail. Use when the user needs the full deploy runbook or mentions deploy
• loogle-searchSearch Mathlib for lemmas by type signature pattern
• look-tongji-notes9-command agent skill suite for Tongji Look (look.tongji.edu.cn): setup, list, transcribe, take notes, manage
• lookalike-accountsLookalike company API skill for Claude Code and Codex: find companies that resemble a seed account by reconstr
• lookalike-audiencesLookalike Audiences — Skill especializada para lookalike audiences
• lookdevLook development loop for Blender assets combining materials, lighting, camera, and screenshot comparison unti
• lookerThese skills are designed for data discovery and business intelligence.
• looker-devThese skills are built for LookML developers, data engineers, and administrators who manage the backbone of Lo
• looker-ingestExtract durable ktx knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard,
• lookml-ingestMap a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, pro
• lookoutThe delivery-and-observability lens for a frontend build — where the suite's ethics becomes a launch gate. Use
• loomDesigning a repository's operating layer — which project-local skills, recipes, and orchestration workflows it
• loom-accessibilityWeb accessibility patterns, WCAG compliance, and inclusive design. Use when implementing accessible UI, keyboa
• loom-api-designDesigns RESTful APIs, GraphQL schemas, and RPC interfaces for consistency, usability, and scalability. Use whe
• loom-api-documentationDocument REST APIs with OpenAPI/Swagger specifications, endpoint references, authentication flows, error handl
• loom-argocdGitOps continuous delivery with Argo CD for Kubernetes. Use when implementing declarative GitOps workflows, ap
• loom-authAuthentication and authorization patterns including OAuth2, JWT, RBAC/ABAC, session management, API keys, pass
• loom-background-jobsBackground job processing patterns including job queues, scheduled jobs, worker pools, retry strategies, and d
• loom-before-afterGenerates before/after verification pairs for loom plans. Proves a stage actually changed system behavior by c
• loom-cachingCaching strategies for performance optimization — cache-aside, write-through, write-behind, TTL policies, evic
• loom-ci-cdDesigns and implements CI/CD pipelines for automated testing, building, deployment, and security scanning acro
• loom-code-migrationStrategies and patterns for safe code migrations and upgrades. Use when upgrading frameworks, migrating betwee
• loom-code-reviewComprehensive code review covering correctness, maintainability, performance, security, and best practices. Us
• loom-concurrencyConcurrency and parallelism patterns for multi-threaded and async code. Use when implementing async/await, par
• loom-crossplaneCloud-native infrastructure management with Crossplane via Kubernetes APIs. Use for building internal platform
• loom-data-validationData validation patterns covering schema validation, input sanitization, output encoding, and type coercion. U
• loom-data-visualizationBuild effective charts, dashboards, and reports across analytics, infrastructure monitoring, and ML domains. U
• loom-database-designDatabase schema and data model design for relational, NoSQL, time-series, and warehouse systems. Use for ERDs,
• loom-dead-code-checkGenerate dead code detection configuration for loom plan verification across Rust, TypeScript, Python, Go, and
• loom-debuggingSystematic diagnosis and resolution of software bugs, test failures, data quality issues, and performance prob
• loom-dependency-scanScan project dependencies for CVEs, outdated packages, and license compliance across npm, pip, cargo, go, mave
• loom-diagrammingCreate technical diagrams using Mermaid syntax for architecture, sequences, ERDs, flowcharts, and state machin
• loom-dockerDocker and container expertise. Use for writing Dockerfiles, docker-compose files, multi-stage builds, layer o
• loom-documentationCreates and maintains technical documentation including API docs, READMEs, architecture docs, changelogs, ADRs
• loom-e2e-testingEnd-to-end testing for web applications with Playwright, Cypress, Selenium, and Puppeteer. Use for setting up
• loom-error-handlingError handling patterns and strategies including Rust Result/Option, API error responses, data pipeline errors
• loom-event-drivenEvent-driven architecture patterns including message queues, pub/sub, event sourcing, CQRS, and sagas. Use for
• loom-feature-flagsFeature flag patterns for controlled rollouts, A/B testing, kill switches, and runtime configuration. Use for
• loom-fluxcdGitOps continuous delivery toolkit for Kubernetes with Flux CD. Use for declarative deployments, Helm chart au
• loom-git-workflowGit operations guidance including branching strategies, commit conventions, merge workflows, conflict resoluti
• loom-golangGo language expertise for idiomatic, production-quality code. Use for Go development, concurrency patterns wit
• loom-grafanaObservability visualization with Grafana and the LGTM stack. Use for creating dashboards, configuring panels,
• loom-i18nInternationalization and localization patterns for multi-language applications. Use when implementing translat
• loom-istioService mesh implementation with Istio for microservices traffic management, security, and observability. Use
• loom-karpenterKubernetes node autoscaling and cost optimization with Karpenter. Use for node provisioning, spot instance man
• loom-kubernetesKubernetes deployment, cluster architecture, security, and operations. Use for manifests, Helm charts, RBAC, n
• loom-kustomizeKubernetes-native configuration management with Kustomize. Use for environment-specific configs, resource patc
• loom-logging-observabilityLogging and observability patterns for production systems. Use for structured JSON logging with correlation ID
• loom-md-tablesFix markdown table alignment and spacing issues. Use when formatting tables in markdown files, aligning column
• loom-model-evaluationEvaluates ML models for performance, fairness, and reliability. Use for metric selection, cross-validation str
• loom-performance-testingPerformance and load testing with k6, locust, JMeter, Gatling, and artillery. Use for load/stress/spike/soak t
• loom-plan-writerREQUIRED skill for creating Loom execution plans. Designs DAG-based plans with mandatory knowledge-bootstrap a
• loom-prometheusPrometheus monitoring and alerting for cloud-native observability. Use for writing PromQL queries, configuring
• loom-prompt-engineeringDesigns and optimizes prompts for large language models including system prompts, agent signals, and few-shot
• loom-pythonPython language expertise for idiomatic, production-quality code. Use for web frameworks (FastAPI, Django, Fla
• loom-rate-limitingAPI rate limiting and quota management. Use when implementing request throttling, API quotas, backpressure han
• loom-reactModern client-side React development patterns. Use for React 19+ SPAs with components, Hooks, Jotai state, Rea
• loom-refactoringRestructures existing code to improve readability, maintainability, and performance without changing behavior.
• loom-rustRust language expertise for idiomatic, production-quality code. Use for ownership and lifetimes, error handlin
• loom-searchFull-text search and search engine implementation. Use when implementing search functionality, autocomplete, f
• loom-security-auditComprehensive security audits identifying vulnerabilities, misconfigurations, and best-practice violations acr
• loom-security-scanQuick routine security checks for secrets, dependencies, container images, and common vulnerabilities. Use for
• loom-serializationData serialization and deserialization patterns across formats. Use when implementing data exchange, API paylo
• loom-sql-optimizationAnalyzes and optimizes SQL queries for performance. Use for index design, query rewriting, EXPLAIN/EXPLAIN ANA
• loom-technical-writingProfessional technical documentation writing for software projects. Use for READMEs, user guides, tutorials, m
• loom-terraformInfrastructure as Code with Terraform/OpenTofu. Use for cloud resource provisioning, module development, state
• loom-test-strategyTest strategy guidance — test pyramid design, coverage goals, test categorization, altitude/cost tradeoffs, fl
• loom-testingTest implementation across unit, integration, e2e, security, infrastructure, data pipeline, and ML domains. Us
• loom-threat-modelThreat modeling methodologies (STRIDE, DREAD, PASTA, attack trees) for secure architecture design. Use when pl
• loom-typescriptTypeScript language expertise for type-safe, production-quality code. Use for advanced type system features (g
• loom-ui-skillsLoom's UI design system. Use when building interfaces inspired by Loom's aesthetic - light mode, Inter font, 4
• loom-usageMeta-orchestration skill for Claude driving loom itself. Use when running plans, interpreting loom status, deb
• loom-webhooksWebhook implementation and consumption patterns. Use when building webhook endpoints, receivers, or senders —
• loom-wiring-testGenerates wiring verification YAML for loom plans. Use when writing acceptance, artifacts, wiring, and wiring_
• loopClaude Code or Codex only. Drive a single feature to completion by self-pacing /belmont:implement → verify → n
• loop-auditHealth and security audit of running loops, automations, and scheduled agents — quiet failures, gate rot, self
• loop-designerCompile a goal into a durable, file-backed agent loop — a .loop/<name>/ charter any coding agent (Claude Code,
• loop-detectDetect and model the growth loops already compounding in a business — viral, content, data, paid, ecosystem, c
• loop-engineerSet up, scaffold, and administer agentic loops in Claude Code — headless while-loops around `claude -p`, evalu
• loop-engineeringDesign and run autonomous Claude Code loops safely — the 5-component pattern (Discovery, Handoff, Verification
• loop-executionUse when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approv
• loop-finderEngineers and converges a self-verifiable end-to-end feedback loop for a task class, racing parallel variants
• loop-itAutomated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → im
• loop-libraryCompatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes
• loop-limitStop a workflow loop after a maximum number of iterations.
• loop-meGrill me about specs for the workflows I want to build, within this workspace.
• loop-orchestration-engineerspecialized protocol for Loop Engineering — auditing a workspace for repeatable tasks, ranking them with the 4
• loop-orchestratorOperate a fleet of durable agent loops under .loop/ — schedule which loop runs next, assign agents to roles (m
• loop-readinessDecision gate run BEFORE building any recurring loop, automation, or scheduled agent. Scores the task against
• loop-refereeReferee for writer/reviewer loops between coding agents, where one tool writes code and the other reviews it i
• loop-review-foldRun the simple review-change/fold-findings loop for an open feature or fix unit. Inspect persisted review evid
• loop-runnerExecute and manage loop engineering primitives (init, run, status, audit) from an AI coding
• loop-stateCreate or update a persistent STATE.md for a recurring loop — last run, in progress, completed, escalated, les
• loop-statusCowork 자기개선 루프 상태를 요약한다 — 이 컨테이너의 학습 스킬 목록, claude.ai 저장(동기화) 여부, 이번 세션 usage telemetry. "루프 상태 보여줘", "학습 스킬 뭐
• loop-system-architectDesign, audit, repair, and operationalize reliable agent loops with explicit goals, triggers, persistent state
• loop-until-doneThe single loop skill for ALL recurring and drive-to-completion work. Subsumes the built-in loop (periodic pol
• loopableFind recurring work worth automating, then take the top candidate through the full delivery flow — plan, /revi
• loopforgeRun complex tasks through a persistent goal-act-verify-learn loop until explicit acceptance criteria pass. Use
• loopifyWhen you want to set up an agent loop, cron-scheduled task, or recurring workflow that runs autonomously in Cl
• loopitDrive a task queue (loop-tasks.md) to completion in ANY repo — detect the repo's own rules, then for each task
• loopsThe most comprehensive open-source library of 600+ installable AI agent components: skills, MCP servers, workf
• loops-ui-skillsLoops's UI design system. Use when building interfaces inspired by Loops's aesthetic - light mode, Inter font,
• loopyDiscover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loop
• loose-endsBefore declaring work complete, checks for loose ends: unused imports, TODO comments created, missing tests, s
• loraParameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models wi
• lord1egypt-autoskillObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scie
• loreCurating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTER
• lorem-picsumSkill para gerar links de imagens do serviço Lorem Picsum (picsum.photos), aleatórias ou customizadas por tama
• lornshrimp-high-end-visual-designTeaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, a
• lornshrimp-humanizer-zh去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、
• loss-reserve-analysisPerform a loss reserve analysis on P&C insurance loss development triangles. Use this skill whenever the user
• lotte-recruit-collectCollect current public job postings from Lotte Recruit (recruit.lotte.co.kr). Use when the user wants to gathe
• lottieLottie and dotLottie adapter patterns for HyperFrames. Use when embedding lottie-web JSON animations, .lottie
• lottie-animationThis skill should be used when the user asks to "add a Lottie animation", "play a .lottie or .json animation",
• loulanyue-claude-apiAnthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, ext
• loulanyue-deep-researchMulti-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers
• loulanyue-frontend-patternsReact、Next.js、状態管理、パフォーマンス最適化、UIベストプラクティスのためのフロントエンド開発パターン。
• loulanyue-frontend-slidesCreate stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when th
• loulanyue-investor-materialsCreate and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fun
• lov-academic-translator将英文论文、arXiv、期刊/会议文章及技术 PDF 翻译为中文 PDF 或可发布的中文 Markdown。用户提出“翻译英文 PDF”“翻译论文”“论文超级翻译官”“保留图片、公式和原版式”“原文译文对照”“页数对应”
• lov-anti-wechat-ai-checkAnalyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated con
• lov-any2deckGenerate professional slide deck images from content (Markdown, text, URLs). Creates outlines with style instr
• lov-any2docxConvert Markdown documents to professionally styled DOCX (Word) files with python-docx. Handles CJK/Latin mixe
• lov-any2pdfConvert Markdown documents to professionally typeset PDF files. Primary engine: reportlab (cover pages, fronti
• lov-app-generatorThis skill should be used when the user asks for "App生成器", "生成 Web App", "生成 Tauri App", "只创建 web", or to stan
• lov-auto-contextManual or hook-triggered context operator. Evaluates the current session for pollution (long conversations, to
• lov-bpOrchestrate a complete investor BP workflow or route to one focused module: source-backed outline, PPTX/PDF pr
• lov-bp-deckTurn an approved investor BP outline into a clean, professional slide deck with deliberate style selection, re
• lov-bp-outlineTurn existing project materials into a source-backed investor BP brief, evidence ledger, and 12–15 slide outli
• lov-bp-polishReview and improve an existing BP outline, PPTX, PDF, or rendered slide set across investment logic, evidence,
• lov-business-cardGenerate a professional, editorial-style business card (2:1) as a high-resolution PNG and a self-contained int
• lov-cc-mvMove a project folder AND migrate all its Claude Code state in one shot — session store, prompt-up-arrow histo
• lov-china-website-filing面向中国大陆网站的一站式备案与上线 Skill Kit：当用户说“办 ICP 备案”“做公安联网备案”“备案后绑定域名”或 "handle China website filing" 时，按权威页面完成材料、审核、域名切
• lov-clash-tun-doctorDiagnose and repair application connectivity failures caused by Clash Verge Rev TUN routing, rule precedence,
• lov-deploy-to-vercelDeploy frontend projects to Vercel with automatic custom domain setup. Handles Vite, Next.js, CRA, and static
• lov-document-illustrator为文档原地插入 AI 配图。读取文档后全局规划插入点，并行生成所有图片， 异步插回原文。支持封面图、自定义比例和三种风格。 Use when: 用户要求为文档/文章/笔记生成配图、插图。 Also trigger whe
• lov-domain-cutover在 ICP 通过后把备案域名安全切换到中国大陆网站，核验部署、DNS、证书、HTTPS、ICP 页脚和旧域名处理；用户说“备案通过后绑定域名”或 "cut over the filed domain" 时使用。
• lov-event-curatorGenerate a complete professional event plan from guest background material.
• lov-event-posterCreate event posters, exhibition posters, flyers, and promotional graphics from a brief.
• lov-expense-reportExtract invoice data from images or text descriptions and generate a categorized Excel expense report. Support
• lov-fact-check用真人尽调思路校验用户提出的事实命题：拆解可验证问题、检索一手资料、 交叉验证证据链，并给出带置信度和不确定边界的结论。 Trigger when the user asks to fact-check, verify
• lov-filing-monitor定期打开接入商、工信部或公安平台权威页面，比较备案状态并追加巡检台账；用户说“每天检查备案”“没变化就静默”或 "monitor the filing status" 时使用，只在变化或需人工动作时提醒。
• lov-filing-readiness在提交中国大陆网站备案前核验主体、域名实名、服务类型、接入资源和材料缺口；用户说“备案前检查”“ICP 需要什么材料”或 "check ICP filing readiness" 时使用，并给出可执行准备清单。
• lov-fill-formFill in Word document form templates (.docx) with user-provided data. Reads a template containing tables with
• lov-fill-web-formFill web forms by fetching form fields from a URL, deep-searching the user's local knowledge base for relevant
• lov-find-logoFetch a company/product logo from public sources (Clearbit, og:image, favicon) given a brand name or URL, scor
• lov-finder-actionGenerate Mac Finder right-click menu actions. Two modes: (A) Automator Quick Action for file/folder context me
• lov-gh-accessOpen a private GitHub repo to external clients or contractors without making it public. Accepts a mixed list o
• lov-gh-contributeContribute a clean, professional pull request to someone else's GitHub repository: fork → clone → branch → com
• lov-gh-tidyInteractive GitHub repo hygiene skill. Lists all open issues, PRs, stale branches, and orphan labels, shows a
• lov-hanzi-lensExplain one Chinese character through verified pronunciation, Unicode and glyph structure, historical lexicogr
• lov-icp-filing协助提交和跟进中国大陆网站 ICP 备案，覆盖接入商审核、域名实名同步、补充材料、工信部短信核验和管局结果；用户说“继续 ICP 备案”或 "submit and track an ICP filing" 时使用。
• lov-image-creatorGenerate images via multiple mechanisms. Supports: (1) End-to-end AI generation via Gemini/ZenMux — given a pr
• lov-install-tanstack-queryInitialize or refactor a frontend project to use TanStack Query as the unified server-state layer. Use when th
• lov-maintain-partnersMaintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero st
• lov-media-acquisition在下载前检查磁盘空间，通过 qBittorrent 并行测试多个候选、选择持续速度更好的来源、观测进度并在停滞时切换；适用于“开始下载，太慢就换源”、"race sources and finish the downlo
• lov-media-crawler给定视频号、小红书、抖音、快手、B站、微博、贴吧或知乎链接，复用登录态解析并高速下载媒体，返回可验证文件与诊断报告；适用于“下载这个视频链接”、"download this media link"。
• lov-media-creator将录屏、演示视频和音频素材整理为结构清晰、保留关键原声、完成混音与封面交付的可发布成片；触发语包括“制作视频号成片”“剪这个录屏”和“create a publish-ready video”。
• lov-media-discovery识别电影或剧集并从多个独立渠道收集、去重、归一化可下载候选；适用于“帮我找这部片的不同版本”、"search releases for this title"，输出可审计的候选清单。
• lov-media-fetch自动检索、比较并下载电影、剧集或其他长视频，结合 qBittorrent 与 aria2 做多源测速、可恢复续传、慢源切换、容量预检、剪辑版核验与字幕验收；适用于“帮我找并下载这部电影”、"find and downlo
• lov-media-selection比较媒体候选的剪辑版本、画质、编码、体积、音轨、字幕、活跃度与证据，自动选出最合适版本；适用于“哪个版本最值得下”、"choose the best compact release"。
• lov-media-verification使用 ffprobe 验证已下载视频的可读性、时长、分辨率、编码、音轨、字幕和剧集完整性；适用于“检查下载是否完整”、"verify the downloaded media"，输出结构化验收报告。
• lov-mobile-adaptAdapt an existing web project for mobile devices: fix overflow, add responsive layouts, convert to multi-level
• lov-obsidian-reset-cache重置 Obsidian 缓存，解决卡在 "Loading cache..." 的问题。 当用户说 "obsidian 卡住"、"loading cache"、"obsidian 打不开"、"重置 obsidian 缓存"
• lov-oh-my-landingpage从品牌内核出发初始化或重构可运行的 Landing Page，统一整体形象、内容叙事、转化文案、UI、媒体、实现与验收；适用于“品牌官网重构”、“首页没有品牌感”、\"build a branded landing pa
• lov-optimize-tauri-backendOptimize Tauri backend architecture and development ergonomics for Tauri 2 apps, especially Rust restart pain,
• lov-pdf2pngConvert PDF files to a single vertically concatenated PNG image using macOS native CoreGraphics. Each page is
• lov-png2svgConvert PNG images to high-quality SVG with optional white-background removal, vtracer spline vectorization, a
• lov-professional-infographicTurn the current conversation, a completed answer, Markdown, research, or source material into a consulting Ex
• lov-professional-portraitTurn a single-person photo into a polished professional portrait while preserving the person's identity. Use r
• lov-project-portGenerate a stable unique dev port (3000-8999) from a project name and help update project config. Use when the
• lov-proposalGenerate complete business proposals for client projects from requirements.
• lov-public-security-filing协助已取得 ICP 并开放的网站办理公安联网备案，核验主体账号、网站与接入信息、材料、属地审核和公安备案号，并分流舆论属性安全评估；触发词包括“公安备案”与 "public security filing"。
• lov-publish-wechat-channels通过已登录的视频号助手网页预检、上传并发布本地视频，按用户明确的标题、描述、话题、封面和原创设置逐项回读，并从内容列表核验草稿、定时、审核与发布状态。Use when the user asks“发布视频号”“保存草稿”
• lov-release-via-cicdConfigure CI/CD and publish new versions for Node, Tauri, Vite, shell, and GitHub Release projects. Use when t
• lov-repo2docsTurn any folder of source material — a code repository, a pile of articles, a mixed knowledge dump with images
• lov-review-doc专业合同分析、审阅、批注与红线修订。用于用户要求审查合同、协议、条款、NDA、采购或服务合同、SaaS 或数据协议、劳动或顾问协议、知识产权许可、投融资文件，或要求风险分析、逐条批注、修订模式、谈判建议、审阅报告时；支持
• lov-rich-export将一份面向用户的内容稳定导出为单文件 HTML、带 assets 的 HTML 文件夹、Markdown、DOCX 与 PDF，并按格式正确处理图片、音频、视频和嵌入式交互内容。用于“富媒体导出”“一键导出”“导出 ht
• lov-skill-creator创建、验证并安装本地 Skill Publisher Skill 或 Skill Kit，并为每个新 Skill 固化真实案例、维度地图、定价依据和分发状态；当用户说“创建 skill”、"create a skill"
• lov-skill-optimizerAudit and optimize one or more existing Agent Skills from a canonical source path, then bump semver, update RE
• lov-skill-pricing为一个或多个 Agent Skill 生成可解释的 Skill Pricing Card：结合创作者时间与维护成本、用户价值、稀缺性、购买信心和生态潜力，输出建议价、价格区间、渠道策略及证据缺口；触发语包括“给这个 Sk
• lov-skill-publisherUse when the user asks to publish, release, package, or submit a validated Skill. Before every release, run lo
• lov-solution-architectCreate research-backed product and technical solution plans from a user's requirement. Use when the user asks
• lov-style-cloneAnalyzes one or more sample articles to extract a writing style profile (文风画像), then rewrites any target artic
• lov-subtitle-freedomCreate learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars
• lov-thesis-polishPolish and elevate MBA thesis / dissertation to national outstanding thesis quality (全国优秀论文). Performs compreh
• lov-translation-reviewReview Chinese-to-English translations for accuracy, grammar, terminology, and consistency. Produces a structu
• lov-video-chapterTurn SRT/VTT subtitles and source videos into 3–5 semantic chapters, an editable React chapter-bar project, a
• lov-video-chapter-designRefine chapter boundaries, titles, colors, typography, placement, and progress behavior in the bundled React v
• lov-video-chapter-exportPackage chapter overlays, timestamps, CSV metadata, and project JSON for 剪映/CapCut and other video editors. Us
• lov-video-chapter-planAnalyze timestamped SRT/VTT subtitles and determine 3–5 natural video chapters with cue-aligned cuts, concrete
• lov-video-chapter-renderRender a chapter project as a transparent ProRes 4444 overlay or burn it into the source video with FFmpeg. Us
• lov-visual-cloneAnalyze a reference design image and extract visual DNA — layout, style, color palette, texture, typography, c
• lov-wdb-cli万能微信秘钥：使用已有密钥或已解密数据库，按日期、对象、关键词、结构与稳定记录身份精准读取本地微信数据。
• lov-wechat-article-branding-skill自动读取微信公众号文章并完成目录、封面、正文首屏、可公开封面 Prompt、结构优化和品牌内容应用；适用于“把当前公众号文章品牌化”“加上封面 Prompt”、\"turn this WeChat article int
• lov-wechat-article-operator自动读取、编辑、保存并重载验证微信公众号文章；适用于“读取当前公众号文章”“替换封面”“插入这段内容”、\"edit this WeChat article\" 等需要可靠操作现有文章的任务。
• lov-write-professional-bookWrite multi-chapter books end-to-end from an outline.
• lov-wxmp-crackerExport WeChat Official Account articles into reusable structured content.
• lovable-checkpointMid-build health check — tells you what's working, what's silently broken, and whether it's safe to keep build
• lovable-cleanupRefactors the codebase before it gets too messy for Lovable to work with effectively.
• lovable-designGenerates an Awwwards-level Lovable prompt — the exact ingredients that separate a stunning website from a gen
• lovable-planTurns your app idea into a structured plan before you write your first Lovable prompt.
• lovable-promptRewrites what you want to say into a precise, safe Lovable prompt that won't break what's working.
• lovable-securityAudits your Lovable app for the security vulnerabilities that vibe-coded apps almost always ship with.
• lovable-seo-geo-optimizer-skillAudit and fully implement SEO and GEO (AI discoverability) across a Lovable project. Use this skill whenever s