Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use this skill to run Android-aware unit tests on the JVM with Robolectric — the right runner choice (AndroidJUnit4 vs RobolectricTestRunner), @Config sdk/qualifiers/application, the includeAndroidResources requirement, common shadows (ShadowApplication, ShadowLog, ShadowLooper, ShadowPackageManager, ShadowSystemClock), looper draining (shadowOf(Looper.getMainLooper()).idle()), and when NOT to reach for Robolectric (screenshot tests, RenderThread, accessibility services). Also covers the AGP 7.2+ sharedTest reality check and the migration to KMP androidHostTest/androidDeviceTest. If the user mentions Robolectric, AndroidJUnit4 host test, RobolectricTestRunner, @Config, includeAndroidResources, ShadowLooper.idle, shadowOf, sharedTest broken on AGP 7.2, ParameterizedRobolectricTestRunner, "test passes on JVM fails on device", or "Resources NotFoundException" in unit tests, use this skill.
Screen US stocks for high-quality dividend opportunities combining value characteristics (P/E ratio under 20, P/B ratio under 2), attractive yields (3% or higher), and consistent growth (dividend/revenue/EPS trending up over 3 years). Supports two-stage screening using FINVIZ Elite API for efficient pre-filtering followed by FMP API for detailed analysis. Use when user requests dividend stock screening, income portfolio ideas, or quality value stocks with strong fundamentals.
Assemble the final video with narration: lay the voiceover audio over the source video, lower the original audio during narration windows, generate SRT / ASS subtitles and optionally burn them in, then normalize loudness. Use as the final assembly stage. Inputs: source video, tts_meta.json, and narration positions; outputs: recap video and subtitles. Triggers: video assembly, mixing, subtitles, burn-in subtitles, assemble video, mux, ducking, subtitles, final cut.
Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops. Defaults to Seedance 2 but works the same with Kling 3 / 4, Veo 3 or Sora 2. Output is one MP4 saved to the project folder. When the workspace also ships an interactive-video / hyperframes skill, prefer composing several short shots into a single timeline rather than one long monolithic clip.
Translate, dub, and localize speech in an existing video while optionally preserving speaker voices, generating translated captions, or synchronizing the speaker's lip movements. Use when the user asks for 视频译制、多语言配音、 把视频里的中文变成英文、让视频里的人说另一种语言、保留原音色、翻译声音、 口型同步、translated video, video dubbing, voice translation, or lip-synced localization, as well as traducción de video, doblaje de video, traducir un video, or sincronización labial. This Skill MUST be loaded before composing treatment choices for an ambiguous video-translation request in any language, including a turn that only asks the user to choose a treatment. Do not use when the user only wants subtitles translated, wants an SRT/VTT file, wants text or a script translated before generating a new avatar video, or wants ordinary TTS with a newly selected voice.
Design voice interactions and speech interfaces that work for people with diverse speech patterns, accents, and communication styles. Use when designing voice commands, voice search, dictation, voice assistants, or any interface that accepts speech input. Triggers on: voice, speech, dictation, voice command, voice search, speech recognition, accent, stutter, speech disability, non-verbal, AAC, voice assistant, talk to type.
Design and build waiting-list portals for anticipated goods or services: classify whether the experience needs interest capture, verified early access, referral growth, a virtual waiting room, appointment backfill, or scarce-item allocation; choose a reversible architecture; and define the state machine, abuse controls, consent and email lifecycle, fairness, observability, and release gates. Optionally validate supplied email and phone contacts with expiring magic links or provider-managed verification, then feed eligible, consented records to a runtime-configured CRM adapter. Use for prelaunch signups, beta access, launches, bookings, reservations, traffic-spike queues, and premium or cinematic campaign experiences. Do not use for generic landing-page copy, ordinary CRM or email operations, or checkout and inventory systems in isolation; route those parts to the appropriate specialist skill.
Use when the user needs Playwright-based web application testing — screenshots, browser log analysis, interaction verification, visual regression, accessibility, and network mocking. Triggers: E2E test setup, visual regression testing, accessibility audit, Playwright configuration, page object model creation, CI test pipeline.
When the user asks about a weekly report, weekly summary, or work recap, collect multi-channel evidence around the target time range, merge it into work themes, and generate a structured weekly report. Suitable for scenarios where multiple information sources coexist, such as collaboration platforms, Git, Agents, and local documents. Trigger phrases: "周报", "周总结", "工作汇总", "上周工作", "周工作", "weekly report", "work summary".
Set up, validate, and reconfigure the llm-wiki skill suite. Always use this skill when the user says /wiki-config, asks to 'set up my wiki', 'configure wiki', 'initialize wiki config', mentions 'page structure problems', 'schema issues', 'missing templates', 'wiki help', 'how does the wiki work', or when any wiki skill reports a missing or invalid config, schema, or templates. Also use when the user wants to know what wiki skills are available, seems confused about how the wiki system works, or asks why a skill isn't behaving as expected - even if they don't say 'config'. Owns the interactive configuration flow, schema management, and template management for the wiki system. When in doubt whether a setup or configuration issue is being raised, use this skill.
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or troubleshooting deployment failures, workflow errors, and environment configuration issues
XiaoHongShu viral content writing assistant that helps generate high click-through-rate notes that read like a human wrote them. Includes AI-flavor removal checks, 7 title formulas, 5 opening templates, 3 closing templates, and SEO optimization. Use when the user wants to write XiaoHongShu content, generate viral post titles, or needs help with RedNote writing. Trigger on: 写小红书笔记、小红书文案、爆款标题、种草笔记、学习日记、干货分享。
Use when debugging services on a user's dedicated server via SSH. Use when needing to run a command on the server, inspect pods, check container logs, view k8s resources, or run kubectl commands. Use when "service exec" is insufficient and you need server-level access. Use when user says "check my server", "run X on my server", "debug pod", "kubectl", "SSH into server", "check k8s", or "inspect cluster".
Format ACM conference papers and journal articles with the acmart LaTeX class (sigconf, sigplan, acmsmall, acmlarge, acmtog, manuscript/review/anonymous modes) or the ACM Word template, covering CCS concepts, keywords, ACM Reference Format, rights management and copyright blocks, anonymization for double-blind review, accessibility (alt text), the TAPS production workflow and common acmart errors. Use when writing for CHI, SIGGRAPH, KDD, SIGMOD, CCS, FAccT, WWW, SIGIR, CSCW, PLDI or any ACM venue or journal.
Audit and establish current agent context for the technologies that define a project's stack. Use when setting up a project for agent work, after selecting or adding a framework, library, developer tool, or hosted service, or when entering an existing project whose agent context has not been audited.
Retrieve unresolved PR review comments and general conversation comments (including actionable notes from the PR author), explain each issue and propose fixes interactively, then spawn a coordinated developer team to implement approved fixes. After committing, respond to each comment on GitHub with resolution details.
This skill should be used to retroactively record an architectural decision that was made in the past but never written up as an ADR — typically surfaced by a doc audit or by a user realising a long-ago shipped change should have been documented. PROACTIVELY activate on "backfill ADR", "retroactive ADR", "post-hoc ADR", "reconstruct an ADR from history", "write up a past decision", "we never documented this decision", "decision was made but no ADR exists", "we decided years ago", "back when", "before my time", or "the audit surfaced a backfill candidate." Tense rule: `adr-drafting` claims "we decided / we're deciding"; `adr-backfill` claims "we decided years ago / back when / before my time / never wrote it down." Refuses when reconstruction confidence is `low` -- routes to `open-questions.md`. Requires evidence in two independent locations and a verbatim honesty clause in the record. Provides: backfill ADR template, confidence rubric, evidence corroboration, honesty-clause boilerplate.
Audit an AI agent setup: can one email leak your data? Use when someone asks whether their agent is safe, before letting an agent run unattended, or after adding a connector, MCP server, tool, token, inbox, webhook or network rule. Works on a Claude Code repo (settings, hooks, devcontainer), a Claude Code routine, a Hermes install, or an agent in GitHub Actions. Checks the lethal trifecta (private data, untrusted input, a way out), names the exact config that opens each leg, and proposes the cheapest leg to cut. Read-only: it reports, it changes nothing
Alibaba Cloud Live Recording Diagnostic Skill. Use for diagnosing live stream record issues including missing recordings, file generation problems, unexpected recording behavior, and callback issues. Triggers: "live record", "live stream record diagnosis", "record not working", "record file missing", "record callback issue", "录制诊断", "直播录制问题".
Use when understanding images with Alibaba Cloud Model Studio Qwen VL models (qwen3-vl-plus/qwen3-vl-flash and latest aliases). Use when building image Q&A, visual analysis, OCR-like extraction, chart/table reading, or screenshot understanding workflows.
Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a component feel alive, or build a transition. For critiquing existing motion use review-animations; for auditing a whole codebase use improve-animations.
Use this skill any time the user wants to create diagrams, flowcharts, or visual structures. This includes: architecture diagrams, mind maps, org charts, user journey maps, system design diagrams, ER diagrams, sequence diagrams, process flows, decision trees, network topologies, class diagrams, Gantt charts, SWOT analysis diagrams, wireframes, and sitemaps. Also trigger when: user says 画个流程图, 做个架构图, 思维导图, 组织架构图, 用户旅程图, 系统设计图, 甘特图. If a diagram or visual structure needs to be drawn, use this skill.
Use this skill any time the user wants to generate, create, or design images, illustrations, or visual assets. This includes: posters, banners, social media graphics, product mockups, logo concepts, thumbnails, marketing creatives, profile pictures, book covers, album art, icon designs, and any request for AI-generated imagery. Also trigger when: user says 生成图片, 做个海报, 画个插图, 设计个banner, 做个封面, 社交媒体配图, 产品效果图. If an image or visual asset needs to be created, use this skill.
Apple on-device machine learning framework reference. Core AI (.aimodel) / Core ML / Create ML / Vision / Natural Language / Speech / Media Intelligence / Music Understanding. AIModel, InferenceFunction, MLModel, MLModelConfiguration, MLMultiArray, MLTensor, MLComputeUnits, MLImageClassifier, MLTextClassifier, MLDataTable, VNCoreMLRequest, VNImageRequestHandler, VNRecognizeTextRequest, RecognizeTextRequest, NLTagger, NLEmbedding, NLLanguageRecognizer, SpeechAnalyzer, SpeechTranscriber, SFSpeechRecognizer, SFSpeechAudioBufferRecognitionRequest, SFTranscription, FaceGroupAnalyzer, MusicUnderstandingSession.
Configure rich popup content with text, fields, media, charts, attachments, and related records. Use when customizing feature popups, adding charts or images to popups, templating popup titles and field formatting, or displaying related record data on click.
Guide for using Argo to create polished product demo videos from Playwright scripts with AI voiceover and animated overlays. Use this skill whenever the user mentions Argo, demo videos, product demos, screen recordings with narration, Playwright video demos, voiceover generation, or wants to automate creating marketing/sales/onboarding videos from a web app. Also use when you see imports from '@argo-video/cli', files named '*.demo.ts' or '*.scenes.json', or an 'argo.config.js' in the project. Even if the user just says "record a demo" or "make a video of my app", this skill applies.
Fetch and analyze an arXiv paper via tiered fallback (markdown -> arXiv HTML -> ar5iv -> PDF). Rate-limited for arxiv2md (28 req/min, deterministic). Produces a structured summary with citation, problem, key claims, method, results, limitations. Use when the user says "analyze arxiv paper", "summarize arxiv", "read paper", "what does this paper say", or provides an arXiv ID/URL to analyze.
Write usage scenarios that include assistive technology and diverse interaction methods. Use when writing scenarios, use cases, user journeys, or storyboards. Triggers on: assistive technology, AT, screen reader, switch, voice control, magnifier, braille display, head pointer, eye tracking, how people use our product, usage scenario, use case.
Use when the user wants to prepare, create, or generate an AWS FIS (Fault Injection Service) experiment configuration. Triggers on "prepare FIS experiment", "create FIS experiment for [scenario]", "generate chaos experiment config", "准备 FIS 实验", "生成 [scenario] 混沌实验配置", "create experiment template for AZ power interruption", "set up fault injection test". Covers Scenario Library pre-built scenarios (AZ Power Interruption, AZ Application Slowdown, Cross-AZ Traffic Slowdown, Cross-Region Connectivity), custom single FIS actions (aws:rds:failover-db-cluster, aws:ec2:stop-instances, etc.), and SSM Automation-based fault injection for Amazon MSK (broker reboot) and ElastiCache Redis/Valkey (primary node reboot, replication group failover).
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.