Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Use when asked to verify this, prove it works, did this fix it, or show the evidence.
Verifies a merged change took effect in production by revision ancestry and cohort sampling, and reports a bound over sampled requests rather than "fully deployed". Use when the user says "is it live in prod?", or when asked to confirm or report whether a merged change is live or deployed in production, before answering, even when the build-info, status, or deploy output is already in hand; also when gating on a deploy reaching the fleet, sequencing deploys, or verifying a one-time migration, backfill, or cleanup. Not for CI or build state.
Interpret YouTube Analytics, TikTok Analytics, and video performance data. Identifies trends, explains metrics, and provides actionable recommendations for growth. Use when analyzing video performance, understanding metrics, or optimizing channel strategy.
Recommend YouTube videos worth watching on a topic — from your subscribed channels and beyond — ranked with reasons, skipping what you've already watched or summarised with video-lens. Activate on "what should I watch about AI", "new Kubernetes videos this week", "recommend cooking videos", "catch me up on my AI channels", "what did I miss on YouTube", "anything good on Rust lately", "set up video recommendations", "import my YouTube takeout", "sync my YouTube", "add this channel to my AI topic", "mute this channel".
Video processing toolkit. Use when user wants to: - Download videos from YouTube or other sites - Remove silence from videos - Trim, cut, or extract segments from videos - Extract audio from video files - Enhance or denoise audio - Replace audio track in a video - Change video playback speed - Concatenate multiple videos - Generate transcripts/captions (VTT) - Generate video descriptions, timestamps, or context cards - Upload videos to YouTube or Bunny.net CDN - Post social updates to X (Twitter) or LinkedIn - Get video metadata (duration, resolution, codec)
Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style. Produces a counted baseline file and checks any new draft against it. Use when an agent's drafts start sounding like a caricature of you, before publishing anything written in your voice, or every ten new pieces to re-measure.
Use when building a narrated, voiceover-synced motion-graphics explainer or B-roll film in Remotion — paper-texture collage, cut-out subjects with an offset red marker stroke, code-drawn charts, newspapers, documents and typewriter reveals. Horizontal 1920x1080 by default, vertical 1080x1920 for TikTok, Reels and Shorts on request. Triggers on "make a vox style video", "vox editorial video", "b-roll sequence", "Remotion explainer", "documentary motion graphics about X", "turn this script into a video", "make a TikTok explainer". Not for hard-sell product ads (use fastcut-ad).
Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: "research X for me", "do web research on", "look up sources for", "find citations for", "gather evidence on", "what does the web say about X". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), local file search, LLM-as-judge evaluation, or paywalled/auth-gated scraping. Produces a written plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.
Ingest sources into WikiContext, synthesize and publish cited knowledge pages, answer questions from its authenticated SQL evidence, maintain authoritative repository files and their GitHub destinations, and export a reproducible Obsidian vault. Use for WikiContext knowledge operations, including text, PDF, reviewed images, external transcript bundles and authorized Gemini audio ingestion; Markdown exports are presentation only.
Use when 王建硕 wants to turn his uploaded VoiceDrop voice memos into WeChat official account article drafts — pulling the unprocessed recordings sitting on jianshuo.dev/files (the R2 inbox), transcribing them, and mining articles from each. Triggers — "处理 VoiceDrop 录音", "把新录音挖成文章", "口述备忘变文章", "处理一下我的录音", "/wjs-mining-voicedrop".
Use when an iOS app already on TestFlight needs to ship to the App Store — preparing the screenshots and the description/metadata, then using the existing fastlane setup to submit for review. Triggers — 「提交 App Store」「上架」「app store 审核」「准备截图和文案」「submit for review」「/wjs-publishing-appstore」.
WordPress Playground review and development guidance. Use when reviewing Blueprints, Playground JSON setup flows, `@wp-playground/cli` usage, embedded Playground demos, reproducible bug repros, docs examples, or when user mentions "WordPress Playground", "Blueprint", "playground.json", "run-blueprint", "build-snapshot", "embed Playground", or "zero-setup repro". Helps review Blueprint design, local Playground workflows, demo reliability, and reproducible WordPress environments.
This skill convenes a 6-seat collaborative pre-production session — Story Architect, Story Analyst, Dialogue Writer, Scene Writer, Standards Reviewer, and Research Specialist pitch their creative visions before writing begins. Optionally convenes the seats across MULTIPLE models/providers (Claude + self-hosted vLLM + cloud) for genuine diversity. Use when: starting a new screenplay, planning major rewrites, reimagining existing material, or seeking diverse expert perspectives.
Managing cloud infrastructure using declarative and imperative IaC tools. Use when provisioning cloud resources (Terraform/OpenTofu for multi-cloud, Pulumi for developer-centric workflows, AWS CDK for AWS-native infrastructure), designing reusable modules, implementing state management patterns, or establishing infrastructure deployment workflows.
Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.
Operate a Seeed XIAO ESP32S3 board with arduino-cli on Windows: install the core, compile, upload, read serial output, and run verified examples (blink, serial, touch, ADC, PWM, WiFi scan/AP, BLE, deep sleep). Use this skill WHENEVER the task involves an ESP32S3 / XIAO board, arduino-cli, flashing a sketch, reading the serial monitor, COM ports, or any embedded/Arduino work — even for a "simple" LED change. It contains verified commands and known pitfalls (DTR reset, deep-sleep USB drop, PSRAM flag) that prevent wasted debugging time.
ZenTao CLI shared foundation: config initialization, token-based authentication, config precedence, permission error handling, update checks, security rules. Triggers when the user says: 'configure zentao', 'init config', 'config init', 'auth', 'login zentao', 'ZenTao login', 'token', 'view config', 'config show', 'config set', 'environment variables', 'ZENTAO_URL', 'ZENTAO_TOKEN', 'insufficient permission', 'auth status'.
ZenTao test case management — list test cases, view test case details, query test cases by product/project, and run test cases. Triggers when the user says: 'query test cases', 'test case list', 'what test cases are there', 'testcase list', 'view test case', 'test case details', 'create test case', 'new testcase', 'run test case', 'test case results', 'test cases', 'ZenTao test cases'.
Search, retrieve, inspect, add, or edit Zotero literature via the `zotagent` CLI. Load this skill whenever the user wants to query their Zotero library (keyword / semantic / metadata), pull quotations or context from indexed papers, add items by DOI, web page URL, ISBN / PMID / arXiv identifier, Semantic Scholar paperId, JSON, or manual metadata, change existing items (fix a field, add or remove tags, file into a collection, attach a note, trash an item), inspect recent Zotero items, or diagnose indexed attachments. Use it even on indirect requests — any mention of references, citations, bibliography checks, PDF passages, or literature discovery. Do not guess at zotagent's flags — consult this reference first.
Implement global state management for React/TypeScript applications. Use when creating, modifying, or debugging Zustand stores, implementing state management patterns (slices, persist, devtools, immer), setting up Zustand with Next.js/SSR, writing tests for Zustand stores, or working with TypeScript typing for Zustand (curried create, StateCreator, middleware mutators).
Search a library of 4,600+ AI motion graphics with their prompts and 2,100+ video-editor presets before building any motion graphic or video edit from scratch. Use whenever the user wants styled captions on video (karaoke, word-by-word, TikTok, Reels, Shorts), hooks, kinetic typography, titles, lower thirds, text behind the subject, transitions, colour grades and film looks, split-screen layouts, font pairings, logo reveals, intros, product launch videos or explainer videos, in HyperFrames, Remotion or HTML, even if they only say make or build and never ask for examples. Returns ready presets that one MIT engine renders as a pure function of time, real examples with prompts and creator credit, and 40 explainer styles with starter prompts. Not for converting, trimming or transcribing video files or fixing a framework install.
When the user wants to pack 2D rectangular items into bins, optimize 2D cutting patterns, or minimize material waste in 2D packing. Also use when the user mentions "2D packing," "rectangular packing," "sheet packing," "2D bin packing problem," "guillotine cutting," "two-dimensional packing," or "rectangle packing optimization." For 1D problems, see 1d-cutting-stock. For 3D problems, see 3d-bin-packing.
Execute AdCP Creative Protocol operations with creative agents - build creatives from briefs or existing assets, preview renderings, and discover format specifications. Use when users want to generate or transform ad creatives, preview how ads will look, or understand creative format requirements.
Generate background music and add it to your Remotion project. Describe the mood/genre you want, and this will generate a commercially licensed track with Eleven Music (official ElevenLabs music skill) and wire it into your composition with proper fade in/out.
Use this skill when you need a complete developer-ready design specification for a named aesthetic: W3C DTCG design tokens, CSS custom properties, cultural marker lists, component-level notes, and accessibility flags. Translates aesthetic understanding into implementable values across all 7 dimensions. Use when the user asks to 'make it look like X', requests design tokens or CSS variables, or needs a developer handoff spec grounded in an aesthetic. Depends on aesthetic-literacy. Do not use before an aesthetic is confirmed; do not use for accessibility resolution or component architecture.
Compare AG2 agents, models, or prompts to decide which is better. run_variants scores several named agents on one suite and ranks them on a leaderboard (Variants holds a mapping of named Agent instances plus an axis label). run_pairwise with pairwise_judge does head-to-head LLM comparison using a dual-order position swap (a win counts only if it survives the swap, else a tie), reporting win-rate with a Wilson 95% CI, wins, losses, ties, flips, and agreement (Cohen's kappa). human_pairwise collects a person's blinded vote inline, or via an exported manifest with export_pairwise_cases and human_labels. Use when the user wants to A/B test prompts or models, run a leaderboard, pick a winner, judge head-to-head, measure win-rate, or collect human preference labels. For running and grading a single agent, see ag2-evaluation.
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.