Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guides a contributor from a workflow idea to a complete Workflow Implementation Packet (draft workflow file, draft workflow command, cross-cutting update checklist) in a staging area for review. Runs overlap analysis against the existing workflows with a Why Gate, then helps select and sequence skills with authored handoffs. Use when creating a new multi-skill workflow or promoting a repeated ad-hoc chain into a durable one. To build a single skill instead, use utility-pm-skill-builder; to run a sequence without authoring anything, use the chain command or utility-pm-workflow-orchestrator
Ship every change the way the user requires, with the guardrails. Take screenshots of the start, the key moment, and the result; give the change its own changelog version with pictures; verify with tests; commit only your own files; merge with the latest main and push as a fast-forward; publish that exact main live; confirm each step; and report measured sizes, asking before any upload over 50 MB. Use at the end of every change (feature, fix, tweak, art, balance, polish) and whenever the user says “ship it”, “commit”, “push”, “merge”, “publish”, “deploy”, “go live”, or “update the changelog”. Project specifics (hosting, the changelog pipeline, merge conflicts) go in an optional local references/<project>.md next to this skill
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use for generic GKE cluster node pool creation or standard non-TPU workload management (use gke-basics or gke-cluster-creation instead).
Mutating operations on the user's Longbridge recurring-investment (DCA) plans — list (read-only), create a plan, update / pause / resume / stop a plan, view trade history, check eligibility. Requires longbridge login WITH TRADE SCOPE because every plan automatically commits real money on a schedule. Every mutation requires a two-step preview + confirm protocol, and `create` requires the user to read back amount / frequency / symbol / start date / end date before confirming. Use only when the user gives a clear imperative ("create a monthly DCA on AAPL for 500 USD", "停止定投 700.HK"); ambiguous prompts ("帮我看看定投") must be rejected with a "please be specific" reply rather than triggered. Triggers: "创建定投", "新建定投计划", "设置定投", "暂停定投", "停止定投", "恢复定投", "修改定投", "建立定投", "建立定投計劃", "設置定投", "暫停定投", "停止定投", "恢復定投", "修改定投", "create DCA", "create recurring investment", "set up DCA plan", "pause DCA", "stop DCA plan", "resume DCA", "monthly DCA on X", "weekly recurring buy".
Foreign-exchange rates for all currencies supported by Longbridge Securities — HKD / USD / CNY / SGD / EUR / GBP / JPY / etc. Use to convert multi-currency holdings, normalise account values, or quote a cross-rate. Light-touch utility skill, no login required. Triggers: "汇率", "美元兑港币", "人民币兑美元", "港币换美金", "今天汇率", "USD HKD", "CNY USD", "外汇", "匯率", "美元兌港幣", "人民幣兌美元", "港幣換美金", "今天匯率", "外匯", "exchange rate", "fx rate", "currency conversion", "USD to HKD", "HKD to USD", "CNY to USD", "JPY to USD", "convert HKD to USD", "1 USD in HKD".
Design and implement microservices architecture including service boundaries, communication patterns, API gateways, service mesh, service discovery, and distributed system patterns. Use when building microservices, distributed systems, or service-oriented architectures.
Expose ZenStack V3 data as automatic CRUD web APIs ("Query as a Service") and consume them. Use when adding REST/RPC endpoints with a server adapter (Express, Fastify, Next.js, Nuxt, SvelteKit, Hono, Elysia, TanStack Start), wiring per-request access control via getClient/$setAuth, generating an OpenAPI spec, or calling the API from a client (fetch-client, TanStack Query hooks).
Build a paper sheet in Three.js that reads as paper up close: washi, cotton rag, or kraft with baked fibre and tooth relief, laid and chain lines, a torn deckle edge with frayed fibres, four-layer thickness, a rolled corner and crease, ink that wicks along the fibres, toasted aged edges, contact shadows, and back-lit translucency. Use for a hung sheet, scroll, page, label, shoji pane, or card that must survive a macro close-up, or when paper looks like a flat white plane, has ruler-straight edges, no thickness, or does not glow when lit from behind. Use 3d-wood-material, 3d-cloth-material, or 3d-metal-material for those materials, and paper-cinder-transition for burning paper.
When the user wants to improve their persistent but respectful outreach that keeps deals moving. Also use when the user mentions "following up," "staying on top of deals," "persistent outreach," "keeping deals alive," "not letting deals fall through," or "consistent follow-up."
Expert patterns for Godot audio including AudioStreamPlayer variants (2D positional, 3D spatial), AudioBus mixing architecture, dynamic effects (reverb, EQ, compression), audio pooling for performance, music transitions (crossfade, bpm-sync), and procedural audio generation. Use for music systems, sound effects, spatial audio, or audio-reactive gameplay. Trigger keywords: AudioStreamPlayer, AudioStreamPlayer2D, AudioStreamPlayer3D, AudioBus, AudioServer, AudioEffect, music_crossfade, audio_pool, positional_audio, reverb, bus_volume
Expert blueprint for performance profiling and optimization (frame drops, memory leaks, draw calls) using Godot Profiler, object pooling, visibility culling, and bottleneck identification. Use when diagnosing lag, optimizing for target FPS, or reducing memory usage. Keywords: profiling, Godot Profiler, bottleneck, object pooling, VisibleOnScreenNotifier, draw calls, MultiMesh.
US ETF capital-flow analysis via Longbridge Securities — tracks institutional money migration via ETF creation/redemption changes, sector breadth signals, and thematic momentum. Analyses major SPDR sector ETFs (XLK / XLF / XLE / XLV etc.) for net inflow / outflow to gauge industry rotation and risk-appetite shifts. Triggers: "ETF资金流", "ETF流向", "美国ETF", "板块ETF", "XLK", "XLF", "XLE", "机构资金迁移", "行业轮动信号", "ETF資金流", "ETF流向", "美國ETF", "板塊ETF", "機構資金遷移", "ETF flow", "US ETF flow", "sector ETF", "SPDR", "institutional flow", "sector rotation signal", "ETF inflow outflow", "fund flow".
Mutating operations on the user's Longbridge watchlist — create group, rename group, add / remove symbols, delete group (optionally purging members). Requires longbridge login. Every mutation requires a two-step preview + confirm protocol. Use only when the user gives a clear imperative ("add X to favourites", "delete the Tech group"); ambiguous prompts ("organise my watchlist") must ask back. Triggers: "把 X 加到自选", "添加到自选", "创建自选分组", "删除自选", "删除分组", "改名分组", "把 X 加到自選", "新增至自選", "建立自選分組", "刪除自選", "刪除分組", "重新命名", "add to watchlist", "create watchlist group", "remove from watchlist", "delete group", "rename group", "watchlist edit".
Designs a deliberate sequence of offers (attraction, upsell, downsell, continuity) so a new customer generates enough cash within ~30 days to fund acquiring the next one - Alex Hormozi's client-financed acquisition. Use when customers buy once and never again, when CAC eats all the profit, when you can't afford to advertise profitably, when the business grows but cash shrinks, when you sell one product at one price, when deciding what to sell first or next, or when structuring upsells, downsells, payment plans, trials, and continuity. Covers the 30-day payback rule, attraction/upsell/downsell/continuity offer types, and cash-flow sequencing for validated markets.
Classify and wire Remotion Studio config options as either startup-fixed or reloadable while preventing mixed lifecycle behavior across consumers. Use when adding, changing, or reviewing a Config setter or CLI option consumed by Studio, its preview server, compiler, HTML bootstrap, public-folder watcher, or render queue.
Generate and optimize AI image generation prompts with primary support for Google Gemini (Nano Banana), plus Midjourney, Stable Diffusion, DALL-E, Leonardo.ai, and other text-to-image tools. Use when users request: (1) Generate a prompt/提示词 for an image, (2) Optimize or improve an existing prompt, (3) Create variations of a prompt, (4) Translate ideas into detailed prompts, (5) Ask for help with AI image generation, or (6) Mention keywords like 'prompt', '提示词', 'Gemini', 'Nano Banana', 'Midjourney', 'Stable Diffusion', 'AI绘图', '文生图', 'text-to-image', or '/imagine'.
Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, implementing dark mode typography, or when asked about readability, font pairing, line height, measure, typographic hierarchy, variable fonts, font loading, or OpenType features.
Build convincing timber for Three.js as one procedural MeshPhysicalMaterial with growth rings, cathedral figure, pores, medullary rays, checks, tool marks, end grain, and oil, wax, or lacquer finishes, so the grain follows the form and survives macro close-ups without image textures. Use for wood boards, benches, carved panels, tool handles, joinery, floors, and any request to make 3D wood look real, detailed, or less like a tiled photo or plastic.
Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels. Use when user asks to: search email, read email, send email, create email draft, mark as read, archive email, star email, or manage Gmail labels. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.
Refer to this when eliciting users’ tacit knowledge through dialogue (active listening, interviews, clarifying vague answers, exploring past decisions, challenging assumptions, reconciling contradictions, eliciting motivations, and refining thinking). Integrates eight techniques—Rogers-style listening, DICE probing, CDM, devil’s advocacy, dialectical inquiry, motivational interviewing OARS, narrative elicitation, and Socratic questioning—with a situational selection guide and shared rules.
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.