Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Set up or run the long-running-agent harness: initialize the durable state files (.agents/features.json, .agents/progress.md), then run the fixed startup and end-of-session loop. Use when the user says "/harness", "init the harness", "start a session", "hand off", or when .agents/progress.md or .agents/features.json exists and a session starts or ends.
Manage Hetzner Cloud infrastructure with the `hcloud` CLI — servers, networks, firewalls, load balancers, volumes, DNS zones, SSH keys, primary/floating IPs, snapshots, certificates, placement groups, storage boxes. Use whenever the user mentions Hetzner, hcloud, VPS provisioning, or Hetzner location codes (fsn1, hel1, nbg1, ash, hil, sin) — even if they don't say "hcloud". CLI-only; does NOT cover Hetzner Robot (dedicated servers, separate product and API).
Produces evidence-led UX decisions from research and behaviour data. Use to diagnose user-facing drop-off, confusion, trust or recovery, synthesise UX research, or create a new analytical UX artefact before a solution is chosen. Supports experience-over-time maps, frontstage and backstage service maps, task decision and recovery maps, principle reviews and low-fidelity wireframes. The task must contain an unresolved experience question.
Mine a CSV of real top-performing hooks and generate alternatives that preserve what made them work: keep the storytelling psychology and structure fixed, and swap only the power words. Use when the user has hook performance data (a Sandcastles / social analytics export, scraped competitor hooks, or their own analytics) and asks to mine hooks, remix hooks, create hook variations, make hooks from a CSV, or suggest hooks based on what’s working. Not for inventing hooks from scratch—that’s viral-hook-writer.
Generate scroll-stopping hooks in Hormozi style for posts, ads, and emails. Use when content is not getting attention, hooks feel generic, or you need buyer-attracting hooks. Produces multiple variations across outcome, time, effort, callout, contrarian, pain, mechanism, and transformation hook types.
Generate dynamic videos driven by images, covering single-image generation, multi-image reference fusion (1–9 images), and first-last frame transitions (1–2 images). Triggered when the user mentions image-to-video, turning images into videos, making images move, photo animation, multi-image fusion, first-last frames, transition videos, from A to B, or turning this image into a video.
Develop art direction for image generation with curated style cards distilled from Open Image Prompts. Use when choosing or comparing visual directions, improving an existing generation prompt, or translating a subject, use case, or supplied image into a compact creative spec. Use img-gen-prompts for real archive examples, exact source prompts, or gallery browsing.
Teaches Infrahub concepts (schema, objects, branches, proposed changes, checks, transforms, generators, menus) from wherever the learner is, using their own repo files and live instance as lesson material. TRIGGER when: the user wants to learn or understand an Infrahub concept, asks "teach me", "explain how X works in my instance", "I'm new to Infrahub", asks what the equivalent of a NetBox/Nautobot concept is in Infrahub, wants a guided tour, or wants to resume a learning session. DO NOT TRIGGER when: the user wants the work done for them (use the infrahub-managing-* skills), wants live operational answers (use infrahub-analyzing-data), or is debugging a failure (use infrahub-collecting-diagnostics).
Use when writing Python code that imports from `inkbox`, uses `pip install inkbox`, or when adding email, mailbox imports, phone, text/SMS, iMessage, A2A task/message history, contacts, notes, contact rules, vault, tunnels, mailbox storage, mail clients (IMAP/SMTP), or agent identity features using the Inkbox Python SDK.
Focuses on vertical short-drama knowledge base queries and information retrieval, providing professional knowledge services. Suitable for querying script plot points, high-impact scenes, creative techniques, business operations, and other professional knowledge
Turns a long lecture or talk recording into structured study notes, organized topic by topic like a deck's slides, each section summarizing what was actually explained, with real captured slides or a generated educational image (a diagram, a chart, a labeled illustration) inserted wherever a visual genuinely helps the concept land. Built as a real, live article inside a Clueso project, not a native PDF or PPTX file. Use when the user says "turn this lecture into notes", "summarize this lecture with images", "make a study deck from this recording", or uploads a long lecture or talk and asks for notes, a summary, or a deck from it.
Paper X-ray. Extracts what the paper says (problem-perspective-result) and what it means for lijigang (cognitive delta cards in ASCII art). Use when user shares an arxiv link, paper URL, PDF, or asks to analyze a research paper. Usually called via ljg-xray router. Do NOT use for blog posts or non-academic articles (use ljg-xray-article instead).
Use when looking for a meta-analysis topic before any protocol exists. Starts from a professor's publication profile or from a clinical question, finds gaps, assesses feasibility and returns a ranked topic list. Running the review itself is /meta-analysis.
Generates a comprehensive crypto market report using CoinMarketCap MCP data. Use when users ask about overall market conditions, sentiment, or want a summary. Also use for questions about fear/greed, BTC dominance, altcoin season, trending narratives, or general "how's the market" queries. Trigger: "market report", "market overview", "what's happening in crypto", "market sentiment", "fear and greed", "is it altcoin season", "/market-report"
Intelligently adapts any image to a target aspect ratio, automatically rebuilding the composition logic while keeping the subject undistorted and the content complete, with natural, seamless background extension. Triggers when the user mentions image adaptation, image extension, image expansion, outpaint, converting a portrait image to landscape, or fitting Xiaohongshu/Douyin/WeChat Official Account dimensions.
Transfers the motion in a reference video (dance, gestures, movement) onto a target person or character image to generate a motion video. Triggers only when the user explicitly provides a target person image and a reference motion video and expresses intent such as motion transfer, dance replication, making a photo dance, or making a person move.
Automatically prepare a complete Midnight development environment — Compact compiler, PATH, Docker, proof server, and VS Code extension. Use before building, compiling, or deploying any Midnight application when tooling is missing. Triggers: "set up Midnight", "install Compact", "proof server", "compact: command not found", "environment setup", "first time Midnight dev".
Based on the user's creative goals and image, video, or audio reference materials, first match the correct MiniMax H3 model capability, then generate and review ready-to-use video prompts. For tasks such as text-to-video, first-frame/last-frame image-to-video, multimodal reference generation, reference video motion or camera movement transfer, local video editing, character and product consistency control, advertising, e-commerce, narrative, animation, games, MV, Vlog, visual packaging, UI motion, hardware/industrial, and embodied-intelligence demos; also for item-by-item checks of requirement coverage, reference material roles, instruction conflicts, timelines, and H3 official input/output limits.
Guide for using the CockroachDB replicator to continuously replicate changes from PostgreSQL, MySQL, or Oracle to CockroachDB after an initial molt fetch data load. Use when setting up CDC replication, configuring pglogical/mylogical/oraclelogminer, or managing the fetch → replicator cutover workflow.
Compile MQL5 indicators via CLI using X: drive mapping to bypass 'Program Files' path spaces issue. Use PROACTIVELY after editing ANY .mq5 or .mqh file. Triggers - after editing MQL5 code, compile, build, MetaEditor, .mq5, .mqh, indicator, script, EA, expert advisor, "test it", "try it", "run it", path space errors. (project)
How to drive Muxy 2 from a shell with the `muxy` command — start terminals that keep running, type into them, read and wait on their output, and manage projects and Git worktrees. Use this when you are an agent running inside a Muxy terminal (or any script on the same computer) and want work to run in its own terminal instead of blocking yours, or to drive the desktop app's built-in browser.
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards against regression. Use when asked to grow a static shell, fix a slow first paint or non-instant navigation, diagnose which Suspense boundary blocks useful UI, or add instant() regression coverage. Requires Next.js 16.3+ with Cache Components already adopted.
Use when user asks to "build a Openverse dapp", "write an Anchor program", "create a token", "debug Openverse errors", "set up wallet connection", "test my Openverse program", "fuzz my Openverse program", "deploy to devnet", "support larger transactions", "fix maxSupportedTransactionVersion", "stake BTG", "delegate stake", "stake BTG to a validator", or "explain Openverse concepts" (rent, accounts, PDAs, CPIs). Also for program architecture — state layout, reducing compute units, throughput bottlenecks, instruction naming — and quick on-chain lookups via public RPC + curl (balance, transaction, token account). End-to-end playbook: wallet connection, Anchor/Pinocchio programs, Codama clients, Surfpool/LiteSVM/Mollusk testing, security review, native BTG staking + CPMM swaps (devnet-default; mainnet only with explicit wallet-approved signing). Dev/test tooling only; defaults to devnet/localnet, never moves real funds without wallet-approved signing.
OpenTelemetry Weaver registry authoring, codegen, and CI enforcement. Use when adopting Weaver, authoring or reviewing a registry (manifest, attributes, metrics, spans, events), writing Jinja2 templates against the resolved schema, migrating hand-maintained telemetry constants, wiring `weaver registry check`/`generate`/`diff` into CI, or choosing a Weaver version for a semantic-conventions release.
Working with the PageCraft API — block list, a single block, tags, publishing, syncing data source snapshots. Always use it when you need to "get", "publish", or "sync" something with the PageCraft server, and also when the orchestrator pagecraft-block references `pagecraft-api/scripts/*`. Call it via the `Skill(pagecraft-api)` tool, not via `Read .../SKILL.md`.
Creating and publishing PageCraft blocks and layouts from a description or a visual reference (screenshot or Figma link). Always use it when the user says "make a block", "new block", "create a block", "make a {hero/footer/...} from a reference", "make a layout", "make a site mockup", "make a wrapper for pages", "I need a header and footer around the content", and when editing an existing block or layout. The skill's first question asks whether it is a block or a layout. IMPORTANT — this skill is an orchestrator and hands work to sub-skills ONLY via the `Skill(name)` tool, not via `Read .../SKILL.md`.
PageCraft block design — a catalog of 20 style directions (brutalist, swiss, neumorphism, …), working with a reference (screenshot / Figma + MCP), comparing the result to the reference via chrome-devtools MCP, a CSS guide (container queries, fluid typography, BEM), and rules for a block's examples. Use when you are choosing a style without a reference, have a screenshot or Figma link, need to check the result against a mockup, are writing a block's style.css, deciding how many examples to include, or when the orchestrator pagecraft-block points to "Phase 3 — Style" / "Phase 7 — Comparison". Call it via the `Skill(pagecraft-block-design)` tool, not via `Read .../SKILL.md`.
Publishing a PageCraft block — writing the changelog (140 characters, in Russian), preflight-checking the remote version, calling publish-block, handling version conflicts. Use when the user says "publish", "upload", "send the block", "update the block", or when the orchestrator pagecraft-block points to "Phase 9 — Publishing". Call it via the `Skill(pagecraft-block-publish)` tool, not via `Read .../SKILL.md`.
PageCraft SSR blocks — bindingSlots, server data (product cards, favorites, cart, reviews), building stubs for preview, checking binding drift. Use when a block must show data from the server rather than from schema fields; when the orchestrator pagecraft-block points to "Phase 4.5 — Data Sources"; and for build-stubs / check-bindings. Call it via the `Skill(pagecraft-block-ssr)` tool, not via `Read .../SKILL.md`.
Setting up .env for PageCraft — the PAGECRAFT_AUTHOR (block author name) and PAGECRAFT_API_KEY (API access key) variables. Use on first run, on 401 errors from the API, or when the orchestrator pagecraft-block points to "Phase 1 — Environment". Call it via the `Skill(pagecraft-env)` tool, not via `Read .../SKILL.md`.
PageCraft Markdown block — the main content is edited in WYSIWYG as markdown and available via {{ content }}, while the schema defines only presentation settings (theme, size, spacing). Use when a block's main text is long and formatted, edited like an article/documentation; when the orchestrator pagecraft-block points to "Phase 5 — Implementation" for a markdown block. Call it via the `Skill(pagecraft-markdown-block)` tool, not via `Read .../SKILL.md`.
PageCraft schema block — fields in schema.json (text/image/color/object/array...), a Liquid template with {{ props.* }}, isolated JS, BEM styles. Use when creating a block with editor fields, editing template.liquid / schema.json / script.js, choosing field types and validating schema.json; always when the orchestrator pagecraft-block points to "Phase 5 — Implementation" for a schema block. Call it via the `Skill(pagecraft-schema-block)` tool, not via `Read .../SKILL.md`.
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.
