Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Check the template’s “standard” pattern—whether it’s complete, whether there’s local drift, and whether /sync-template from remote is needed. Compare local ↔ remote ↔ disk version.json (0 token, fail-open). Triggers: “health check”, “check pattern”, “cần sync chưa”, “/health-check”.
Registers state-type triggers that automatically fire functions when key-value state is created, updated, or deleted within a scope. Use when building reactive side effects, change watchers, audit logs, cache invalidation, notification dispatchers, or any observer pattern where data changes should trigger downstream processing.
Shipyard's internal requirements intake for non-engineer contributors (support/ops) — turn a pasted chat log or verbal problem report into a five-section intent.md through numbered batch questioning with a completion gate, walk it through tracker review with harbor's four records, and hand the accepted intent to /launch as its mission brief. Produces decisions, not code.
Search TikTok e-commerce livestream rankings using kalodata data and query detailed data for a specified livestream. Browse top-ranked and best-selling TikTok shopping livestreams by region, currency, language, and date range, and use livestreamId to retrieve sales, viewer count, duration, GPM, and the number of products sold. Trigger this skill when the user mentions TikTok livestream rankings, TikTok live rankings, TikTok shopping livestream rankings, top-selling TikTok livestreams, TikTok livestream details or data, livestream viewer counts, kalodata livestream search or rankings, TikTok livestream ranking, TikTok live ranking, TikTok top livestreams, TikTok live shopping ranking, TikTok livestream detail, kalodata livestream search/detail, or live analytics. Trigger it even if the user does not explicitly mention “kalodata,” as long as they want to view TikTok platform livestream rankings or detailed data for a specific TikTok livestream.
Use when asked to review, edit, or improve the writing quality of a scientific or engineering manuscript. Triggers include “review my writing”, “check my manuscript”, “improve clarity”, “clean up the prose”, “edit for journal submission”, “writing review”, or any request to evaluate sentence-level quality, eliminate clutter, fix passive voice, or enforce keyword consistency in a research paper draft. Also triggers when asked to prepare a manuscript for submission to a specific journal. Do NOT use for content or technical review of methods or results, statistical analysis, or citation formatting.
Translates beliefs (probabilities) into optimal actions (bet/pass/hedge) using quantitative frameworks including edge calculation, Kelly Criterion bet sizing, forecast extremizing, and Brier score optimization. Use when converting probabilities into decisions, calculating edge against market odds, sizing bets optimally, extremizing aggregated forecasts, improving Brier scores, or when the user mentions betting strategy, Kelly Criterion, edge calculation, Brier score, extremizing, or translating belief into action.
Read and publish on Medium (medium.com) with the user's own login cookies (BYOC) — list their posts with clap/response stats, inspect one post, and publish a new story. Use when the user mentions Medium, "my Medium posts", reading their post stats (claps/reads), or publishing a story to Medium.
Use for UI/UX research with Mobbin MCP, including screen references, flow research, competitive audits, pattern exploration, PRD-driven research, or researching a target UI component by component to find the best development reference. Triggers include: Mobbin search or research; screen references; product flow research; pattern analysis; competitive UI audit; UX benchmarking; onboarding, checkout, empty, error, or confirmation screens; fintech or crypto UX; AI product patterns; SaaS dashboard patterns; ecommerce checkout patterns; PRD research; building or implementing a UI or screen; finding the best reference for each component; researching design components; component-by-component reference research; or turning abstract product questions into concrete screen and flow searches. This skill uses the Mobbin MCP server specifically—not Refero or other design reference tools.
Guides safe, evidence-led changes to the TaxonomicFilter, PostHog's picker for events, actions, properties, cohorts, and more. Use when adding features, fixing bugs, removing groups or tabs, changing search, ordering, recents, pinning, empty states, loading or performance, or refactoring the classic picker, rebuild menu, or headless filter panel. Indexes how users actually pick, known failure modes, the feature inventory, design principles, contested decisions, where to find evidence, and how to measure a change.
Manage Motoko projects with the mops CLI — toolchain pinning, dependency management, type-checking, building, and linting. Use when working with mops.toml, mops.lock, running mops commands, adding/removing packages, pinning moc or lintoko versions, checking or building canisters, configuring moc flags, or setting up a new Motoko project.
Creates showreel-grade motion graphics videos entirely from code — HTML scenes rendered frame by frame in headless Chrome with real motion blur, plus an original score composed for each video on the same beat grid. It directs the film itself from whatever the person gives — their words, a site, a GitHub repository, an app, screenshots, their own video clips and photos, or reference clips — and sets the pace and the energy of the music from them. Use for any promo, ad, launch video, explainer, reel, Shorts or TikTok, intro, kinetic type or logo animation for a business, product, app, site, bot, channel or person, even when all you have is a link or a name.
Use this skill when the user asks to operate MoviePilot through the local `moviepilot tool` MCP CLI for normal product workflows: media search, torrent search, downloads, subscriptions, downloader tasks, library checks, sites, schedulers, workflows, and messages. Prefer dedicated skills for slash command dispatch, manual file organization or failed transfer retry, direct REST API calls, direct database SQL, browser operations, and restart/upgrade.
Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed `rust_dynamic` native or `worker` gRPC plugin, with deterministic validation and rollback-safe registration.
How to work in a Plain Notes project (the `plain-notes` starter pack): a flat notes/ folder plus a daily/ journal. The “I just want to write” layout. Read when the project has these folders, or when asked to jot a note, capture a quick thought, or write today's journal entry. Carries the linking habit and daily-entry behavior so templates and folder descriptions stay minimal. Complements the platform `open-knowledge` skill; does not replace it.
Distill anyone’s way of thinking—their mental models, decision-making heuristics, and expressive DNA—to generate a runnable OpenClaw Perspective Skill. Fully automated pipeline: six parallel research tracks → dual-track distillation → source verification → adversarial testing → output. Trigger phrases: “distill XX,” “create a person,” “Nuwa,” “XX’s way of thinking,” “make a skill from XX’s perspective,” “perspective skill.” Vague requests also trigger it: “I want to improve the quality of my decisions,” “Is there a way of thinking that could help me…,” “I need a thinking consultant.”
Optimize an Omni Analytics model for Blobby, the Omni Agent — configure ai_context, ai_fields, synonyms, sample_queries, and ai_settings. Use this skill whenever someone wants to improve AI accuracy in Omni, make Blobby smarter, add AI context or example questions, curate which fields the AI sees, personalize AI context by user attribute, diagnose context-window pruning or truncation, raise a topic's AI context budget, control which topics AI can reach, troubleshoot why Blobby gives wrong answers, or any variant of "make the AI better", "Blobby isn't answering correctly", "optimize for AI", or "teach the AI about our data".
Scripted, branded onboarding for LaunchDarkly. Fixed sequence with LaunchDarkly voice and tone. Enforces step completion before advancing. Redirects drift. Use when the user wants to set up LaunchDarkly from scratch or asks to start onboarding.
Email sequences, newsletters, automation, and deliverability strategies. Use when the user requests 'email sequence', 'newsletter', 'drip campaign', 'welcome email', 'lifecycle email', 'cold email', 'email automation', or 'email copywriting'.
Builds product positioning documents for marketing clarity. Use when the user requests 'positioning', 'target audience', 'differentiation', 'proof points', 'ICP', 'buyer persona', 'messaging framework', 'competitive positioning', or 'value proposition'.
PDF engineering for extraction, generation, modification, and form filling. Use when extracting text or tables from PDFs, generating PDFs with Puppeteer, modifying PDFs with pdf-lib, filling PDF forms, or implementing PDF security. Use for AI-assisted OCR, HTML-to-PDF conversion, and document processing pipelines.
Podcast-to-everything content pipeline. Takes a podcast RSS feed or raw transcript and generates a full cross-platform content calendar: short-form video clips, Twitter/X threads, LinkedIn articles, newsletter sections, quote cards, blog outlines with SEO keywords, and YouTube Shorts/TikTok scripts. Scores each piece by viral potential (novelty × controversy × utility) and deduplicates against recent output. Use when asked to: “repurpose this podcast,” “turn this episode into content,” “podcast content calendar,” “extract clips from this episode,” “podcast to social,” “content from RSS feed,” “batch process episodes,” or any request to turn podcast/audio content into a multi-platform content plan
Drive the pollo-cli to generate images and videos through the Pollo platform open API — discover a model, read its input fields, submit a generation with local or hosted image inputs, and poll it to a finished URL. Use this whenever the user asks to generate/create/make an image or video, animate a photo, do image-to-video / text-to-video / reference-to-video, check Pollo credit balance or estimate the credit cost of a generation, or asks what Pollo models are available — trigger even if they don't name "pollo-cli" or "pollo" explicitly, e.g. "turn this photo into a video" or "how many credits do I have left". NOT for building the platform API itself (server-side model exposure — use the expose-platform-model-api skill) or wiring a model into the web frontend (use the add-model skill).
Designs high-performing ad creatives across Instagram, Facebook, TikTok, LinkedIn, Google (Display / Demand Gen), YouTube, Pinterest, and X/Twitter — locking platform dimensions, safe zones, text overlay policy, character limits, industry visual DNA, ad objective hierarchy, composition patterns, CTA strategy, and prompt sanitation. Use when the user says "create an ad", "design an ad creative", "make an ad", "广告创意", "帮我做个广告图", "Instagram ad", "TikTok ad", "Facebook ad", "Google Display ad", "LinkedIn ad", "YouTube ad", "Pinterest ad", "promotional image", "campaign creative", "ad banner", "投放图", or any platform-specific ad request. Routed from `product-shots` when `asset_type == "ad"` or `is_promotion == True`.
Unified image-generation engine for the product-shots ecosystem. Dispatches to the right model family (OpenAI gpt-image-2 / Gemini gemini-3-pro-image-preview Nano Banana Pro) with one parameterised script for text-to-image and image-to-image. Primary backend: OmniMaaS / Cloubic gateway (https://api.omnimaas.com/v1); also supports any OpenAI-SDK-compatible gateway via fallback env vars. Auto-resizes oversized reference images to prevent edge-proxy timeouts. Use when the user says "generate an image", "make a picture", "create a visual", "render this", "edit this image", "做一张图", "生成图片", "改这张图" — or when invoked as the image-generation backend by another product-shots skill (main-image / detail-page / ad-creative / social-post / multi-angle). NOT a creative-direction skill: takes a prompt + optional reference images, returns a file path.
qws zoom-out: Step back from the current details and find the level where the problem truly lies. First assess whether the question itself is right and which steps may be unnecessary, then provide the final solution in the same reply. If the question is misguided, reframe it correctly and answer it. Use when this Skill is invoked (/qws-zoom-out, $qws-zoom-out, Skill link), or the user says “zoom out,” “look at the big picture,” or “is this a local issue?” It can also be loaded when the user remains dissatisfied after repeated revisions to the same thing (e.g. “still not right,” “it keeps getting worse,” “why do you keep changing it,” “the AIs all say different things”), but only add a brief note at the end of the reply suggesting a zoom-out; do not launch into analysis automatically. Do NOT use for specific business execution
React data-fetching patterns at scale — recommender carousels, infinite feeds, pages with many parallel fetches, dashboards. Covers request orchestration (parallelism, batching, deduplication), cache strategy (keys, normalization, staleTime, SWR), backend protection (concurrency caps, debounce/throttle, jittered retries, circuit breakers), prefetching (route loaders, hover/intent, idle, server hydration), failure resilience (AbortController, timeouts, error boundaries, stale fallback, idempotent mutations), and feed/carousel patterns (virtualization, cursor pagination, summary/detail split). Includes 5 ready-to-use scaffolding templates (resource query hook, carousel data loader, infinite feed, hover-prefetch link, request collapser). Trigger when building, reviewing, or refactoring React components that fetch data — even if the user doesn't explicitly mention "performance" or "scale".
Measure, profile, optimize, and regression-test Rust performance across latency, throughput, CPU, allocations, memory, binary size, and compile time using representative workloads, Criterion, iai-callgrind, cargo-flamegraph, samply, DHAT, heap or pprof tools, cargo-bloat, cargo-llvm-lines, and build timings. Use when users report slow Rust code, high memory or CPU, large binaries, noisy benchmarks, tail-latency regressions, or need performance budgets and evidence-backed optimization.
Close a workstream and ship it to production with ONE approval point: it independently checks what will ship (syntax, tests, secrets in the diff, outdated base), shows once exactly what goes to production and whether the push publishes on its own, and only after the user's OK does it commit, integrate, publish and verify. Use from inside the workstream folder when the user says 'release', 'publicar', 'subir para produção', 'fechar a frente' or 'integrar'. It is the other end of the sdd-new-session skill.
How to send real-time in-app notifications from PostHog backend code. Use when integrating notifications into a new feature, wiring up a notification source (alerts, comments, approvals, pipelines, issues), or choosing the right target type and priority for a notification.
Audit, score, or improve an existing skill using repository checks, free Tessl lint, optional credit-aware Tessl review, metadata discovery, progressive disclosure, eval coverage, and repo conventions. Use for skill quality, activation failures, package comparisons, or publish readiness. Do not use for general code review, application verification, or unrelated documentation cleanup.
BM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only compact view (~2K tokens) and injects top-K relevant skill descriptions per turn via BM25 retrieval (~300 tokens). Saves ~9K tokens/turn. Use when system prompt token overhead from skills is a concern, or when skill discovery quality matters.
Construir e revisar sites Astro com renderização, content collections, ilhas de interatividade, actions, integrações, imagens, SEO e performance. Use quando houver astro.config ou dependência astro e a tarefa tocar páginas, layouts, componentes, endpoints ou conteúdo; use também para decidir a diretiva de hidratação correta de uma ilha; não use para lógica interna do framework de UI hidratado numa ilha React — aí combine com a skill React.
SSH remote access patterns and secure shell utilities. Covers connections, config management, key generation (Ed25519, FIDO2), tunneling, port forwarding, file transfers, and multiplexing. Use when connecting to servers, managing SSH keys, setting up tunnels, transferring files over SSH, configuring jump hosts, or hardening SSH access.
Survey Director — Responsible for topic planning, outline design, task assignment, and final review for frontier AI/ML survey papers. Activate when the user requests help writing a survey. Coordinates 5 Agents through the entire process, from topic selection to final draft.
Worked full-length scripts of banqiang-system Chinese opera with their creation records (板腔体全本语料库). Primary texts; 翁偶虹《锁麟囊》 (the revised score edition, 65 arias, 15 self-account-vs-score checks), 汪曾祺等《沙家浜》 (the 1965 text, not the 1970 one; 36 arias, a 12-row two-version diff), 田汉《白蛇传》 (the 1955 book, not the web revision; 16 scenes, 王瑶卿说腔五条), 杨兰春《朝阳沟》 (1978 revival, 50 arias, 口语入唱, per-scene sung/spoken ratios), 魏明伦《潘金莲》 (跨时空, missing pages), 罗怀臻's 越剧《李清照》《真假驸马》, 淮剧《金龙与蜉蝣》, 甬剧《典妻》; plus index tables of 翁偶虹's 60 创作记 and 范钧宏's seven 改编札记. Use when you want to see how a 唱工戏 lays out its 板式, need real scene counts, aria counts and 辙口 to imitate, want the road from raw material to 审腔, are writing a 现代戏 or colloquial lyrics, or compare one author across two声腔 systems. Method is in sw-chinese-opera-banqiang; this skill holds the worked scripts and their creation records.
Chinese opera playwriting for the qupai (曲牌体) system — 元杂剧, 明清传奇, 昆曲, 川剧高腔, where sung text is filled into fixed tune patterns (填词) rather than built from paired lines varied by metre. Covers stage vs study (李渔 vs 吴梅/王季烈), the 清曲/剧曲 switch, the zaju branch (四折一楔子, one 宫调 and one rhyme per act, 一人主唱, 题目正名), the chuanqi branch (出, 副末开场, 南北合套, 集唐下场诗), tune-filling (格律, 前腔/换头/幺, 衬字, 务头, 尾声, 四十禁), the seventeen 宫调 and their affects, 套数, 排场 alternation, the spoken-to-sung cue, 帮腔, adaptation, and modern practice. From 李渔《闲情偶寄》, 吴梅《顾曲麈谈》《曲学通论》, 王季烈《螾庐曲谈》, 孔尚任's 凡例, 关汉卿, 汤显祖, 魏明伦. Use when writing or revising a 曲牌体 script, choosing a 宫调 for an emotion, laying out a 套数, filling one tune pattern, writing a zaju act or a chuanqi scene, cutting an old 传奇 into a playable version, writing a modern qupai opera, or judging whether a famous script's prosody may be copied. Not for 京剧/豫剧/越剧, which are the banqiang system; see sw-chinese-opera-banqiang.
Use when working with 3D math in Three.js: vectors, matrices, quaternions, rotations, colors, or coordinate transforms. Prevents the common mistake of mutating shared vectors, using wrong rotation order, or confusing Euler gimbal lock. Covers Vector3, Matrix4, Quaternion, Euler, Color, MathUtils, Box3, Sphere, coordinate system. Keywords: Vector3, Matrix4, Quaternion, Euler, Color, MathUtils, lerp, slerp, cross, dot, normalize, degToRad, Y-up, right-handed, rotate object, position math, smooth interpolation.
Use when creating 3D shapes, custom geometry, or instanced meshes in Three.js. Prevents the common mistake of forgetting dispose(), not setting needsUpdate on BufferAttribute, or using non-indexed geometry when indexed is better. Covers BufferGeometry, BufferAttribute, all 21 built-in geometries, InstancedMesh, ExtrudeGeometry, custom geometry. Keywords: BufferGeometry, BoxGeometry, SphereGeometry, PlaneGeometry, InstancedMesh, BufferAttribute, geometry, shape, extrude, custom mesh, particles, point cloud, particle system, create shape.
Build dashboards, analytics interfaces, and data-rich UIs using the Tremor design system (React + Tailwind CSS + Recharts). Use when the user asks to create dashboard components, KPI cards, charts, data tables, analytics pages, monitoring interfaces, or any data visualization UI that should use Tremor. Triggers include mentions of "Tremor", "tremor.so", "@tremor/react", requests for dashboard UIs with charts and tables, or when the user's project already uses Tremor components. Supports both Tremor Raw (copy-and-paste, tremor.so) and Tremor NPM (@tremor/react) versions. Do NOT use for general frontend work unrelated to dashboards or data visualization, or when the user explicitly requests a different component library.
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.