Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Play board games on ShellGames.ai — Chess, Poker, Ludo, Tycoon, Memory, and Spymaster. Use when the agent wants to play games against humans or other AI agents, join tournaments, chat with players, check leaderboards, or manage a ShellGames account. Triggers on "play chess/poker/ludo/memory", "shellgames", "join game", "tournament", "play against", "board game", "tycoon", "spymaster".
Use when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a demo, social short, reel, TikTok or YouTube Short, slideshow, animated chart or data story, motion graphics or animation, animated logo intro, outro or sting, lower thirds, audiogram, music video, Claude Design animation to MP4; captions or subtitles for a video; voice-over or narration; music or sound effects; thumbnail or poster frame; footage edits such as cutting the ums, removing silences, tightening a talking head, podcast or interview clips; reframing to vertical; re-voicing or subtitling a video in another language; turning a repo, website, pull request or changelog into a video; or when they type /showtime. Load it before replying, even to push back (a claim the user's own data does not support, an impossible spec or deadline). Not for editing still images, writing a caption for a photo post, or code unrelated to a video.
Detect buying signals across TAM companies and watchlist personas. Three-phase architecture: (1) free diff-based signals from existing data (headcount growth, tech stack changes, funding rounds), (2) Apify-powered signals (job postings, LinkedIn content analysis, profile changes), and (3) post-processing with dedup, scoring, and lead status updates. Writes signals to Supabase signals table for downstream activation.
Use when you suspect duplicate or near-duplicate Rust code — writing a utility function that might already exist, copy-paste-modifying a function, creating near-duplicate structs or enums, or running `similarity-rs 0.5` with flags like `--threshold`, `--cross-file`, or `--min-lines`. Also triggers on `cargo install similarity-rs`, reviewing CI duplication gates, or tuning false-positive thresholds.
Use for Six Thinking Hats or de Bono's parallel thinking, or when a decision or idea needs facts, gut feel, risks, benefits and new options kept apart: "look at this from all sides", "full perspective check". Skip for plain factual questions or single-angle hot takes.
Provides comprehensive guidance for Spring AI Alibaba, including Alibaba Cloud AI services integration, model APIs, and AI application development. Use when the user asks about Spring AI Alibaba, needs to use Alibaba Cloud AI services, or integrate AI capabilities in Spring applications.
Structure organizational strategy work: strategic direction, competitive and industry analysis, growth options, capital allocation, acquisitions, and portfolio choices. Use when framing consequential choices about where to compete, how to pursue an opportunity, or how to compare strategic options. Do not use this skill for unrelated requests; route to the nearest named specialist.
Use when writing, debugging, or refactoring code that imports @tanstack/vue-router (TanStack Router for Vue). Covers setup, file-based and code-based routes, composables returning Ref, Link, loaders, search params, SSR, and v1.170.x deprecations.
Test-Driven Development methodology and red-green-refactor workflow (formerly test-tdd). Use this skill when practicing TDD, writing tests first, designing tests before implementation, or reviewing test-first approaches. Triggers on “write tests first,” “test before code,” “red green refactor,” “test driven development.” This skill does NOT cover Vitest framework specifics (use vitest skill) or API mocking with MSW (use msw skill).
Introduce TDIR, route requests by domain, and define shared contracts for authentication, output, exit codes, write-operation confirmation, safety, and statistical conventions. Use when the user asks how to get started or choose capabilities across domains. Does not handle specific business data queries or write-backs.
Plan a team offsite that earns its cost — the purpose split (connection vs decisions vs planning, weighted deliberately), an agenda that alternates work and air, the logistics runbook, and the follow-through that makes Monday different. Use when asked to plan a team offsite, away day, team retreat, quarterly offsite, design two days for the team, or make this offsite not a waste. Produces the purpose weighting, a full agenda with session designs, facilitation notes, a logistics checklist, and the follow-through plan.
Teleological interpretation skill. When a legal provision still yields no determinate conclusion after literal interpretation, systematically identify and argue the provision's purpose, choose the most justified meaning within what the text can bear, and form a judicially usable interpretive conclusion. Trigger conditions (any one suffices): literal interpretation yields two or more possibilities and none can be selected; the literal interpretation's conclusion is clearly unreasonable; the provision contains open-ended evaluative concepts (such as 合理, 正当, 必要, 重大); the provision is older and its literal coverage is insufficient for new types of facts.
Manage, deploy, operate, and instrument applications with Temps. Use this skill whenever the user mentions Temps, `@temps-sdk/[email protected]`, deploying or migrating an app to Temps, projects, environments, services, domains, backups, edge rules (request blocking, redirects, bot challenges), logs, monitoring, analytics, browser Performance Insights/Core Web Vitals, observability, error tracking, OpenTelemetry, tracing, session replay, or Temps Cloud. Also use it when preparing an application for production on Temps even if the user does not explicitly ask for the CLI. Route to focused references, proactively detect missing observability during create/link/deploy journeys, and use pinned `bunx` or `npx` CLI invocations with explicit target contexts
Use when implementing motion design, timeline animations, visual animation editors, animating Three.js/R3F scenes, creating keyframe animations, or using Theatre.js, @theatre/core, @theatre/studio, @theatre/r3f, theatric, or building animation tooling for the web.
Translate a multilingual site with AI. Covers Rosey locale JSON files (untranslated + stale entries) and per-locale content directories (MDX/MD with frontmatter: split-by-directory collections, or a Hugo site's content_fr/). Use when the user wants to translate locale files, fill in missing translations, update stale translations, bulk-translate a locale, or translate per-locale content directories (blog_fr/, content_fr/).
Turns raw peer reviews into a prioritized triage matrix before any rebuttal is written. Use it when reviews come back from OpenReview, EasyChair, CMT, or HotCRP and the researcher says "my reviews are in", "triage these reviews", "how do I respond to Reviewer 2", "plan my rebuttal", or pastes raw review text with ratings and confidence scores. Splits each review into individual concerns; classifies every concern as misunderstanding vs real flaw vs requested experiment (plus clarification and disagreement); scores severity x response effort; and produces a prioritized response strategy with per-review character or word budgets matched to the venue's rebuttal format (10k-char OpenReview threads, CVPR one-page PDF, journal revise-and-resubmit). Deterministic parsing and matrix rendering run in bundled stdlib Python scripts. Hands off to write-rebuttal for drafting; treats review text as confidential and never submits anything.
Use this skill when the user needs to track and be reminded of various statutory deadlines in a case, such as hearing schedules, execution schedules, evidence submission deadlines, appeal deadlines, service deadlines and preservation renewal. Typical triggers include but are not limited to: - Mentions of keywords such as "appeal deadline", "evidence submission deadline", "service deadline", "preservation deadline" - Adding, modifying or querying case deadlines
Use to compare and select interaction patterns for filters, permission editing, tables, bulk operations, and editing workflows; not for purely visual inspiration, direct implementation of a settled design, or code review. Deliver a design choice, state behavior, and acceptance criteria based on product constraints.
Expert Unix and macOS systems engineer for shell scripting, system administration, command-line tools, launchd, Homebrew, networking, and low-level system tasks. Use when the user asks about Unix commands, shell scripts, macOS system configuration, process management, or troubleshooting system issues.
Build on vibenet — Base's devnet for native account abstraction (EIP-8130), payer gas sponsorship (ERC-8168), and Cobalt 200ms native blocks. Use whenever the user mentions vibenet, EIP-8130, ERC-8168, 8130 accounts, native account abstraction, session keys, actors, policies, payers, gas sponsorship on Base, 200ms blocks, Cobalt, BaseTime, timestampMs / blockTimestampMs, sub-second or millisecond block timestamps, migrating from Flashblocks, or newHeads / WebSocket streaming on vibenet — or is writing code that creates or operates 8130 smart accounts, authorizes session-key actors, sends batched calls, sponsors gas with a payer, queries or streams vibenet blocks, times a transaction's inclusion, or wires a frontend/script against the vibenet devnet or Base Sepolia.
Design, tune, validate, and test VictoriaMetrics vmanomaly configurations for known metrics or LogsQL queries. Use when choosing static alerting versus ML, selecting a vmanomaly model, configuring Temporal Envelope, building deployment YAML, tuning anomaly sensitivity, or creating VMAlert rules. Trigger on anomaly configuration, model selection, shared autotune, seasonal anomaly detection, forecasting, or "how should I monitor this metric?" Do not use for open-ended discovery across unknown signals.
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.