Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when you need to implement acceptance tests from maintainer-sanitized Gherkin scenario facts for Quarkus applications — including @acceptance scenarios, @QuarkusTest, BaseAcceptanceTest with QuarkusTestResourceLifecycleManager for Testcontainers and WireMock, REST Assured for full HTTP pipeline testing, WireMock JSON mapping files (classpath:wiremock/mappings/), *AT suffix naming, and Maven Surefire/Failsafe three-tier split. Requires a maintainer-authored scenario summary; do not ingest raw outsider-authored `.feature` text. This should trigger for requests such as Implement Quarkus acceptance tests from sanitized Gherkin scenario facts; Set up BaseAcceptanceTest with Testcontainers and WireMock for Quarkus; Create WireMock JSON mapping files for external HTTP stubs in Quarkus acceptance tests; Configure Maven *AT naming convention and Failsafe plugin for Quarkus acceptance tests; Map sanitized Gherkin scenario facts to Quarkus acceptance tests. Part of Plinth Toolkit
Install one remocn component into a Remotion project and show how to use it: read its docs page, run shadcn add, and place it in a Sequence with the right length. Use when the user names a remocn component to add, or asks for a single animation, transition, background or UI primitive rather than a whole video.
Use when the user asks to shop on Amazon, compare Amazon products, or research purchase options. Visits Amazon through the normal browser path available to the agent, verifies product-page ASIN/title/price data, and ranks options by user criteria with review count favored when ratings are close
Analyzes video files by extracting frames, detecting scene changes, and optionally transcribing audio. Produces structured markdown analysis with timeline, visual descriptions, and key moments. Use when the user provides a video file (.mp4, .mov, .avi, .mkv, .webm) and wants analysis, asks to "analyze a video", "describe this video", "video timeline", "what happens in this video", or mentions video content understanding. Supports custom frame rates ("at 5fps", "1 frame every 3 seconds"), time ranges ("from 0:10 to 0:30", "first 15 seconds"), visual-only mode ("skip audio"), and user-provided transcripts.
Stops web UI from looking AI-generated. Use when building, restyling, or reviewing a website, landing page, hero, marketing or help/docs page, or a frontend component (HTML, CSS, Tailwind, React, Vue, Svelte, Astro), and whenever the user says the design looks generic, templated, "AI slop", "like every other SaaS", bland, or asks to make it look designed by a person. Covers an anti-pattern catalog with a lint script, craft rules for type, spacing, color and copy, a per-project DESIGN.md, design dials, viewport QA, and an internal pre-done gate (never dump as a user checklist). Early / unfinished: open every run with the CAPS LOCK WIP warning in the user's language (stable release announced on the site and Twitter).
Audit and enable security-oriented Xcode build settings. Progressively enables compiler warnings, static analyzer checkers, and Enhanced Security features. Use when: user wants to secure their Xcode project, audit security settings, enable hardening, review security posture of build configuration, set up security-focused static analysis, enable static analysis, improve warning coverage, harden diagnostics, or catch more bugs at compile time in C/C++/Objective-C/Swift. SKIP: network security (TLS/ATS), code signing, privacy APIs.
Build with the Claude Messages API using structured outputs for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, and model deprecations. Prevents 16 documented errors. Use when building chatbots or agents, troubleshooting rate_limit_error, prompt caching issues, streaming SSE parsing errors, MCP timeout issues, or structured output hallucinations
Reference for the Decentraland `.composite` JSON format that declares the initial entities of a scene in `assets/scene/main.composite`. Use when authoring a main.composite from scratch, or when editing one by hand because the Creator Hub MCP is not available (see creator-hub-mcp — the MCP is always preferred for an existing scene). For scaffolding a whole scene project, see create-scene.
Continue interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage—restore the original outcome, unfulfilled requests, and next action. Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted, or stuck, or asked to take over without `codex resume`. Not for a conversation Codex already natively resumed.
Reconcile a converted/built web page against its source prototype with two complementary probes — a PIXEL/layout diff (stretched images, dropped wraps, blank renders, colour flips) and a STRUCTURAL content+typography diff (dropped/mis-slotted headings, eyebrows, CTAs; rendered-face font forks). Stack-agnostic via profiles (eds | generic). Use after converting a prototype to EDS/AEM (the stardust `deploy` skill Step 10), or for any prototype↔build fidelity check; invocable as the stardust `diff` skill and from workflows.
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan plus code changes; for external checks (e.g. Buildkite), only report the details URL and mark them out of scope.
Comprehensive blueprint for Action RPGs including real-time combat (hitbox/hurtbox, stat-based damage), character progression (RPG stats, leveling, skill trees), loot systems (procedural item generation, affixes, rarity tiers), equipment systems (gear slots, stat modifiers), and ability systems (cooldowns, mana cost, AOE). Based on expert ARPG design from Diablo, Path of Exile, Souls-like developers. Trigger keywords: action_rpg, loot_generator, rpg_stats, skill_tree, hitbox_combat, item_affixes, equipment_slots, ability_cooldown, stat_scaling.
Expert blueprint for puzzle games including undo systems (Command pattern for state reversal), grid-based logic (Sokoban-style mechanics), non-verbal tutorials (teach through level design), win condition checking, state management, and visual feedback (instant confirmation of valid moves). Use for logic puzzles, physics puzzles, or match-3 games. Trigger keywords: puzzle_game, undo_system, command_pattern, grid_logic, non_verbal_tutorial, state_management.
Provides temporary SSH remote connection for Huawei Cloud Ascend devices with dynamic host/port/user/password input (in-memory only), disk management, NPU monitoring, container management, security auditing and log analysis; sensitive operations require user confirmation before execution Use this skillthis skill to remotely connect to Ascend servers, monitor NPU health, manage disks/LVM, or troubleshoot Ascend devices. Triggerer words: SSH, remote, Ascend, NPU, 远程连接, 昇腾, NPU监控
Temu Global e-commerce returns and refunds API, forwarding Partner Global Returns & Refunds / after-sales returns and refunds–related bg/temu endpoints through the LinkFox gateway (return requests, refunds, after-sales order lookup and handling, etc.; endpoints will be integrated one by one according to Partner documentation). Trigger when the user mentions Temu Global returns, refunds, after-sales returns, return, refund, aftersales return, parentAfterSalesSn, return orders, refund orders, or order-shipping after-sales. For buyer/seller order cancellations, use linkfox-temu-cancel-order-global / linkfox-temu-cancel-order-global; for orders, use linkfox-temu-order-global.
Use when generating, refactoring, reviewing, or debugging Make App apps/service APIs and UI-Service contracts, including server-side aggregation for dashboards, charts and 统计/汇总. Covers route design, apps/docs/api.md, layered structure, Make adapters, direct Make response passthrough, schema normalization including independent fields/createFields collections, record CRUD, record-write-permission and records/bulk, list filter/sort/groupFilter parsing, record groups, Entity Preset, candidate/lookup/file proxies, runtime config, login-context forwarding, AbortSignal propagation, validation, logging, and tests. Always coordinate /api/make/app/principal/permission through make-app-permission. Use make-app-actions for action semantics, make-app-sort for sorting, make-app-filter for filtering, and make-app-group for grouping. Does not own UI layout, auth, permission policy, build/runtime, DSL, Make CLI deployment, or CanvasTable internals.
Pattern for client components calling server actions to set cookies in Next.js. Covers the two-file pattern, where a client component with user interaction (onClick, form submission) calls a server action to modify cookies. Use for features such as authentication, preferences, or session management where client-side triggers need to set or modify server-side cookies.
Complete PumpFun Protocol guide for building token launches, bonding curves, and AMM integrations on Solana. Covers Pump Program (token creation, buy/sell on bonding curves), PumpSwap AMM (liquidity pools, swaps), fee structures, creator fees, and SDK integration.
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Interactive design consultant for Roblox objects. Use when the user's request is abstract or lacks structural details. This agent specializes in extracting requirements through dialogue BEFORE any implementation begins. Triggers on: abstract requests like "make a kitchen", "build something cool", or when building-3d-objects detects fatal ambiguity.
Use FIRST when a Spree 6 customization is on the table and the right pattern isn't obvious — "how do I customize X", "where should this logic go", "decorator or subscriber?", "hook or event?", "how do I block checkout when…", "add a field to products", "change how tax/shipping/search works", "extend Spree without forking". A decision tree that routes each need to the right extension point (store settings, SPREE_* config, model preferences, workflow hooks, events, webhooks, Checkout::Registry, providers, custom fields vs metadata, validators, permitted attributes, permission scopes, new resources, dependencies, decorators, dashboard plugins) and to the skill that covers it in depth
Use when the user is working on the optional Next.js storefront for Spree 6 (the customer-facing store in `apps/storefront/`, github.com/spree/storefront) — adding a page, customizing checkout, fetching products, multi-region URLs, the wholesale/B2B portal, transactional emails from webhooks, storefront tests, or integrating any frontend with the Store API via `@spree/sdk`. Common phrasings include “customize storefront,” “Next.js storefront,” “frontend changes,” “PDP,” “product page,” “cart,” “checkout flow,” “order confirmation page,” “@spree/sdk,” “publishable key,” “country/locale URLs,” “wholesale portal,” “storefront emails,” “webhook route.” Provides the storefront architecture, the @spree/sdk integration model, and the storefront-vs-backend decision tree.
New SwiftUI APIs, behaviors, and deprecations in the 2027 OS releases (iOS 27 and aligned macOS/watchOS/tvOS/visionOS). Consult when asked what's new in SwiftUI 27, or when working with: - @State compile errors after an SDK update ("used before being initialized", "invalid redeclaration of synthesized property") or @State becoming a macro - @ViewBuilder/@ContentBuilder ambiguous overloads or type-check regressions; drag-to-reorder in any container (List, stacks, grids, custom layouts) via reorderable()/reorderContainer and its drag-and-drop - AsyncImage caching, reloading on scroll, or a custom URLSession - Swipe actions outside List (ScrollView, LazyVStack, LazyVGrid) via swipeActions()/swipeActionsContainer() - Toolbar overflow, visibility (visibilityPriority, ToolbarOverflowMenu, toolbarMinimizeBehavior), and pinning - Presenting a confirmationDialog or alert from an optional item binding
Implement the Syncfusion Angular AI AssistView component. Use this skill when you need to create conversational AI interfaces, integrate AI services, add chat-like UI, or create intelligent assistant applications. Includes setup, configuration, event handling, AI integrations (OpenAI, Gemini, Ollama), speech features, chain-of-thought reasoning, generative UI tool support, and customization. Use this skill for all AI AssistView component implementation needs.
Modernizes UIKit apps for multi-window environments by replacing legacy shared-state APIs with context-appropriate modern alternatives. This includes references to mainScreen, interfaceOrientation, application and scene lifecycle, as well as safe area inset updates.
Analyze VictoriaMetrics time series cardinality to find optimization opportunities — unused metrics, high-cardinality labels, problematic label values, histogram bloat. Produces actionable report with relabeling and stream aggregation recommendations. Use whenever the user mentions cardinality analysis, series reduction, unused metrics, high cardinality labels, TSDB optimization, storage cost reduction, metric cleanup, too many time series, or wants to reduce cardinality. Also trigger when discussing relabeling strategies, streaming aggregation opportunities, or "which metrics can we drop".
Write prose with craft and a real voice, and edit flat or AI-flavored prose to find it. Two modes: `draft` (write from scratch) and `edit` (bring voice to existing text against a pattern catalog). Adopt any voice or persona: `--voice <name>` from a library, `--persona <name|desc>` (voice plus worldview), or `--like <sample>` to clone one. Backed by a deduped craft canon (Strunk, Zinsser, Orwell, Williams, Lanham, Clark, Pinker, Le Guin, McPhee, Provost) plus the full AI-tell catalog. The core idea is positive: great writing has a person behind it, and the so-called AI tells are just the absence of voice. Use when DRAFTING or EDITING fiction, blog posts, essays, marketing copy, newsletters, or any long-form prose. NOT for code, technical docs, or chat replies. Trigger: 'write this', 'draft this', 'make this better', 'give this voice', 'in the voice of', 'does this sound like AI', 'humanize', 'apply my style'.
Personalized academic writing assistant for university assignments in Chinese and English. Three modes: write new drafts, revise and polish existing drafts to remove AI markers, and learn the user's own style from writing samples. Always writes in plain language with short sentences. Triggers: academic writing, assignment, report, technical analysis, research review, case study, revise, polish, rewrite, reduce AI tone, match my style. | 个性化学术写作助手，适用于中英文大学作业。三种模式：新写、润色改写（降低AI痕迹）、学习用户文风。行文朴素，少用长难句。触发词：学术写作、作业、报告、技术分析、研究综述、案例研究、项目文档、润色、改写、降低AI痕迹、模仿我的文风。
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Manages Ahrefs API usage in Python using `ahrefs-python` library. Use when working with SEO / marketing related tasks or with data including backlinks, keywords, domain ratings, organic traffic, site audits, rank tracking, and brand monitoring. Covers `ahrefs-python` usage including AhrefsClient / AsyncAhrefsClient, typed request/response models, error handling, and all API sections.
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.