Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Design a ProcessOn-ready mind-map outline for ideas, requirements, knowledge systems, meeting notes, learning plans, or hierarchical analysis. Use when the user explicitly requests a ProcessOn mind map, editable mind map, or a hierarchical outline intended for ProcessOn. Do not trigger for ordinary diagrams, generic prose outlines, or Mermaid mind maps unless ProcessOn is requested.
Give sparse, evidence-based progress updates for long-running agent tasks and projects. Use when work will take more than 15 minutes, spans multiple milestones, involves delegated agents, or when the user asks for progress bars, status cadence, fewer updates, or a global cross-agent progress rule. Not for short answers or tasks with no meaningful intermediate state.
Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building LLM applications requiring reliable outputs, implementing RAG systems, creating AI agents, or optimizing prompt quality and cost. Covers OpenAI, Anthropic, and open-source models with multi-language examples (Python/TypeScript).
Expert guide to end-to-end Python video pipelines combining FFmpeg, OpenCV, PyAV, ffmpegcv, Decord, VidGear, and Modal.com for scalable GPU-accelerated workflows. PROACTIVELY activate for: (1) FFmpeg+OpenCV in same pipeline (decode, process, re-encode); (2) color-format mismatches (BGR vs RGB across OpenCV, PIL, PyAV, FFmpeg); (3) frame dim ordering (HWC vs CHW) between OpenCV and ML frameworks; (4) audio stream loss in filter chains; (5) memory mgmt for long/large videos (streaming vs in-memory); (6) choosing ffmpegcv/Decord/VidGear/PyAV for performance; (7) GPU decode/encode on Modal.com; (8) parallel + chunk-based processing on Modal; (9) transcoding pipelines on serverless; (10) HLS generation on Modal; (11) upload -> process -> transcode -> HLS workflows; (12) batch sizing for GPU memory, pixel formats, large-video streaming. Provides: library selection matrix, integration recipes, Modal.com deployment examples, GPU pipeline tuning, production-ready workflow examples.
Review a pull request as a QA engineer — check whether the change actually solves the stated issue, flag backwards-compatibility breaks and risks, and list the scenarios that must be verified before merge. Use when asked to "review this PR as QA", "what should we test in this PR?", or "is this PR safe to merge?".
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally
Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.
Cross-browser, cross-platform, and cross-device compatibility testing ensuring a consistent experience across environments. Use when validating browser support, testing responsive design, or ensuring platform compatibility.
Optimizes QE agent performance through transfer learning, hyperparameter tuning, and pattern distillation across test domains. Use when improving agent accuracy, applying learned patterns to new projects, tuning quality thresholds, or implementing continuous improvement loops for AI-powered testing.
Internationalization (i18n) and localization (l10n) testing for global products including translations, locale formats, RTL languages, and cultural appropriateness. Use when launching in new markets or building multi-language products.
Apply Edward de Bono's Six Thinking Hats methodology to software testing for comprehensive quality analysis. Use when designing test strategies, conducting test retrospectives, analyzing test failures, evaluating testing approaches, or facilitating testing discussions. Each hat provides a distinct testing perspective: facts (White), risks (Black), benefits (Yellow), creativity (Green), emotions (Red), and process (Blue).
Analyzes Rails applications and generates comprehensive upgrade reports with breaking changes, deprecations, and step-by-step migration guides for Rails 2.3 through 8.1. Use when upgrading Rails applications, planning multi-hop upgrades, querying version-specific changes, or answering what stands between the app and the next Rails version. Based on FastRuby.io methodology and "The Complete Guide to Upgrade Rails" ebook.
Find the animations an interface doesn't need and remove them — motion on keyboard actions, high-frequency surfaces, functional data, and decoration with no purpose — then clean up what they leave behind. Edits code, but only to subtract; it never adds or retunes motion. Use when the user says the app "feels slow", "has too much animation", "feels over-animated", wants to "tone down the motion", or asks what animations to remove. For finding places that should animate, use find-animation-opportunities; for fixing animations that should stay, use improve-animations or review-animations.
Use for any in-page content edit on a WordPress site with a page builder. Covers finding elements, applying surgical edits, duplicating before large changes, and verifying the result. Works across Elementor 3 + 4, Divi 4 + 5, Beaver Builder, Bricks, Oxygen Classic, Oxygen 6, Breakdance, WPBakery, Uncode, and Gutenberg.
Load this skill for any project with a user interface that must work across screen sizes and input methods, such as websites, web apps, dashboards, marketing pages, emails, or design systems. Use when building or reviewing layouts, choosing breakpoints, setting up fluid type, sizing touch targets, or making components adapt to their container. One design must serve phones, tablets, laptops, desktops, touch, mouse, and keyboard. Prefers content-first, mobile-first, framework-agnostic CSS and Baseline-stable features.
Internal tech-debt transform pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Transforms the synthesized findings table into explicit debt items, each with a re-trigger condition; it does not rescan the diff. Findings only; never edits code.
This skill MUST be used when customer reviews, support tickets, app store feedback, or similar text must be scored and analyzed statistically for segmentation, targeting, and positioning (評論分析、客群區隔、目標市場、產品定位、STP). It MUST NOT be used for qualitative summaries or review tagging alone.
Internal run-it verification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Runs the project's gate and the changed behavior for real — commands, exit codes, observed output — instead of assuming; what cannot be executed goes to the manual checklist. Findings only; never edits code.
Answers Riverpod FAQ (ref.refresh vs invalidate, ConsumerWidget vs StatelessWidget, Ref vs WidgetRef, reset all providers, ref after unmount) and do/don't best practices (avoid init in widgets, avoid ephemeral state in providers, avoid side effects in provider init, static providers, riverpod_lint). Use when the user asks Riverpod FAQ, best practices, or do/don't guidelines.
How Roblox behaves at runtime. Use whenever writing, reviewing, or debugging server/client Roblox code that touches services, Instances, replication, RemoteEvents/Functions, character lifecycle, physics, DataStore, or platform caveats. Engine layer only — language rules live in luau-expert; UI libraries live in roblox-ui; Rojo/Wally workflow lives in roblox-toolchain.
Execute approved implementation plans phase by phase with automated and manual verification. Use when the user explicitly says "implement the plan", "execute the plan", or "start implementing" and has a plan file ready. Do not use for ad-hoc coding tasks without a plan.
This skill MUST be used for semantic Rust navigation and analysis: resolving definitions across crate boundaries, finding all references to a symbol, inspecting inferred types or trait implementations, searching symbols by name, and renaming symbols safely. SHOULD be preferred over grep or file reads whenever the task requires Rust-aware understanding.
The addon billing lifecycle for a Salla app — defining an addon, activating on app.subscription.started (item_type "addon", matched by item_slug), persisting the entitlement, and handling renewal/cancellation/expiry. Use when wiring what happens AFTER a merchant buys an addon, tracking addon subscriptions, or gating features by addon. The in-iframe purchase UX is part of the embedded flow → salla-addon-purchase-embedded. Plan/pricing/entitlement primitives → salla-app-billing; webhook hygiene → salla-webhooks.
The in-app addon purchase UX inside an embedded Salla app — list the app's add-ons, open a native checkout, and hear the payment result via the embedded SDK Checkout module (`embedded.checkout.getAddons` / `.create` / `.onResult`). Salla owns billing; never collect payment in the iframe. Use when building the buy/upsell UI in an embedded page or wiring the checkout handoff. Part of the embedded flow → salla-embedded-app. Activation + entitlement lifecycle after purchase → salla-addon-purchase.
Router for building Salla App Functions — serverless TS/JS handlers Salla runs in a sandboxed V8 on store events (e.g. `order.created`, `shipment.creating`). Start here for any App Function task, then follow the step skills: design the trigger, write the handler, validate, test, release. Prefer App Functions over webhooks; act with `salla_functions`. Builds on salla-api-core and salla-webhooks.
Use when a PUBLIC Salla app is going to review (App Store listing): the master skill for stepwise publication via app_publish. It reads the current draft, routes each step to its owner, and HARD-GATES sending to admin review behind a clean validate plus the partner's explicit confirmation. Private apps publish via salla_private_apps — see salla-app-builder. Hand-offs: listing/images → salla-app-ui-builder; pricing + billing cycle → salla-app-billing; scopes → salla-app-auth; webhooks → salla-webhooks; settings → salla-app-settings.
Make a Salla app's STOREFRONT (the store) UI native — shopper-facing pages on the Twilight theme. Build from native `<salla-*>` web components driven by the Storefront JS SDK, inherit Twilight CSS tokens, use Salla Icons (`sicon-*`), match the page's spacing, write Arabic-first/RTL, and verify with a LIVE screenshot on an installed demo store (`url`). Use when a snippet draws visible UI. Injection recipe → salla-snippets. Embedded/dashboard UI → salla-embedded-ui.
A skill that takes a news headline as input and analyzes an 18-month scenario. Runs the main analysis with the scenario-analyst agent and gets a second opinion from the strategy-reviewer agent. Generates a comprehensive report in Japanese including first-, second-, and third-order impacts, recommended stocks, and a review. Example usage: /scenario-analyzer "Fed raises rates by 50bp" Triggers: news analysis, scenario analysis, 18-month outlook, medium- to long-term investment strategy
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.
A collection of algorithms for image processing in Python. Built on NumPy, SciPy, and Cython. It focuses on scientific image analysis including segmentation, geometric transformations, color space manipulation, analysis, and filtering.
"Searches aptos-core and daily-move for reference implementations before writing contracts. Triggers on: 'search examples', 'find example', 'check aptos-core', 'is there an example', 'reference implementation', 'how does aptos implement', 'similar contract', 'daily-move'."
Advanced information retrieval specialist combining systematic search strategies, multi-platform expertise, and precision filtering techniques. Excels at finding specific, high-quality information across diverse sources while minimizing noise and maximizing relevance.
Configures the security features of the Harbor open-source container registry - integrated Trivy scanning, Cosign and Notary content trust policies, project-level RBAC, immutable tag and retention rules, and OIDC authentication - to enforce provenance and block deployment of vulnerable images. Use when deploying or hardening Harbor, or when compliance requires that only signed and scanned images can be pulled. Keywords: Harbor, project policy, content trust, immutable tag, retention, robot account, OIDC, replication. Do not use for signing images with Cosign outside a registry - use implementing-image-provenance-verification-with-cosign.
Write high-quality prompts for the Seedance 2.0 video generation model on ByteDance's Jimeng platform. Use this skill when the user mentions Jimeng, Seedance, Seedance 2.0, AI video generation, AI short films, AI commercials, or needs to write prompts for a video generation model. Covers prompt templates and best practices for all scenarios: text-to-video, image-to-video, multimodal reference, one-shot, product commercials, video editing and more.
Use when starting work on a new or unfamiliar project, when encountering unexpected patterns, when user corrects your assumptions, or when explicitly invoked via /learn - auto-discovers and remembers project context through structured codebase analysis
Measure AI Search share of voice for a target domain versus competitors across ChatGPT, Perplexity, Gemini, Google AI Overview, and AI Mode. Pulls the AIO leaderboard, then samples prompts where each domain appears as a source or brand mention, and analyses topic clusters each brand owns. Use when the user asks for AI Search share of voice, LLM visibility tracking, AEO/GEO analysis, AI Overview competitive analysis, or wants to know which brands LLMs cite in their category.
Audit and optimize content for SEO, GEO (generative engine optimization), and AEO (answer engine optimization). Use when user asks to "audit SEO", "check search visibility", "optimize for AI search", "generate schema markup", "validate metadata", "extract keywords", "optimize for Perplexity/ChatGPT/Gemini", "check Open Graph tags", "submit to IndexNow", or mentions SEO, GEO, AEO, or search optimization. Do NOT use for creating new content from scratch or image optimization.
Local SEO audit for brick-and-mortar, service-area, and multi-location businesses. Covers Google Business Profile signals on the website, NAP consistency across page and schema, local-pack rank tracking, citation samples on Tier-1 directories, and reviews on Google / Yelp / Trustpilot. Distinct from `seo-page` (URL-level keywords, no local layer) and from `seo-schema` (which generates LocalBusiness markup — this skill defers to it). Use when the user asks "local SEO", "GBP", "Google Business Profile", "NAP", "local pack", "citations", "near me", "service area", or "multi-location SEO".
Use when the user needs technical SEO audits, meta tag optimization, structured data markup, Core Web Vitals improvement, or search engine visibility enhancement. Trigger conditions: site audit request, meta tag review, Schema.org implementation, page speed optimization, indexability issues, sitemap or robots.txt configuration, hreflang setup, Open Graph or Twitter Card tags, rich snippet eligibility.
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.