Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Debug Meta VR and Horizon OS VR, MR, and Android applications using the metavr CLI—view logs, capture screenshots, and diagnose common issues. Use when troubleshooting crashes, errors, or unexpected behavior on Meta VR devices. Build paths: All; use hz-quest-verify-first if the path is unclear.
Temu US e-commerce promotions API. Routes related bg/temu endpoints for Partner US Promotion through the LinkFox gateway, including campaign creation, enrollment, queries, coupons, and flash sales; endpoints will be integrated one by one according to the Partner documentation. Trigger when users mention Temu US promotions, promotion campaigns, coupons, flash sales, campaign enrollment, promotion campaign, or product-inventory promotions. Use linkfox-temu-manage-product-us for product management, linkfox-temu-price-us for pricing, and linkfox-temu-order-us for orders.
Temu EU e-commerce returns and refunds API. Routes related bg/temu endpoints for Partner EU Returns & Refunds through the LinkFox gateway, including return requests, refunds, and after-sales case queries and handling; endpoints will be integrated one by one according to the Partner documentation. Trigger when users mention Temu EU returns, refunds, after-sales returns, return, refund, aftersales return, parentAfterSalesSn, return records, refund records, or order-shipping after-sales. Use linkfox-temu-cancel-order-eu for order cancellations and linkfox-temu-order-eu for orders.
Temu US e-commerce returns and refunds API. Routes related bg/temu endpoints for Partner US Returns & Refunds through the LinkFox gateway, including return requests, refunds, and after-sales case queries and handling; endpoints will be integrated one by one according to the Partner documentation. Trigger when users mention Temu US returns, refunds, after-sales returns, return, refund, aftersales return, parentAfterSalesSn, return records, refund records, or order-shipping after-sales. For buyer/seller order cancellations, use linkfox-temu-cancel-order-us / linkfox-temu-cancel-order-us; for orders, use linkfox-temu-order-us.
Temu EU e-commerce tax API. Routes seven Partner EU temu.pay.tax.* endpoints through the LinkFox gateway: export reports, Galerie signatures, invoice queries/downloads, and merchant report downloads/invoice uploads. Trigger when users mention Temu EU Tax, temu.pay.tax.invoice, VAT, invoice upload, export report, Galerie signature, or site=eu tax. Use linkfox-temu-manage-product-eu for product management.
End-to-end guidance for solving mathematical modeling competitions. Covers all problem types (A–F) in the national contest (CUMCM) and MCM/ICM, with 12 analyses of problem fundamentals, a decision matrix for 95+ scenarios, 5 algorithm Cookbooks, 11 complete example Playbooks, and 22 Python + 7 MATLAB runnable code templates. Pairs with math-modeling-paper for “problem solving → writing.” Use this skill when users mention modeling approaches, choosing a model, how to model, contest problem solving, pasting problem text, MCM/national contest problem analysis, CVaR/NSGA-II/Monte Carlo/time series/ANOVA/grey relational analysis, network flow/graph theory/ecological modeling, model naming, Memo/Letter/Our Work flowcharts.
Today's calls and today's inbound. Three modes - score an inbound lead against your ICP (single or a whole day's batch, ranked), build a one-screen pre-call brief (company + person + 3 talking points, one sharp opener, 2 discovery questions, the likely objection), and build a call plan (discovery question plan mapped to a qualification framework, or a demo flow built only from pains the prospect actually stated). Runs on Crustdata company, people, job, news, and post data. Use for "prep my 2pm", "prep my call with <company>", "score this lead", "is this inbound worth my time", "triage today's inbound", "build me a discovery plan".
Unattended queue worker for PRs a human labeled `automerge`. Within a time window (default 2h), works up to the configured number of PRs concurrently to get three signals, each recorded as a label — code review, QA, CI. A missing signal goes to om-auto-review-pr, om-auto-qa-pr or om-auto-fix-pr in orchestrated mode. Never waits on slow CI. Defaults to guarded squash-merge; config/CLI can select prepare-only and independent native review.
Transform podcast transcripts into comprehensive content marketing suites including blog posts, social media content, newsletters, SEO-optimized articles, and timestamps. Use when user provides podcast transcripts or wants to repurpose podcast content.
Enforce Tailwind container queries instead of viewport breakpoints for responsive components. Use when writing or reviewing responsive Tailwind code, when a component must adapt to its available space (cards, sidebars, lists, panels, or anything reused in different layouts), or when migrating sm:/md:/lg: classes to @container variants.
Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy check, pre-launch check, verify the deploy, test this page, does the page render, broken link, 404, image not loading. Also triggers proactively after a deploy or a new page launch where verification matters. Covers accessibility, performance, and SEO at the surface-signal level only: deep audits belong to `accessibility-audit`, `performance-optimization`, and `seo-technical`, and code-level debugging to `code-review-web`.
Use this skill when the user wants to “create a skill,” “add a skill to a plugin,” “write a new skill,” “improve a skill description,” or “organize skill content,” or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Use when the user is calling or debugging Spree 6's REST API v3 — the Store API (storefronts, mobile apps, customers), the Admin API (integrations, back-office tools), or the Seller API (marketplace sellers). Covers auth (publishable/secret keys, JWT audiences), scopes and permissions, prefixed IDs, the cart → order split, checkout `requirements[]`, order statuses, the `{data, meta}` envelope, expand/fields, Ransack filters, errors, idempotency, localization headers, and rate limits. Common phrasings include "Spree API", "Store API", "Admin API", "publishable key", "secret key", "X-Spree-Api-Key", "X-Spree-Token", "API scopes", "403 required_scope", "cart_ vs or_", "complete cart", "cart 404 after checkout", "prefixed IDs", "expand", "Idempotency-Key", "429 rate limit", "v3 endpoint", "Admin API OpenAPI spec". For adding or documenting (OpenAPI) a new endpoint, use spree-resource; for AI agents driving the store over MCP, use spree-mcp; for roles and permissions internals, use spree-auth-permissions.
Use when investigating or improving Spree 6 performance — slow cart writes, slow checkout, slow Store API product listings, N+1 queries in custom endpoints or serializers, search latency, Meilisearch indexing floods, image processing backlogs, Solid Queue/Sidekiq queue tuning, HTTP/CDN caching of the Store API, dashboard data-fetching, or tracing with OpenTelemetry. Common phrasings include "slow cart", "add to cart is slow", "tax provider called too often", "N+1 in Spree", "slow product listing", "search slow", "Meilisearch reindex", "import is starving jobs", "jobs backlog", "queue tuning", "Spree cache", "CDN caching API", "trace a checkout", "find the slow workflow step".
Optimizes SQL queries, designs database schemas, and troubleshoots performance issues. Use when a user asks why their query is slow, needs help writing complex joins or aggregations, mentions database performance issues, or wants to design or migrate a schema. Invoke for complex queries, window functions, CTEs, indexing strategies, query plan analysis, covering index creation, recursive queries, EXPLAIN/ANALYZE interpretation, before/after query benchmarking, or migrating queries between database dialects (PostgreSQL, MySQL, SQL Server, Oracle).
Implement the Syncfusion Angular File Manager component for file browsing, management, and operations. Use this skill whenever the user needs to create a file manager interface, handle file operations like upload/download/delete, manage folders, or customize file browsing experiences in Angular applications.
Use for WordPress Playground workflows: fast disposable WP instances in the browser or locally via @wp-playground/cli (server, run-blueprint, build-snapshot), auto-mounting plugins/themes, switching WP/PHP versions, blueprints, and debugging (Xdebug).
Use when the user wants to simplify, clean up, refactor, tidy, or refine code—their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on: “simplify”, “simplify this”, “simplify my code/changes”, “clean up”, “clean this up”, “clean up my changes”, “refactor this”, “make this cleaner”, “tidy this up”, “reduce complexity”, “flatten this”, “remove dead code”, “make it more readable”, “polish before commit”, or “absolute simplify”. Acts on your working diff; for repo-wide dead code use absolute-prune; for lint/type debt use absolute-debt.
Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries; creates, lists, updates, or deletes an AHM data alert on an agent metric (escalation rate, deflection, etc.); asks why an alert is not firing or wants to check whether alerts have fired (notification counts, or the per-alert Incidents view). DO NOT TRIGGER when: user creates, modifies, or debugs .agent files during development (use agentforce-generate); writes or runs test specs (use agentforce-test); uses sf agent preview for local development iteration; deploys or publishes agents.
Entry point and governing principle of the Qiushi methodology. Load once at the start of each new top-level session to constrain all judgments with “seek truth from facts,” and route tasks to the corresponding methodology skill only when clearly applicable. Sub-agents delegated a single, specific task should skip it. English: Entry point and governing principle of the Qiushi methodology. Load once at the start of a top-level session to enforce "seek truth from facts" and route to a downstream skill only when it clearly helps. Delegated sub-agents on narrow tasks should skip it.
Creates or edits a Power Apps Canvas App through the Canvas Authoring MCP coauthoring session. Handles staged experience design, direct and partitioned targeted edits, planned multi-screen changes, responsive layout, and compile-error convergence. Trigger on requests to create, build, generate, modify, update, change, fix, or edit a Canvas App or .pa.yaml files.
Provides comprehensive CLAUDE.md file management capabilities including auditing, quality assessment, and targeted improvements. Use when user asks to check, audit, update, improve, fix, maintain, or validate CLAUDE.md files. Also triggers for "project memory optimization", "CLAUDE.md quality check", "documentation review", or when CLAUDE.md needs to be created from scratch. This skill scans all CLAUDE.md files, evaluates quality against standardized criteria, outputs detailed quality reports with scores and recommendations, then makes targeted updates with user approval.
Pixel-faithful clone of any web UI into the user's existing stack, using whatever sources are available — a screenshot alone, a live URL, raw HTML/CSS, or any combination. Use this skill whenever the user wants to recreate, match, replicate, or "clone" a design from a screenshot, image, URL, Figma export, or HTML dump. Trigger on phrases like "clone this", "match this design", "build this from screenshot", "recreate this page", "make it look like this", "rebuild this UI", "copy this layout", or any time the user provides a visual reference and asks for a faithful implementation. Do not undertrigger — even if the user just drops a screenshot without explicit phrasing, this skill applies.
Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead or complex code, or handling explicit Codebase Memory requests. Otherwise skip tasks confined to a supplied known file, tiny one-file check, exact literal, configuration value, error string, or non-code text.
Scaffold a new Adobe Commerce app using the aio-commerce-sdk. Creates the base project structure and app.commerce.config file with metadata. Use when the user wants to create a new Commerce app from scratch or initialize a bare Commerce app project. After scaffolding, chains to appbuilder-project-init for Developer Console setup (project, workspace, API subscriptions) when the user wants to deploy. Does not configure extensibility domains — use commerce-app-eventing, commerce-app-webhooks, commerce-app-business-config, commerce-app-admin-ui, or commerce-app-storage for that
Creates step-by-step decomposition plans and migration roadmaps for breaking apart monolithic applications. Use when asking “what order should I extract services?”, “plan my migration,” “create a decomposition roadmap,” “prioritize what to split,” “monolith to microservices strategy,” or tracking decomposition progress. Do NOT use for domain analysis (use domain-analysis) or component sizing (use component-identification-sizing)
Plans and builds end-to-end Fabric data platforms on the Bronze, Silver, and Gold medallion pattern: ingestion to analytics, PySpark and Delta layers, pipeline orchestration, per-layer Spark tuning, Materialized Lake View versus notebook choices for Silver and Gold, and Direct Lake handoff. Use for layered architecture design, planning and recommendations. For questions over an existing Power BI report use fabriciq.
Turn product information, packaging and qualifications, target platform, audience, and visual references into actionable e-commerce visual plans, including conversion strategy, Campaign Style Lock, main images/detail pages/Listing/A+ Storyboard, in-image copy, design notes, image-generation Prompt, and evidence and compliance review. Suitable for Taobao, Tmall, JD.com, Pinduoduo, Douyin Shop, Xiaohongshu, Channels/WeChat Shop, as well as Amazon, Shopify, TikTok Shop, Temu, Shopee, and Lazada. Use when users need product images, detail pages, in-image copy, design briefs for designers, or localization for cross-border products. Not for short-video/livestream scripts only, ad placement or store operation optimization, or final legal conclusions requiring a lawyer (risk screening is possible); it does not automatically list or publish products. Do not fabricate qualifications, data, sales, reviews, certifications, or efficacy claims; verify official sources for current platform rules or high-risk compliance conclusions.
Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta read, beta readers, test readers, human review, reader review, to read something like a human, to be a first reader, whether a piece holds attention or will actually get read, for a quick read of whether a busy skimmer would even open a post, what readers will remember or take away tomorrow, where readers stop reading or bounce, or why a draft still feels off or hollow after anti-slop or humanizer edits. Final gate before publishing; reports where the reading broke; never rewrites.
Expert blueprint for survival games (Minecraft, Don't Starve, The Forest, Rust) covering needs systems, resource gathering, crafting recipes, base building, and progression balancing. Use when building open-world survival, crafting-focused, or resource management games. Keywords survival, needs system, crafting, inventory, hunger, resource gathering, base building.
Hunt HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE). Cause: front-end proxy and back-end server disagree on where one request ends and the next begins (Content-Length vs Transfer-Encoding header parsing inconsistency). CL.TE: front-end uses CL, back uses TE → smuggle by sending TE: chunked but with body that fits CL count. TE.CL: opposite. H2.CL: HTTP/2 downgrade, smuggle CL into HTTP/1.1 back-end. Detection tools: Burp HTTP Request Smuggler extension, smuggler.py, h2csmuggler. Confirm: time-delay technique (smuggled GET with 30s timeout) — if front-end returns slow on next victim request, smuggling works. Validate: cache poisoning chain (smuggle request that gets cached for victim), credential theft (smuggle X-Forwarded-For override that captures next user's cookies), bypass auth (smuggled internal-path request). Real paid examples from major CDN deployments. Use when hunting H1 paid programs running CDN+origin stacks, when targeting load balancer / WAF bypass.
Writes compelling Japanese marketing copy, including catchphrases (キャッチコピー), product descriptions, landing pages, and ad copy. Understands cultural nuances, emotional triggers, and transcreation principles. Use when creating marketing content for Japanese audiences.
Writes, debugs and refactors JavaScript code using modern ES2023+ features, async/await patterns, ESM module systems and Node.js APIs. Use when building vanilla JavaScript applications, implementing Promise-based async flows, optimising browser or Node.js performance, working with Web Workers or the Fetch API, or reviewing .js/.mjs/.cjs files for correctness and best practices.
JavaScript style and best practices based on Google's official JavaScript Style Guide. This skill should be used when writing, reviewing, or refactoring JavaScript code to ensure consistent style and prevent common bugs. Triggers on tasks involving JavaScript, ES6, modules, JSDoc, naming conventions, or code formatting.
Use when generating, integrating, reviewing, or debugging Make App record-list keyword search through Service filter.expression or advanced/conditional/table/header filtering with @qfei-design/make-app-filter. Triggered by 列表搜索, 关键词搜索, 筛选, 高级筛选, 条件筛选, 表格/表头/列头/按字段筛选, CEL/DNF, field-type operators, candidate values, and filter Preset save/echo. In search-only mode, use the package compiler without a filter panel or Preset lifecycle. In advanced-filter mode, use the package panel, permission-aware Entity Preset, and desktop/tablet CanvasTable header linkage; phone uses the mobile panel layout. Consume make-app-permission list access. When make-app-actions is present, a successfully applied filter must clear its selection and invalidate pending work; drafts and failures preserve selection. Does not own page layout, CanvasTable internals, Service route implementation, sorting, grouping, auth, runtime, DSL, Make CLI, or table cell editing.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
Use when the user asks to enhance, improve, refine, rewrite, strengthen, or validate a prompt, or says "make this prompt better". Returns a clearer, more specific, better structured version of the prompt without executing it, picking validation checks from the prompt's own context. Contexts include coding, research, writing, image or video generation, agentic tasks, data work, and system prompts. Flags ambiguity, contradictions, missing constraints, missing success criteria, format gaps, and leaked secrets. Do not use when the user wants the prompt's task performed.
Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4). Use whenever writing or editing Remotion code — scaffolding a video project, animating with interpolate/spring over useCurrentFrame(), sequencing scenes and transitions, captions/subtitles, audio, GIFs/Lottie/3D, charts, visual effects, dynamic duration via calculateMetadata, or rendering. Consult before reaching for a Remotion API, since its components and props evolve (e.g. @remotion/media).
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.