Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Design alternatives to gesture-based and motion-based interactions. Use when designing swipe actions, pinch-to-zoom, shake-to-undo, tilt controls, multi-finger gestures, or any interaction that requires specific physical movements. Triggers on: gesture, swipe, pinch, shake, tilt, multi-touch, two-finger, rotation gesture, device motion, accelerometer, gyroscope.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Analyze real projects and generate or revise secure, verifiable GitHub Actions workflows; use when the user asks to create CI, test matrices, builds, releases, deployments, caching, Secrets, OIDC, PR automation, or to troubleshoot workflow configuration
Generates a deeply contextual, progressive-disclosure briefing for any GitHub repository. It builds a mental model of the code before analyzing issues and PRs to provide actionable insights. Use when asked for a "GitHub report," "repo status," "daily briefing," or to "catch up on a codebase."
Generate professional GitHub project README.md with standard structure including project intro, features, installation, usage, documentation, FAQ, contact info, donation, statistics, roadmap, and license. Auto-detects project type and tech stack.
Upload screenshots and images to GitHub, returning markdown-ready URLs for PRs, issues, and comments. Use when needing to attach images to GitHub PRs/issues, upload screenshots, embed visuals in markdown, or when a workflow produces images that should be shared on GitHub. Trigger words - upload image, attach screenshot, add image to PR, embed screenshot, visual diff, before/after screenshot.
Full-stack U.S. and Hong Kong stock data toolkit (official sources prioritized) — 17-layer architecture, 50+ endpoints, 18 data sources, all with no authentication. On top of the original eight layers—quotes/K-lines/technical indicators (MA/MACD/RSI/KDJ/Bollinger Bands)/fundamentals/flow/options/SEC filings/tools—it adds: the official CBOE options chain (full Greeks, IV, 0DTE flow, unusual-activity detection), FINRA daily short-sale volume across the market, SEC EDGAR filing event stream (Form 4 insiders/8-K/13F institutional holdings), EDGAR cross-sectional screening across the market, Treasury yield curve/CFTC COT/earnings calendar. V2.1 adds a global rates and FX layer (BIS policy rates for 38 central banks, ECB FX/rates/euro-area yield curves, New York Fed SOFR/EFFR, Federal Reserve H.10 exchange rates/H.6 money stock, U.S. Treasury auctions/federal debt); fixes Yahoo K-line full historical daily data and time zones, and supports market codes for Japan/Taiwan/South Korea/India/Europe and more. V2.2 adds historical CBOE volatility indices and VIX term structure, FINRA short interest (twice monthly), SEC Form 4 insider transaction details and 13F institutional holdings parsing, Taiwan official stock-market OpenAPI (TWSE + TPEx, commercial use permitted), and U.S. Energy Information Administration EIA crude oil/natural gas prices and inventories. V2.3 adds a U.S. macro layer (U.S. Bureau of Labor Statistics BLS public API, no registration: CPI/core CPI/nonfarm payrolls/unemployment/hourly earnings/PPI/JOLTS job openings/import prices/ECI/productivity, with official release schedules and revision rules; U.S. Department of Labor weekly initial/continuing unemployment claims). Each data source is labeled with its compliance level and original terms. All invocation code is embedded; self-contained with no external file dependencies. Suitable for U.S. and Hong Kong stock analysis, market-wide screening, earnings analysis, options and 0DTE strategies, short-sale data tracking, insider transactions and 13F holdings, SEC filing searches, flow and institutional holdings analysis, tracking global rates, FX and central-bank policies, VIX volatility, Taiwan stocks, crude oil and natural gas, and U.S. macro data such as CPI, nonfarm payrolls and unemployment claims, along with release schedules.
Kiểm tra chính tả, dấu câu, khoảng trắng, cấu trúc câu, tham chiếu đại từ và kết hợp từ trong văn bản tiếng Việt. Dùng khi người dùng yêu cầu soát lỗi hoặc proofread; không dùng để áp một phong cách, đổi nội dung, sửa code/URL/identifier, hay coi lựa chọn register và phương ngữ là lỗi ngữ pháp.
Designs complete GraphRAG systems integrating graph databases, vector stores, orchestration frameworks, and LLM reasoning. Guides through pattern selection, technology stack decisions, integration pipeline design, and domain-specific customizations. Use when designing GraphRAG systems, choosing technology stacks for graph-augmented retrieval, combining Neo4j with LLM, using LangChain/LlamaIndex knowledge graphs, applying community detection for RAG, building hybrid symbol-vector pipelines, or deploying production or domain-specific GraphRAG.
Generate a comprehensive portfolio action report with earnings dates and risk assessment. Use when user asks for portfolio review, action items, earnings risk, or position management across IB accounts. Requires TWS or IB Gateway running locally.
React component structure and hooks antipatterns — a seven-section file layout, logic ordering, and the useEffect/useState failure modes behind infinite loops and stale state. Use this skill whenever the user wants to "create a React component", "structure this component", "refactor this component", "extract a custom hook", "fix an infinite render loop", or "my useEffect isn't working" — even if they don't mention React by name, when the file is .tsx/.jsx or the code calls hooks. Do NOT use this skill for general code review of non-React code (see code-review), visual or layout design (see frontend-design), or plain JavaScript with no components or hooks.
Create a distinctive personal website through a phased reference-image-driven process: locking content and style, locking reference images, confirming asset breakdown, reviewing asset generation, then high-fidelity replication and QA. Suitable for building, redesigning, or replicating personal websites, portfolios, creator sites, founder sites, or personal IP sites using Codex, Image 2, reference images, generated assets, or a high-quality image-to-code workflow.
Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
Email triage system that handles both one-time setup and recurring triage in a single skill. Auto-detects state: if no knowledge base exists at ${WORKSPACE}/Email/, runs an 8-section onboarding interview (grill-me discipline, one question at a time) to build a 7-file personalized KB, then offers to run triage immediately. If the KB already exists, skips setup and goes straight to triage — searches recent emails, classifies them via the user's taxonomy, researches new senders, generates TAKE IT/WORTH/PASS/FLAG recommendations, drafts replies (NEVER sends), delivers a report, and updates the KB. Use with 'update' argument to refresh preferences. Setup triggers: 'set up my inbox', 'configure inbox triage', 'set up my email system', 'configure email triage', 'build my email knowledge base', 'initialize email management'. Triage triggers: 'triage my inbox', 'inbox triage', 'check my email', 'run email triage', 'process my inbox', 'what's new in my email', 'handle my email', 'email triage'.
Use when adopting incu-way in a repository for the first time — to bootstrap the project so the development, bug, and security flows have what they need. Detects greenfield (new, empty repo) vs brownfield (existing application — the common case), scaffolds CLAUDE.md, the docs/ tree, the branch model, and .ways/, and drives the architectural/functional documentation of the existing code. Also use to re-initialize or refresh a project that already uses incu-way.
Use to turn a raw need, idea, or client request into development-ready tickets before any development flow starts — validate feasibility against the actual codebase(s), map affected repos and cross-repo contracts, and close open questions up front. Trigger for "refine this ticket", "write the requirements for X", "is X feasible", "prepare tickets for this need", or when a request spans multiple repositories. Do not trigger for tickets that are already well-specified, plain defect reports (use incu-way-bugs), or when the user asks to start building immediately.
Use to validate code against common security rulesets and standards (OWASP Top 10, OWASP ASVS, OWASP API Security Top 10, CWE Top 25) by reviewing the code, a module, or the current branch's changes control-by-control. Produces a traceable compliance report marking each control pass/fail/N-A with evidence, plus prioritized remediation pointers. Invoke standalone to audit against a standard, or from another flow (incu-way-development at validation, incu-way-bugs) to check new code before merge. This is a standards-driven manual review — it complements snyk-remediation (automated SAST/SCA scanning), it does not replace it.
Generate cross-platform install scripts for any software or library — a standalone install.sh runnable via a curl/wget one-liner with OS, arch, and package manager detection. Don't use for Dockerfiles, CI/CD pipelines, or one-off shell scripts.
Craft-first interface design for dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces, and interactive products. Use when designing, building, reviewing, auditing, or refining product UI where visual craft, layout hierarchy, tokens, states, visual direction, or design-system consistency matter. Not for marketing pages, landing pages, campaigns, or brand-only work.
Build and maintain one coherent company story across employees, investors, customers, candidates, and partners. Use when preparing all-hands meetings, investor updates, board presentations, recruiting narratives, or crisis communications.
WeChat Official Account investment blogger distiller. From Official Account article data, it automatically extracts a seven-dimension DNA profile — trading system, market judgment, expression style, content depth, engagement features, hot-topic map, and persona genes — and outputs a structured style profile. Trigger words: distill investment blogger, distill influencer, distill Official Account influencer, analyze investment blogger style, extract trading system, style profile, investment blogger distillation.
Turn a screenshot into a Jam (a shareable jam.dev screenshot with context attached) that points at the problem, with boxes, arrows, notes, redactions and blurs drawn by `jam create jam`. Use when the user asks to file or share an annotated screenshot as a Jam. Local annotation or redaction requests alone do not call for this skill.
Record work you can see on screen with `jam record` and publish it as a Jam link (a shareable jam.dev recording with the console and network attached). Use when the user asks for a recorded Jam, a shareable demo, or video proof of work in a browser or desktop app. A request to verify a change or give sign-off alone does not call for recording or uploading.
Generate and deploy a pro-code AI agent using LangGraph and SAP GenAI Hub, deploy it to SAP BTP Cloud Foundry, create a Joule capability with A2A (Agent-to-Agent) action, and deploy it to Joule. Supports TypeScript (Express or CAP) and Python. Use this skill whenever the user mentions: building a custom agent for Joule, deploying an AI agent to BTP Cloud Foundry, A2A protocol integration with Joule, pro-code agent extensibility, LangGraph agent on SAP BTP, connecting an external agent to Joule, "bring your own agent" for Joule, creating a Joule capability with A2A action, CAP agent, MTA deployment, or any combination of LangGraph/A2A/Joule/BTP/Cloud Foundry/CAP in an agent development context. Also trigger when the user wants to scaffold, modify, or redeploy an existing A2A agent project.
Load this skill for any project with interactive UI, such as buttons, links, forms, modals, dropdowns, menus, tabs, sliders, toolbars, carousels, or custom widgets, in React or vanilla JavaScript. Never ship an interactive element that cannot be fully operated by keyboard alone. Always ensure a visible focus indicator, logical tab order, correct widget key behavior, and no keyboard traps. Targets WCAG 2.2 Level AA.
Script-First design system workflow. Uses a deterministic auditor script to detect frameworks, inventory components, and detect design drift (hardcoded hex, arbitrary Tailwind). Provides a clear report for the agent to judge and implement a Kitchen Sink page.
Laozi's thinking framework and philosophy of living. Based on deep research into 20+ sources — the 81 chapters of the Tao Te Ching, the Shiji's "Biographies of Laozi and Han Fei," Heshanggong's commentary, Wang Bi's commentary, Chen Guying's "Laozi: Modern Annotation and Translation," and Liu Xiaogan's "Laozi Ancient and Modern" — it distills 5 core thought models, 7 life heuristics and a complete expression DNA. Purpose: to serve as a thinking advisor, analyzing system design, leadership, life trade-offs, counterintuitive decisions and similar questions from Laozi's perspective. Use when the user mentions "from Laozi's perspective," "what would Laozi think," "Laozi mode," or "laozi perspective." Also applies to: systems thinking, reverse thinking, leadership cultivation, subtraction strategy, flexible response, and going with the flow. It can also be triggered even when the user merely says "governing by non-action," "the Dao follows nature," "the highest good is like water," "retreat to advance," or "the great Dao is simple." Do not trigger it when the user is only asking general questions such as "is this decision sound" or "help me think this through" — activate it only when system thinking, counterintuitive wisdom, the weak overcoming the strong, governing by non-action and other core Laozi methodologies are involved.
Use when building or maintaining Laravel applications — Eloquent ORM, Blade, Livewire, queues, Pest testing, middleware, service providers, migrations. Trigger conditions: Laravel project setup, Eloquent model design, Blade or Livewire component creation, queue/job implementation, Pest test writing, middleware configuration, migration authoring, route definition, Form Request validation, policy authorization, Sanctum/Passport authentication, Horizon queue monitoring.
Hilarious LinkedIn profile roasting skill that delivers savage but friendly comedy burns based on someone's profile, activities, skills, experience, or lack thereof. Use when users ask to roast a LinkedIn profile, make fun of someone's professional presence, or want a humorous critique of LinkedIn content. Triggers on requests like "roast this LinkedIn", "make fun of this profile", "roast me", "give me a LinkedIn roast", "flame this profile", or any request for comedic mockery of a professional profile.
Audit an app's async surfaces and implement the right loading, progress, and empty states — skeleton screens, spinners, progress bars, first-use/no-results/error-empty views — chosen by expected latency and layout knowledge. Use when the user says 'add loading states', 'the page just goes blank while fetching', 'add a skeleton screen', 'users think it's frozen', 'spinner or skeleton?', 'design the empty state', 'zero state', or when reviewing an app whose fetches show nothing. Produces a loading/empty-state audit of every async surface plus the implemented components.
Generate an HTML translation helper page for Lokalise. Use when the user provides English text (singular/plural) and wants translations across all 23 supported languages, rendered as an interactive HTML page with copy buttons. Triggers on phrases like "translate for Lokalise", "generate translations", "translation table", or when the user provides English strings and mentions languages/i18n/localization.
Convert Markdown documents to professionally styled DOCX (Word) files with python-docx. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, cover pages, TOC field, watermarks, and page numbers. Supports multiple color themes matching any2pdf (Warm Academic, Nord, GitHub Light, etc.) and is battle-tested for Chinese technical reports. Use this skill whenever the user wants to turn a .md file into a styled Word document, generate an editable report from markdown, or create a DOCX from markdown content — especially if CJK characters, code blocks, or tables are involved. Also trigger when the user mentions "markdown to docx", "md2docx", "any2docx", "md转word", "md转docx", "生成word", or asks for an "editable document" from markdown source.
Use when adding or fixing Luau type annotations - luau-lsp/luau-analyze errors, --!strict compliance, "Type X could not be converted into Y", generics, union types, type narrowing/refinements, casts (::), typed metatables and OOP, .d.luau definitions, or .luaurc setup. Triggers include "type error", "strict mode", "luau-lsp", "type mismatch", "export type".
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.