Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Test legacy code: assess first, then propose a plan. Use when a codebase or module has few or no tests and you need to change it safely—for example, adding tests to untested code, building a safety net before a refactor, or taking over code you didn’t write. Examine the stack, dependencies, and code untouched by tests; propose the steps this repo needs (make it testable, characterize it, get approval, run property tests that hunt for crashes at every entry point, measure, and refactor last); wait for approval once, then run every approved step without stopping.
Deconstructs retrieved legal provisions into constituent elements and applies subsumption element by element: civil claim basis review and three-tier criminal law review, outputting a subsumption table, conformity conclusions, and a list of evidentiary gaps. Element deconstruction must be based on the original text of the provision or the reasoning of a judgment; inventing elements or filling facts with speculation is prohibited.
Expert knowledge for real-time and baked lighting in games - from cinematography fundamentals to engine-specific optimization, covering GI, time-of-day, volumetrics, and platform-aware lighting pipelinesUse when "lighting, light design, baked lighting, realtime lighting, lightmap, lightmapping, light probe, reflection probe, global illumination, GI, ambient occlusion, shadow, shadow cascade, time of day, day night cycle, volumetric fog, volumetric lighting, god rays, HDR, tonemapping, bloom, exposure, emissive, area light, Lumen, Enlighten, ray tracing, RTGI, light baking, lighting, global-illumination, lightmapping, shadows, GI, light-probes, reflection-probes, HDR, tonemapping, volumetric, fog, time-of-day, baked, realtime, mixed-lighting, lumen, enlighten, radiosity, ray-tracing, RTGI" mentioned.
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
Systematic literature review workflow: scope, search (arXiv, Semantic Scholar, Google Scholar), screen, extract, synthesize, and identify gaps. Triggers on: "literature review", "survey the literature", "related work", "systematic review", "synthesize the research", "find papers about", "research gap analysis".
Extract invoice data from images or text descriptions and generate a categorized Excel expense report. Supports receipt photos, scanned invoices, and manual text input. Auto-classifies into: business entertainment (客户餐费), travel-transport (机票/火车票/打车), travel-accommodation (酒店), travel-meals, office supplies, communication, and other. Use when the user mentions "发票报销", "expense report", "报销单", "发票整理", "invoice", "报销汇总", "发票分类", "reimbursement", or has invoice images to process.
Detects market top probability using O'Neil Distribution Days, Minervini Leading Stock Deterioration, and Monty Defensive Sector Rotation. Generates a 0-100 composite score with risk zone classification. Use when user asks about market top risk, distribution days, defensive rotation, leadership breakdown, or whether to reduce equity exposure. Focuses on 2-8 week tactical timing signals for 10-20% corrections.
When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas', 'growth ideas', 'how to market', 'marketing strategies', 'marketing tactics', 'ways to promote', or 'ideas to grow.' This skill provides 140 proven marketing approaches organized by category.
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
S-parameters, insertion loss, fields, currents, mesh control, and solver selection for RF PCB performance validation. TRIGGER: user asks to compute S-parameters, analyze insertion/return loss, extract fields or currents, compare MoM vs FEM, or control mesh for any RF PCB component. Invoke BEFORE writing sparameters() or solver code — API is non-obvious. SKIP: designing or creating components (use the specific matlab-design-pcb-* skill), material/stackup setup only (use matlab-manage-pcb-material), optimization sweeps (use matlab-optimize-pcb-design), PDN/IR-drop analysis (use matlab-analyze-pcb-pdn).
Download videos and audio from 1500+ websites including YouTube, Bilibili, TikTok, Twitter/X, Instagram, Vimeo, and more using yt-dlp. Use when the user wants to download videos, save media from social platforms, download with specific resolution (720p/1080p/4K), get subtitles, or download entire playlists. Triggers on requests like 'download this video', 'save this YouTube video', 'download in 1080p', 'download with subtitles', 'download this playlist'.
Reason about SaMD (Software as a Medical Device) regulatory compliance for FDA, EU MDR, and global submissions. Use when the user asks about IEC 62304 safety classification, ISO 14971 risk management, 21 CFR 820/QMSR quality system requirements, Design History File structure, 510(k)/De Novo/PMA pathway selection, SOUP/OTS assessment, verification and validation planning, cybersecurity for medical devices, PCCP for AI/ML devices, design reviews, traceability matrices, or post-market surveillance. Triggers include "SaMD", "medical device software", "IEC 62304", "ISO 14971", "ISO 13485", "21 CFR 820", "QMSR", "510(k)", "De Novo", "PMA", "design history file", "DHF", "software safety classification", "SOUP list", "risk management", "hazard analysis", "design review", "V&V protocol", "FDA submission", "EU MDR", "clinical evaluation", "PCCP", "predetermined change control", "GMLP", "cybersecurity premarket", "Part 11", "design controls", "design inputs", "design outputs", "traceability matrix", "post-market surveillance", "CAPA", "Class II device", "Class III device", "regulatory pathway", "predicate device", "substantial equivalence".
Synthesize and render MIDI/MusicXML files to audio (WAV/MP3) and generate Strudel live-coding patterns for creative music manipulation. Uses analysis data (tempo, key, chords, dynamics) from audio-to-midi for intelligent ghost-note removal and accurate reproduction. Two workflows: (1) Convert MIDI/MusicXML to Strudel/TidalCycles code with note durations for interactive tweaking in the browser at strudel.cc, (2) Render MIDI/MusicXML to WAV/MP3 with FluidSynth or built-in synthesis, with controls for tempo, transposition, instrument override, and ghost-note cleaning. Trigger when the user wants to: play a MIDI file, render MIDI to audio, synthesize MIDI, convert MIDI to Strudel code, create live-coding patterns from MIDI, change instruments, transpose or tempo-shift, clean ghost notes, or any MIDI playback/synthesis task.
Reviews and migrates deprecated wildcard (*) values in Power Pages Web API fields site settings to least-privilege explicit Dataverse columns. Use whenever a user mentions Web API wildcard or select-all remediation, fields settings containing *, data-exposure review, wildcard deprecation readiness, or Web API failures after wildcard retirement. Applies to both non-SPA sites using HTML, CSS, JavaScript, Liquid, and downloaded YAML, and SPA sites using React, Vue, Angular, Astro, or TypeScript. The agent must inspect every source Web API call and consumer, report exact fixes for every wildcard, report every already-explicit configuration, apply approved edits, and verify no wildcard remains.
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video poster", "title card", or pairs Open Claude Design with HyperFrames for a kinetic export.
Use when adding animation to a React app with the Motion library (the framer-motion successor: npm package `motion`, import `motion/react`) — enter/exit animations, variants and stagger, AnimatePresence, layout and shared-element transitions, animated number tickers, gesture states — or when deciding whether a job needs Motion at all versus plain CSS/Tailwind transitions or AutoAnimate. Covers reduced-motion accessibility (MotionConfig, useReducedMotion, WCAG 2.3.3/2.2.2) as a first-class requirement, performance discipline (transform/opacity only), motion restraint for data-dense product UI, Radix/shadcn and router integration, and keeping tests stable (MotionGlobalConfig.skipAnimations). Keywords: motion, framer-motion, animation, AnimatePresence, layout animation, micro-interactions, reduced motion, page transitions, stagger, spring.
Design interfaces that offer multiple input methods so users can choose what works for their abilities and context. Use when designing any interactive system where users provide input — forms, search, editors, creative tools, communication interfaces. Triggers on: multi-modal, input methods, alternative input, how people interact, mouse alternative, touch alternative, input flexibility, switch access, eye tracking, head pointer.
Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically requests Python for an n8n Code node. Note — JavaScript is recommended for 95% of use cases — only use Python when the user explicitly prefers it or the task requires Python-specific standard library capabilities (regex, hashlib, statistics). EXCEPTION — for Python in the AI-agent-callable Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode), use the n8n-code-tool skill instead (input is _query, return must be a string).
Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, mapping data between nodes, or referencing webhook data in workflows. Use this skill whenever configuring node fields that reference data from previous nodes — expressions are how n8n passes data between nodes, and getting the syntax wrong is the most common source of workflow errors. Also use when asked whether a complex expression hurts performance.
Apply these opinionated Next.js conventions whenever writing or reviewing App Router code (14+): Server Components by default, where the 'use client' boundary belongs, the caching defaults that changed in Next 15, tag-based revalidation, treating Server Actions as public endpoints, the Metadata API, and next/image and next/font.
Smart novel generator v2.0, supporting resumable progress for long novels, intelligent context management, a three-layer compression mechanism, chapter jumping, intelligent import of settings, AI-assisted editing, and memory management. Use this skill when the user needs to write a long novel, manage a complex story structure, import settings from external resources, or needs AI assistance for continuous creative writing.
Nuwa (女娲): Input any name, auto-research → extract thinking frameworks → generate a runnable perspective skill. Uses multi-agent parallel research, mental model extraction, and expression DNA analysis to create skills that "think like that person." Trigger: "create a perspective skill for X", "distill X", "nuwa", "make a skill for X", "X's thinking framework"
Use when implementing event-driven automation, setting up CloudEvents rules, troubleshooting event delivery failures, or integrating with Functions/Streaming/Notifications. Covers event rule patterns, filter syntax, action types, dead letter queue configuration, and event-driven architecture anti-patterns.
For drafting or editing official documents of ROC government agencies (letters, official letters, announcements, memos, etc.), correctly applying paragraph structure, wording and formatting rules per the Handbook of Document Processing and the Reference Standards for Government Document Formats. Use this skill when the user wants to write a letter to a government agency, an internal memo, an announcement or a meeting notice, or asks about official document wording, forms of address, or expressions of expectation and purpose.
Integrate OnboardJS into React projects for building user onboarding flows. Use when: (1) Setting up OnboardJS in a React/Next.js project (2) Creating multi-step onboarding, wizards, or guided flows (3) Implementing conditional navigation, data persistence, or step validation (4) Working with OnboardingProvider, useOnboarding hook, or step components Triggers: "onboarding", "onboardjs", "wizard flow", "user onboarding", "guided tour", "multi-step form"
Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating the Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage), signal detection patterns, and iteration algorithms.
Generate penetration test reports in a standard format, including a project information table, a vulnerability findings list, vulnerability details (with an attribute table, description, reproduction steps, evidence screenshots, and remediation recommendations), and appendices (risk level definitions, CVSS explanations, and a glossary). Use this skill when the user asks to generate a penetration test report, security test report, or vulnerability report. Strictly follow the standard format in the project template directory.
XSS audit tool for PHP web source code. Identifies user input entering output contexts (HTML/attribute/JS/URL/template), analyzes escaping and protection strategies, and outputs exploitability grading, PoCs, and remediation suggestions (omission not allowed).
Turn vague requirements into a review-ready product requirements document (PRD). Use this skill when the user says "write a requirements doc", "draft a PRD for me", "how should I write requirements for this feature", "I have an idea I want to ship", "organize this requirement into a document", "a PRD for a requirements review", or when the user describes a feature without structure. Also applies when: the user uploads a raw requirement description / meeting notes / screenshot of a chat and asks for it to be organized into a PRD; the user says keywords such as "PRD", "product requirements", "requirements document", "feature spec"; the user asks to fill in, improve, or find gaps in an existing PRD. Not for: pure technical solution design (use architecture), pure UI mockup annotation (use design-handoff), project-management documents (use status-report).
Fox News headlines from Google Publisher RSS — pick a section (latest, world, politics, sports, ...) or default to latest. Trigger phrases: `fox news headlines`, `what's on fox news`, `fox politics headlines`, `fox sports rss`, `use foxnews`, `run foxnews`.
Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
Triage open PRs: which need attention first, and why. Read every open pull request in a repo, judge how much of a reviewer's attention each one needs (critical, high, medium, low) from what the change actually does, and order the queue most-attention-first — each judgement pointing at the line that drives it, each PR linked to a full reading tour. Renders one self-contained HTML queue plus JSON for agents. Use when the user asks which PR to review first, what needs attention in the PR queue, has too many open PRs, or mentions PR triage, review backlog, or review priority
Structural analysis through dynamically generated cognitive lenses. Generates the optimal analytical lens for the specific code/artifact, then executes it. Finds conservation laws, structural invariants, and concrete bugs that vanilla analysis misses. Use on any code file, system design, or text artifact.
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.