Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Emulated AWS cloud services (S3, SQS, Cognito, IAM, STS) for local development and testing. Use when the user needs to interact with AWS API endpoints locally, test S3 bucket and object operations, emulate SQS queues and messages, test Cognito sign-up, sign-in, JWTs, or Identity Pools, manage IAM users/roles/access keys, test STS assume role, or work without hitting real AWS APIs. Triggers include "AWS emulator", "emulate AWS", "mock S3", "local SQS", "test IAM", "emulate S3", "AWS locally", "STS assume role", or any task requiring local AWS service emulation.
Validates animation durations, enforces typography scale, checks component accessibility, and prevents layout anti-patterns in Tailwind CSS projects. Use when building UI components, reviewing CSS utilities, styling React views, or enforcing design consistency.
Expert in browser automation using Chrome DevTools Protocol (CDP) and WebDriver. Specializes in secure web automation, testing, and scraping with proper credential handling, domain restrictions, and audit logging. High-risk skill due to web access and data handling.
Busabase is the open-source database and workspace for AI agents. Use this skill to read and write a Busabase workspace — records, docs, files, skills and apps — through the CLI, API or MCP. Also use it whenever the user's message contains a Busabase URL (busabase.com, *.busabase.com, or a local Busabase on localhost:15419): resolve it to its space and object and read that through the CLI or API, never by opening the page. Writes are change requests: they land at once with write access and wait for review otherwise.
Speeds up CI and the merge path: finds where changes wait between push and deploy, then fixes the critical path, check placement, merge queue or post-merge checks with auto-revert, flaky tests, and deploy rate. Use when "CI is slow", "speed up CI", "do we need a merge queue", "main keeps going red", "flaky tests block merges", agents open PRs faster than they merge, or building a self-healing merge loop.
Designing CLIs that AI agents will invoke — non-interactive flags, layered --help with examples, stdin/pipeline composition, actionable errors, idempotency, dry-run, destructive-action safety, and predictable command structure. Use when designing, building, or reviewing a command-line tool that AI agents or automation will invoke. Trigger even if the user doesn't explicitly say "agent-friendly" — apply whenever they are writing `--help` text, adding a new subcommand, designing error messages, or reviewing a CLI's UX.
This skill should be used when the user asks to “perform cloud penetration testing,” “assess Azure or AWS or GCP security,” “enumerate cloud resources,” “exploit cloud misconfigurations,” “test O365 security,” “extract secrets from cloud environments,” or “audit cloud infrastructure.” It provides comprehensive techniques for security assessment across major cloud platforms.
Convex backend development guidelines. Use when writing Convex functions, schemas, queries, mutations, actions, or any backend code in a Convex project. Triggers on tasks involving Convex database operations, real-time subscriptions, file storage, or serverless functions.
Runs Didit's standalone passive liveness check on a single selfie image (POST /v3/passive-liveness/). Use when checking that a person is physically present, detecting spoofing or presentation attacks (printed photos, screen replays, masks, deepfakes), adding anti-spoofing to a selfie step, or screening a selfie against the face blocklist and earlier approved faces. Returns a 0-100 liveness score, an Approved/Declined status against a configurable decline threshold, face quality and luminance, and blocklist and duplicate-face warnings.
Migrate a GenAI/LLM app off Traceloop/OpenLLMetry onto OpenInference with its OTel gen_ai.* semconv option enabled (`enable_genai_semconv` / `OPENINFERENCE_ENABLE_GENAI_SEMCONV`). Covers detecting the existing Traceloop setup, swapping the instrumentor per SDK, and the ingestion-shape question that decides what's fixable afterward — an app-owned OTel trace exporter vs. instrumentation-only with OneAgent picking up the spans. Flags that the semconv option is additive, not a replacement — legacy llm.*/openinference.* attributes keep emitting alongside gen_ai.* — and covers the resulting cardinality trade-off and removal options (Collector transform vs. OpenPipeline), checking which is actually available first. Trigger: "migrate off Traceloop", "migrate off OpenLLMetry", "move to OpenInference", "enable OpenInference GenAI semconv". Do NOT use for a first instrumentation with no existing Traceloop setup, or an OpenInference app that never enables semconv (both dt-setup-genai).
Read and extract content from EPUB ebook files. Use this skill when the user wants to read an EPUB file, extract text from an ebook, view EPUB metadata (title, author), list chapters or table of contents, search within EPUB content, or analyze ebook content.
Capture each agent failure, bucket and count it deterministically, and when a failure class recurs past a threshold, scaffold a candidate rule/skill stub into the propose->gate flow so the same mistake becomes a guardrail instead of repeating. Hamel's create->label->fix->repeat flywheel, self-evolving. Trigger when the user says "log this failure", "record the mistake", "why does this keep happening", "turn failures into rules", "failure taxonomy", "what keeps breaking", or invokes /failure-flywheel. Also run --report periodically to see the top recurring failure classes.
AI tax advisor for French individuals' personal taxation: optimization and filing of income tax, IFI, capital income, rental income, employee equity, crypto-assets, and PER. Covers income tax calculation (tax brackets, family quotient, tax discount, withholding at source, CEHR, exceptional income), the 2042 return and appendices, capital income (PFU vs. tax scale, PEA, life insurance, dividends, capital gains), rental income (micro/actual regime, deficit, LMNP, SCI under income tax), startup equity (RSU, BSPCE, stock options, PEE/PERCO), crypto taxation (PAMC, 2086), IFI, deductions (PER, alimony), and artist-author income (BNC, adjustments). Triggers: income tax, 2042, family quotient, tax discount, PFU, flat tax, rental deficit, PER ceiling, tax break, income tax simulation, TMI, foreign account, 3916, 3916-bis, 8UU, artist-author, copyright, micro-BNC, 2042 C PRO, 5HQ. Out of scope: inheritance/gifts (notary), corporate tax/SASU/dividend-salary arbitration/SCI under corporate tax (accountant).
Opt-in fixer (the /claude-seo-ai:fix command). Applies the safe, deterministic SEO/AI-search fixes from a persisted audit to the user's site — meta viewport/charset/lang, JSON-LD, robots.txt AI directives, hreflang, sitemaps, OG/Twitter cards, image dimensions, canonical, AI discovery files — through the adapter that matches the platform (local files, Shopify theme/Admin, WordPress REST/WP-CLI, page APIs, or step-by-step instructions). Dry-run preview by default; writes only after explicit per-change confirmation. Runs only when the user invokes it — never auto-triggered
AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the user asks to build, design, create, or improve any frontend interface — websites, landing pages, dashboards, components, apps, emails, forms, modals, or any UI element. Also triggers on "build me a UI", "design a page", "create a component", "improve this layout", "make this look better", "frontend", "interface", "redesign", or when the user provides mockups, screenshots, or design references. Do NOT use for backend logic, API design, database schemas, or non-visual code tasks.
Design, build, review, and polish production frontend and mobile interfaces with distinctive visual direction, searchable UX and design-system guidance, responsive and accessibility rules, stack-specific recommendations, and concise product copy. Use whenever creating or changing pages, components, layouts, styling, interaction, navigation, motion, charts, visual assets, UI copy, or frontend usability in web, Flutter, React Native, SwiftUI, desktop, or similar interfaces.
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini on Google Ads strategy, SEO best practices, or implementation questions). Use when the user says "gemini review", "ask gemini", "gemini challenge", "second opinion from gemini", "consult gemini", "stress test with gemini", "what would gemini say", "cross-model review", or "get another opinion". Voice aliases: "gem", "gemini check". Especially useful for Google Ads changes, SEO metadata updates, campaign structure decisions, keyword strategies, and bid/budget changes — Gemini has native Google ecosystem knowledge that complements Claude's analysis.
Analyze and score only a page's AI-search visibility (GEO/AEO) — answer extractability, fact density, AI-crawler access and Google AI-feature snippet eligibility, entity linking, AI discovery files, and agent-readiness — and report an AI Visibility score with a citability breakdown, plus optional unscored probes (web-search presence, Search Console generative-AI impressions). Read-only. Use for "will AI engines cite this?", GEO/AEO, or ChatGPT/Perplexity/Google AI Overviews/Gemini optimization.
Build and iterate on an Apollo Connectors subgraph for a GraphOS supergraph from a REST API, with or without an OpenAPI or Swagger spec, in a dedicated git workspace that records what the API offers, the user's operation and field selection, every design decision, and the evidence each verification layer produced. Use whenever the user wants to wrap a REST API as a GraphQL subgraph for their supergraph, add or remove operations or fields from an existing connector subgraph, refresh one against a new spec, or record live API traffic as test fixtures, even if they do not say "connector", "subgraph" or "Apollo"
Break down a company’s sources of growth and assess their profitability, cash generation, sustainability, and risk of slowing down to determine whether the growth is “high quality.” Suitable for screening high-growth stocks, reviewing growth theses, and distinguishing genuine momentum stocks from false positives.
Provides guidance for designing websites optimized for Japanese audiences, including cultural UX principles, information density patterns, bento layouts, trust signals, and localization best practices. Use when building e-commerce sites, landing pages, SaaS products, or any web application targeting Japanese users.
Image copyright infringement detection and risk analysis. Trigger this skill when the user mentions copyright detection, copyright verification, image infringement checks, image copyright risk, copyright similarity search, TRO risk analysis, rights holder lookup, copyright compliance verification, copyright detection, image infringement, copyright risk, TRO risk, copyright lookup, infringement analysis, or Ruiguan. Even if the user does not explicitly mention “copyright,” trigger this skill whenever their request involves checking whether an image may infringe a registered copyrighted work.
Retrieve translated patent specification (description) text from 智慧芽. Trigger this skill when the user requests a patent specification translation, the full patent text in another language, a translated full patent text, or wants to view the Chinese, English, or Japanese version of a patent specification; patent specification translation, patent description translation, PatSnap, or patent translation. Also trigger when the user provides a patent ID or publication number and requests the specification/description in another language, or mentions similar intents such as “patent specification translation,” “description translation,” or “translate the full text.”
Token-efficient persistent memory system for Claude Code that saves ~67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode. Activates at session start (if MEMORY.md exists), on "remember this", "pick up where we left off", "what were we doing", "wrap up", "save progress", "don't forget", "switch context", "hand off", "memory health", "save state", "continue where I left off", "context budget", "how much context left", or any session start on a project with existing memory files. This skill solves two problems at once: Claude forgetting everything between sessions, AND sessions hitting context limits too fast. It replaces thousands of wasted re-explanation tokens with a compact, structured memory load that gives Claude full project context in under 2,000 tokens.
Scaffold a new skill in both publish trees at once — skills/<name>/SKILL.md plus its byte-identical llmwiki mirror — via fdk/tools/new-skill.py, then print the exact commands to register it on the curated surfaces (LOOP_MAP, marketplace.json, AGENT.md/CLAUDE.md). Use when the user says "create a skill", "add a new skill", "scaffold a skill", "make a new skill", "new skill", or invokes /new-skill.
Build, customise and deploy a production booking website on the Opencals hosted API by starting from one of the official open-source Next.js templates (salon, barbershop, clinic, padel/squash club, luxury car rental, language school, villa rental, reformer Pilates studio, dental group, coworking) and the @opencals/storefront-sdk. Use when the user wants a booking/appointment/scheduling site, an Opencals storefront, gives you a business idea + inspiration and asks you to build the booking site, or says "build me a booking website". Covers picking a template, scaffolding, wiring services + availability + checkout, rebranding, and deploying to Vercel. Also covers multi-day rentals booked by the day (cars, equipment) via template-noir, nightly stays with fixed check-in/check-out (villas, cabins, rooms) via template-bali-villas, and schools with group classes, levels, teachers and online lessons via template-fluently, and fitness studios with a multi-studio class timetable, beds left and Full classes via template-reformer, and dental practices or clinic groups with many clinicians across several studios via template-alba, and coworking networks (desks, meeting rooms, booths, studios at several buildings) via template-gable. For the exact API/SDK call shapes, use the companion `opencals-storefront-api` skill.
Scan how you actually work with your coding agent and surface what to encode next. Point it at ONE run’s artifacts to find what would have prevented a specific failure (the reactive loop — “that went wrong, what should change in the AI layer?”), or at a window of session logs to find recurring patterns worth building (the proactive scan). Agent-agnostic. Outputs a shape-only HTML report. Use to evolve your system from real usage.
Get agentic setup prompt categories from a connected Salesforce org using the Connect API via sf api request rest. Use this skill to call GET /services/data/vXX.0/agenticsetup/categories and return the list of prompt categories, optionally with their nested prompts using fetchPrompts=true. TRIGGER when: user asks to get, fetch, retrieve, list, or show agentic setup categories, prompt categories, setup copilot categories, prompt library categories, available setup prompts, Agentforce prompt library, copilot prompts, or calls the agenticsetup categories Connect REST API. DO NOT TRIGGER when: user wants to create new categories, work with non-categories endpoints, or generate OpenAPI specs.
Use this skill whenever the user wants to browse, search, scan, or explore Polymarket prediction markets. This includes finding markets by topic or category, checking current prices and order books, getting market data, viewing trading volumes, looking up prediction market odds, or fetching live Polymarket data. Trigger on: polymarket, prediction market, browse markets, scan markets, market data, trading prices, order book, market odds, betting odds, event contracts, binary options, crypto prices polymarket, polymarket volume, market liquidity, polymarket search, find markets
Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts. Models: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting. Use for: better AI outputs, consistent results, complex tasks, optimization. Triggers: prompt engineering, how to prompt, better prompts, prompt tips, prompting guide, llm prompting, image prompt, ai prompting, prompt optimization, prompt template, prompt structure, effective prompts, prompt techniques
A comprehensive quantum computing toolkit for building, optimizing, and executing quantum circuits. Use for quantum algorithms, simulations, or quantum hardware, including: (1) building quantum circuits with gates and measurements; (2) running quantum algorithms (VQE, QAOA, Grover); (3) transpiling and optimizing circuits for hardware; (4) executing on IBM Quantum or other providers; (5) quantum chemistry and materials science; (6) quantum machine learning; (7) visualizing circuits and results; or (8) any quantum computing development task.
Cut a release from the Conventional Commits a repo already writes: derive the semver bump and a changelog from the commit range, bump the manifest, tag it, and publish a GitHub release, all behind a mandatory preview. Use when the user says "cut a release", "tag a version", "release this", "what's the next version", "generate a changelog", "ship v2", or "/releasekit". It never publishes to a package registry and never moves a published tag.
Fast, accurate code search for AI agents using ~98% fewer tokens than grep+read. Indexes any local or remote repository in under a second (~250ms on CPU, no GPU or API key needed). Supports natural-language and symbol queries, semantic similar-code discovery, and MCP server integration for Claude Code, Codex, Cursor, and OpenCode. Python library available for programmatic use. Triggers on: semble, code search, semantic code search, semble search, token-efficient search, find code, code search mcp, agent code search, semble find-related, semble savings
Generates SmartUI visual regression test configurations for screenshot comparison on TestMu AI cloud. Framework-agnostic—works with Playwright, Selenium, Cypress, and Puppeteer. Use when the user mentions “SmartUI,” “visual regression,” “screenshot comparison,” or “visual testing.” Triggers on: “SmartUI,” “visual regression,” “screenshot comparison,” “pixel diff,” “visual testing LambdaTest.”
Use this skill when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database credentials using sqlmap," "dump tables and columns from a vulnerable database," or "perform automated database penetration testing." It provides comprehensive guidance for using SQLMap to detect and exploit SQL injection vulnerabilities.
Create structured, shareable stock research memos that capture the investment thesis, key disagreements, valuation judgments, risks, and a tracking checklist. Suitable for sharing research conclusions with a team, saving research notes, and producing standardized outputs.
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.