Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
[project] Batch-generate Notion-style relaxed hand-drawn infographic series from reference manuscripts. Use this skill when the user needs to read a document and generate a set of infographics for social media distribution. Suited to turning articles and notes into a visual content series.
Full health and security audit for Rails apps, the review a principal engineer would do. Runs rubycritic, Brakeman, bundler-audit and ruby_audit, triages every finding with the LLM as judge, brings an OWASP Top 10 arsenal of checks for what scanners miss, and returns one impact-ranked action plan. Use for a Rails project audit, a security and health check, "nuke on rails", or a deep review of a vibecoded Rails app.
Write and edit clear, concise, human-centred text free of AI writing tropes across four Surfaces: Longform Prose (essays, blog posts), Technical Docs & READMEs (guides, API docs, ADRs), Web & Content Design (landing pages, help pages) and UX & Microcopy (UI controls, CLI output, error messages).
Invoke OpenCode CLI as a sub-agent to leverage alternative AI models (GPT-5.x, Codex, local models) for code implementation, review, debugging, research, and second opinions. Use when the user asks to "use opencode", "get a second opinion from GPT/Codex", "implement with opencode", "review with opencode", "let opencode handle this", "use a different model", or wants cross-model validation. Also triggers when the user explicitly names an OpenCode model (e.g., "use gpt-5.4", "use codex") or wants to delegate a task to a non-Claude AI system. Supports all providers configured in the user's OpenCode installation (OpenAI, GitHub Copilot, local models via Ollama/LM Studio, and OpenCode's own free-tier models).
Polymarket — research, pricing, trading, deposit/withdraw, and trader leaderboard via the OpenFinance backend. Use for ANY Polymarket task. Polymarket runs a per-EOA "deposit wallet" smart contract that holds pUSD and is the on-chain `maker` on every order — pUSD on the EOA is stranded for trading, and `/user/:address/*` lookups must use the deposit-wallet address (NOT the EOA). Always call `GET /agent/polymarket/deposit-wallet` first to resolve the right address — except for "my data" reads where the `/me/*` aliases inject the caller's address automatically. Triggers — events / markets / odds in politics / sports (IPL, FIFA, NBA, NFL, F1, UFC, cricket) / crypto / culture / entertainment, place / cancel orders (limit GTC/GTD, market FOK/FAK, batch), neg-risk multi-outcome markets, tick sizes, builder attribution, "where do I deposit on Polymarket / what's my Polymarket address", "withdraw / cash out from Polymarket to {chain}", "Polymarket leaderboard / top traders / best wallets / who's making money / where do I rank", "my positions / my activity / my trades / my closed positions", "what is wallet X doing on Polymarket", "X's positions / activity / trades", "claim my winnings", "redeem my Polymarket bet", "I won, cash out", "redeem all", "wrap my USDC.e to pUSD", "convert USDC.e", "make my winnings tradeable". Covers /agent/polymarket/* (events, markets, search, orderbook, price(s), spread, last-trade-price, trades, market/:id/{open-interest,volume,liquidity,trades}, user/:address/{positions,closed-positions,activity,trades,portfolio,pnl}, me/{positions,closed-positions,activity,trades,portfolio,pnl}, leaderboard, deposit-wallet, deposit-wallet/wrap-collateral, deposit-wallet/withdraw-and-bridge, redeem, redeem/all, order, order/market, orders, order/:id, order/:id/scoring, builder/*). Two collateral assets on the deposit wallet — **pUSD** (tradeable on the CLOB, withdrawable) and **USDC.e** (what some resolved-position payouts and some bridges arrive in — depends on the market's settlement collateral; wrap to pUSD via `/wrap-collateral` before trading / withdrawing). For leaderboard queries — DO NOT web-fetch; this tool has the data. Prerequisite — openfin-setup.
Particle Image Velocimetry (PIV) analysis with OpenPIV. Use when extracting velocity fields from PIV image pairs, analyzing fluid dynamics or flow visualization experiments, cross-correlating interrogation windows, validating and replacing spurious PIV vectors, or computing vorticity, strain rate, and turbulence statistics from measured velocity fields.
Autonomous multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tasks, dispatches parallel agents (subagents or Agent Teams), audits completions, and ships PRs. Registry-driven — works for any user with a configured project registry.
Tidy an OXYGEN Table: inspect duplicate columns, ordering, formatting, types, hide/archive candidates, and suspicious values; present findings by category; then apply only approved reversible fixes. This is table structure and cell formatting, not CRM record deduplication or merge.
Plan and review ChatGPT Ads experiments without assuming ad inventory, account access, or platform capabilities. Use for ChatGPT advertising, OpenAI ads, conversational ad concepts, ChatGPT campaign plans, or performance reviews from a verified export.
Upgrade a Panda CSS project from v1 to v2, or debug a project that worked on 1.x and breaks on 2.x. Use when upgrading @pandacss/dev to v2, when a build fails after upgrading, when config hooks, createStyleContext, template literal styles, panda ship, panda mcp, or --cpu-prof stop working, or when CSS output changes after the upgrade. Do not use for writing styles (use panda-css), designing tokens and recipes (use panda-css-theming), or migrating from Tailwind, Emotion, or styled-components.
Convert documents between formats using Pandoc. Use when the user asks to convert files between formats like markdown, docx, html, pdf, latex, epub, rtf, csv, xlsx, or pptx. Triggers on requests like "convert this to Word", "export as PDF", "turn this markdown into HTML", or "convert the CSV to a table".
PDF generation and manipulation. Puppeteer/Playwright HTML-to-PDF, PDFKit, jsPDF, React-PDF, iText (Java), ReportLab (Python). Invoices, reports, and document generation. USE WHEN: user mentions "PDF", "generate PDF", "HTML to PDF", "invoice PDF", "PDFKit", "jsPDF", "Puppeteer PDF", "React-PDF", "iText", "ReportLab" DO NOT USE FOR: PDF parsing/reading - different concern; image generation - different format
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch or JAX. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.
Business logic and workflow abuse assessment for state-machine manipulation, race conditions, replay, quota abuse, order-of-operations flaws, delegated execution abuse, and unauthorized state transitions. Hands off to recon, input/protocol, exploit, or reporting workflows when those become the owner phase.
Offline cyber security agent for the user's own apps and AI coding tools, run locally with the Penthera CLI; open R&D, measured in public. Sets it up in one command ("set up penthera in this repo"). Scans the user's own live URL and repo (TLS, headers, auth, OpenAPI, secrets incl. AI keys, opt-in injection); checks npm and Python dependencies offline ("is this dependency safe?", "what changed in my deps?", "install X safely", "any AGPL in our deps?"); blocks secrets and risky agent config before commit ("add a pre-commit hook"); audits AI tooling ("audit my MCP servers / skills / hooks", "check this skill before I install it"); fixes findings on a local branch and re-scans to verify ("scan and fix my app"); writes reports and evidence ("report for my auditor / manager", NIS2, SARIF, baseline diff). Use when the user asks to scan, audit, harden, fix, or review the security of their own app, staging URL, localhost, repo, dependencies, or agent setup. Do NOT use for targets without explicit authorization.
PHP web source expression injection (non-template) audit tool. Identifies user-controllable expression strings entering an expression engine for evaluation/compilation that ultimately lead to sensitive semantic execution, and outputs exploitability grading, PoC and remediation advice (omission prohibited).
PHP filesystem operation audit tool. Focuses on the security risks of operations such as mkdir/chmod/chown/unlink/rmdir/link/symlink/readlink/touch/permissions and TOCTOU, providing "exploitability enhancement evidence" for path validation bypass and write-chain exploitation (does not replace sink sub-audits such as FILE/UPLOAD/WRITE).
PHP web source template injection/SSTI audit tool. Identifies template engine render points and the controllability of template names/expressions, traces to eval/execution chains, and outputs exploitability grading, PoC and remediation advice (omission prohibited).
Design and implement disaster recovery strategies with RTO/RPO planning, database backups, Kubernetes DR, cross-region replication, and chaos engineering testing. Use when implementing backup systems, configuring point-in-time recovery, setting up multi-region failover, or validating DR procedures.
Design and implement Internal Developer Platforms (IDPs) with self-service capabilities, golden paths, and developer experience optimization. Covers platform strategy, IDP architecture (Backstage, Port), infrastructure orchestration (Crossplane), GitOps (Argo CD), and adoption patterns. Use when building developer platforms, improving DevEx, or establishing platform teams.
End-to-end testing patterns for Blazor applications using Playwright, including component testing and page navigation. Use when writing E2E tests for Blazor applications, testing Blazor component interactions with Playwright, or setting up Playwright testing infrastructure for Blazor apps.
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
Use when: you need to design a motion direction for a brand, create a logo animation demo, define brand motion personality, or transition from a static logo to a dynamic presentation. Do NOT use when: you need professional-grade motion delivery (should go to a designer), finished motion already exists and no direction validation is needed, or you only need a text description with no demo.
Design high-quality research questionnaires. Use this Skill when the user says "design a questionnaire", "do a survey", "help me come up with a questionnaire", "user research", "satisfaction survey", "NPS questionnaire", "market research", "requirements research", "questionnaire design", or "survey design", or when the user describes a research goal but does not yet have a structured questionnaire. Also applies when: the user uploads an existing questionnaire and asks to optimize it, check it for bias, or add questions; the user says "help me check whether this questionnaire has problems"; the user needs to design an A/B test questionnaire, a focus group interview guide, or an NPS/CSAT/CES survey; the user mentions professional terms such as "leading question", "double-barreled question", or "questionnaire bias". Not applicable to: pure data analysis (use pm-analytics), pure organizing of user interview notes (just organize them directly), or pure product requirements documents (use pm-prd-writer).
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.