Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Structured ideation methods: SCAMPER, Six Thinking Hats, Morphological Analysis, TRIZ, Biomimicry, plus more. Decision framework for picking methods by challenge type (stuck, improving, systematic exploration, contradiction). Use when generating research ideas or exploring interdisciplinary connections.
This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design". Use for architecture decision records (ADRs), tech stack evaluation, system design reviews, dependency analysis, and generating architecture diagrams in Mermaid, PlantUML, or ASCII format.
Use when the user needs API design, microservices architecture, event-driven systems, database integration, caching strategies, or backend observability. Triggers: REST/GraphQL API implementation, service architecture design, message queue setup, rate limiting, health checks, OpenTelemetry integration.
Use when the user needs CI/CD pipelines, Docker configuration, Kubernetes deployment, infrastructure-as-code, monitoring, or zero-downtime deployment strategies. Triggers: user says "devops", "docker", "kubernetes", "CI/CD", "infrastructure", "monitoring", "deploy to production", "container", "terraform", "observability".
Build a phased SEO roadmap for a domain — quarter-by-quarter, tied to the site's competitive position, content gaps, technical debt, and AI Search readiness. Synthesises the outputs of multiple skills (`seo-technical-audit`, `seo-content-audit`, `seo-keyword-cluster`, `seo-competitor-gap-analysis`, `seo-ai-search-share-of-voice`) into one site-level plan with sequencing, owners, and success metrics. Distinct from `seo-keyword-cluster` (keyword architecture for one topic), `seo-content-brief` (one article), and `seo-keyword-niche` (longtail content tier). Use when the user asks for an "SEO plan", "SEO strategy", "SEO roadmap", "90-day plan", "quarterly SEO plan", "site SEO strategy", or "where do we focus next".
This skill MUST be used to develop service innovation opportunities into concepts, comparisons, or prototype validation plans (服務創新、創新機會、 服務原型、創新流程、服務體驗工程). It SHOULD also be used when the user wants new service directions, value co-creation, or ways to test an existing service concept without naming a method. Match the workflow to the task; a standalone method request does not require a full workshop.
Set up CI so every pull request gets a Testomat.io run scoped to the code it changes. One job runs after the deploy — it creates the run and launches the affected tests into it. Use when the user wants to integrate Testomat.io runs into a CI pipeline, create test runs per pull request, or set up change-aware testing that triggers affected tests from CI events.
Configure GitHub settings for repositories created from this template using gh. Set up Actions secrets, allow PR creation by Actions, restrict who can create PRs and configure auto-merge, and align the default branch ruleset. Use when creating a new repository from the template or re-aligning GitHub settings.
Query and summarize site activity logs for a Webflow enterprise site. Surfaces recent changes, identifies who made them, and generates human-readable activity reports. Use for site monitoring, change tracking, publish preparation, or weekly activity summaries. Enterprise plans only.
Map situational impairments that affect all users in specific contexts — not just people with permanent disabilities. Use when designing for mobile, outdoor, noisy, stressful, or multitasking contexts. Triggers on: situational, context of use, environment, one-handed, bright sunlight, noisy, driving, multitasking, gloves, temporary disability, context, edge case.
Guide to analyze a current work session and propose improvements to skills. Use (1) automatically after working with a skill to capture learnings, (2) when the user suggests improvements, corrections, or additions during a skill-related session, or (3) when the user manually invokes `self-improve`.
Use for Snyk-driven security work: run Snyk SAST/SCA scans, review findings, triage scope, or produce an approved remediation plan before fixing vulnerabilities. Trigger only when the user mentions Snyk, scanner findings, dependency/source vulnerabilities from Snyk, or remediation of Snyk results. Do not trigger for general security architecture reviews, threat models, manual OWASP validation, or non-Snyk bug fixes.
Parse PDF, images (PNG/JPG/BMP/TIFF/WebP/HEIC), Word, PPT and other documents into Markdown or JSON using SoMark. All document parsing needs (like resumes, papers, contracts, reports, manuals, etc.) should be parsed by SoMark first so AI can understand and answer more accurately.
Guides creation of a new Tambo project from scratch with technology recommendations. Use when user wants to start a NEW project, build a new app with Tambo, create something from nothing, or needs help choosing technologies for a new generative UI application. For adding Tambo to EXISTING projects, use add-to-existing-project skill instead.
Reasoning skill for structure-based drug design strategy. Use when the user asks to assess target druggability, choose a docking strategy, select a scoring function, define a binding site, interpret docking results, plan molecular dynamics or free energy perturbation (FEP), design a virtual screening cascade, or decide between fragment-based and HTS screening. Triggers include "drug design", "druggability", "docking strategy", "scoring function", "binding pocket", "molecular dynamics", "FEP", "SAR", "virtual screening", "induced fit", "allosteric site", "fragment-based drug discovery", "lead optimization", "MM-GBSA", "pharmacophore".
Check and consistently apply the Vietnamese style guide for forms of address, terminology, capitalization, numbers, dates and times, units, headings, bullets, and code. Use when standardizing one or more documents; do not use it to replace grammar review, impose default rules on a custom style guide, or change product names and verbatim quoted content.
Execute implementation plans by dispatching a fresh subagent per task with two-stage review (spec compliance then code quality). Use when you have an implementation plan with mostly independent tasks and want high-quality, fast iteration within a single session.
Configure SuperJSON transformer on both server initTRPC.create({ transformer: superjson }) and every client terminating link (httpBatchLink, httpLink, wsLink, httpSubscriptionLink) to support Date, Map, Set, BigInt over the wire. Transformer must match on both sides. In v11, transformer goes on individual links, not the client constructor.
Review new or changed dependencies for supply-chain compromise before they enter a project — malicious install scripts (preinstall/postinstall), binding.gyp/node-gyp install-time execution (June 2026 worm), self-propagating worms (Shai-Hulud, binding.gyp), credential harvesting and exfiltration, obfuscated payloads, typosquatting, slopsquatting (AI-hallucinated package names), dependency/namespace confusion, maintainer account takeover, and unpinned or unverified versions. Reads manifests, lockfiles, install scripts, and dependency diffs offline across npm, PyPI, Go, Cargo, RubyGems, Maven, NuGet, and Composer, and reports each risk at file:line with a concrete fix — no install, no execution, no phoning home. Trigger when adding or upgrading a dependency, reviewing a PR that changes package.json / requirements.txt / go.mod / a lockfile, deciding whether a package is safe to install, or when the user mentions Shai-Hulud, binding.gyp, a compromised or malicious package, typosquatting, dependency confusion, or asks "is this dependency safe to add?".
Maps identified symmetries to mathematical groups (cyclic, dihedral, symmetric, SO(3), SE(3), E(3)) for equivariant neural network architecture design, using taxonomy and foundations from Visual Group Theory. Use when candidate symmetries have been identified and need formalization into group theory language, or when user mentions cyclic groups, dihedral groups, Lie groups, SO(3), SE(3), or permutation groups.
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.