Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build an immersive scroll-scrubbed "fly through the world" landing page for any industry or brand using Higgsfield. As the visitor scrolls, a pre-rendered camera flies from outside each scene into its interior, then flows on to the next scene with NO cuts — one continuous connected flight (Emons-style isometric diorama world, or any art direction you pick). The skill interviews the user for the topic, the story beats/sections, and brand kit, then generates cohesive scenes + seamless camera clips with Higgsfield and wires a portable, framework-agnostic scroll-scrub engine. Use when the user wants a "3D world" / "browse-through-the-industry" hero, a scroll cinematic, a diorama landing, or to turn a business into a scrollable world.
ScyllaDB CQL data modeling patterns and anti-patterns, including compaction strategy choice, TTL-based expiration, tombstone management, and lightweight transactions. Use when designing tables, reviewing schemas, migrating from SQL or MongoDB, setting data retention, troubleshooting performance issues caused by schema problems or deletes, or writing conditional (LWT) statements. Vector and full-text indexes go to scylladb-vector-search; DynamoDB API tables go to scylladb-alternator. Triggers on "design schema", "ScyllaDB data model", "partition key", "clustering column", "primary key", "CQL table design", "ALLOW FILTERING", "large partitions", "hot partitions", "query-first design", "secondary index", "materialized view", "schema review", "wide partition", "tombstones", "time series", "BATCH", "paging", "fetch size", "TTL", "default_time_to_live", "compaction strategy", "TWCS", "gc_grace_seconds", "tombstone_gc", "LWT", "lightweight transaction", "IF NOT EXISTS", "LOCAL_SERIAL"
Statistical visualization on matplotlib with native pandas support. Auto aggregation, CIs, grouping for distributions (histplot, kdeplot), categorical (boxplot, violinplot), relational (scatterplot, lineplot), regression (regplot, lmplot), matrix (heatmap, clustermap), grids (pairplot, FacetGrid). Use for quick statistical summaries; matplotlib for fine control; plotly for interactive HTML.
Seata distributed transaction skill. Covers the decision tree for choosing among the four modes AT/TCC/SAGA/XA, the mandatory undo_log table in AT mode, useTCCFence in TCC mode to solve idempotency/hanging/empty rollback, SAGA state machine for long processes, global transaction timeout configuration (@GlobalTransactional timeoutMills), and read isolation enhancement (@GlobalLock + FOR UPDATE). Corrects LLM mistakes: not knowing which of AT/TCC/SAGA to choose, not creating the undo_log table, non-idempotent TCC Confirm, and not handling the watch dog.
Guidance for Microsoft Security Copilot agents — autonomous, purpose-built AI agents (e.g., phishing triage, alert triage, conditional access optimization, vulnerability remediation) that work within Security Copilot. Covers available agents, identity/permissions, and supervision. WHEN: Security Copilot agents, autonomous SOC agent, phishing triage agent, alert triage agent, agent identity, supervise AI agent, agentic security, Copilot agent permissions, automate phishing triage, AI agent for SOC, autonomous alert triage, hands-off triage of high-volume alerts. DO NOT USE for basic Security Copilot setup, SCU provisioning, or promptbooks (use security-copilot).
Builds security incident reports, DDoS post-mortems, timelines, IoC sections, CVE correlation, severity scoring, and blameless root cause analysis. Use when the user needs an incident report, post-mortem, forensics summary, security timeline, DDoS analysis, SIR, root cause analysis, or communication for a security event.
Use when writing or changing code that handles user input, uploaded files, authentication, sessions, authorisation, database queries, shell commands, file paths, outbound requests to user-supplied URLs, HTTP responses and headers, secrets or credentials, deserialisation, or new third-party dependencies
Perform language- and framework-specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best-practice guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, then writes a concise actionable Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Covers STRIDE, PASTA, and attacker-goal-based methodologies, with modern considerations for AI/ML systems, cloud-native deployments, and supply chain threats.
Plan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair. Use for an end-to-end Seedance production request; use a narrower prompt skill for a single prompt
SE Ranking API integration architect. Covers the whole SE Ranking surface — the Data API (keyword research, backlinks, domain & competitor analysis, SERP, website audit, AI Search) and the Project API (rank tracking, project/keyword/backlink management, marketing plan, sub-accounts, AIRT prompts). Answers any "how do I…" question about endpoints, parameters, JSON schemas, credit cost, rate limits, or auth, and produces ready-to-paste cURL / Python / TypeScript / MCP-tool-call recipes. With explicit confirmation it also wires up Project API state — creating projects, adding keywords, configuring audits, setting up AIRT prompt groups. Pulls live tool schemas from the connected MCP. Unlike the analysis skills (briefs, audits, reports), seo-api produces integration recipes and wired-up state. Use when the user asks how to use the SE Ranking API, which endpoint returns a metric, how to build a rank tracker, for Postman / cURL / Python recipes, or how to integrate with Looker / n8n / Make.
Capture an SEO baseline snapshot for a domain or URL, then on later runs compare the current state and surface regressions. Tracks authority, traffic, keywords, backlinks, and on-page content. Three subcommands — `baseline`, `compare`, `history`. Use when the user asks for "SEO drift", "baseline this site", "did anything break", "SEO regression check", "compare before and after", "deployment check", or "monthly SEO snapshot".
Search Engine Optimization specialist for content strategy, technical SEO, keyword research, and ranking improvements. Use when optimizing website content, improving search rankings, conducting keyword analysis, or implementing SEO best practices. Expert in on-page SEO, meta tags, schema markup, and Core Web Vitals.
Subdomain ownership map for a domain. Lists subdomains, queries overview/keywords/competitors/backlinks per subdomain, surfaces which subdomains own which topic clusters, where there's fragmentation, and whether consolidation is warranted. Use when the user asks "subdomain analysis", "subdomain ownership", "subdomain SEO", "blog vs main domain", "support vs docs subdomain", or "should I consolidate subdomains".
Diagnose why a page is not ranking by reading the SERP backwards. Identifies the page type Google rewards for the target keyword, scores the candidate page against that pattern from multiple persona perspectives, and recommends the page format that would win the SERP. Use when the user asks "why isn't this page ranking", "page type mismatch", "SXO", "search experience optimization", "intent mismatch", or wants a wireframe.
Technical SEO audit across 9 categories: crawlability, indexability, security, URL structure, mobile, Core Web Vitals, structured data, JavaScript rendering, and IndexNow protocol. Use when user says "technical SEO", "crawl issues", "robots.txt", "Core Web Vitals", "site speed", or "security headers".
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf/AllOf conditions, interrupts, Resource, PriorityResource, PreemptiveResource, Container, Store, time-weighted monitoring, and replication-based output analysis, plus bundled safe CLIs. Use when modeling queues, production lines, logistics, or service operations with generator processes; when contending entities need shared resources or preemption; when instrumenting queue length or utilization correctly; when running independent replications with seeds and confidence intervals; when debugging event ordering or run(until=) boundaries. Not for continuous-time ODE or agent-based modeling frameworks.
Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKILL.md", or asks to find issues in skill definitions. Covers structural and semantic validation. Do NOT use for anti-slop detection, security scanning, token analysis, enterprise checks, or Eval Kit generation; use skill-check-pro for those. Do NOT use for LinkedIn skill engagement; use skillcheck-engage for that.
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
Use the skill-hub CLI to search, install, update, and publish agent skills from skill-hub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed skill-hub CLI.
Security-first skill vetting protocol for AI agents. Use before installing any skill from the platform skill market, skillhub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns to determine whether a skill is safe to install.
Patterns for detecting and managing code smells and technical debt in .NET applications. Run Slopwatch CLI to detect LLM reward hacking, disabled tests, suppressed warnings, empty catches, and other shortcuts. Use when identifying code smells, running quality gates in CI/CD, or validating LLM-generated code changes.
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
Expert sound designer — synthesize any sound from first principles. Reasons from physics, psychoacoustics, and synthesis theory to produce detailed patch recipes with runnable SuperCollider and Web Audio code. Triggers on: sound design, synthesize, synth patch, bass sound, lead sound, pad sound, drum synthesis, FM synthesis, subtractive synthesis, granular, wavetable, physical modeling, audio synthesis, sound texture, timbre.
Use when the user asks to confirm architectural decisions and feature trade-offs in PRD or CRD requirements or development plans; not for quality reviews, writing documents from scratch, or implementation. Generate an interactive HTML confirmation form and revise the document based on submitted approvals, rejections, and changes.
Specify adaptive behaviour for an interface. Chains: user-preference-respect, responsive-accessibility, flexible-typography, colour-independence, simplified-views, information-density. Use when designing a new interface and you want to build adaptability in from the start.
Invoke FIRST, before creating, editing, or deleting components, stories, styles, CSS, themes, colors, or design tokens — anything that changes how the UI looks, no exceptions. Also for starting or previewing Storybook to verify UI, requests to show, browse, or list components, stories, or UI states, and docs, props, or usage lookups.
Long-text shot-splitting batch image generation engine. Intelligently splits stories, courses, and comic scripts into scenes and batch-generates illustrations with a consistent style and consistent characters. Use this skill when the user mentions "shot splitting and image generation", "story illustrations", "batch scene images", "comic generation", or "picture book generation".
Query STRING REST API for PPIs (59M proteins, 20B interactions, 5000+ species). Retrieve networks, run GO/KEGG enrichment, find partners, test PPI significance, visualize networks, analyze homology. For chemical interactions use chembl-database-bioactivity; pathways use kegg-database.
Break down complex problems into a hierarchical, mutually exclusive and collectively exhaustive structural framework. Suited to sorting out messy information, expressing things clearly to others, and analyzing problems comprehensively. Use this skill when you face a pile of scattered elements and cannot form a global view, or when you need to give a structured report to others. Not for problems that are already highly structured or quick decisions that rely on intuition. Key trigger signals: "too much information, can't sort it out", "how to say it clearly", "did I miss anything", "help me break down this problem".
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.