Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
All
SaaS product design methodology for building user-facing application features. Covers: onboarding, empty states, billing UX, feature gating, dashboard design, notification patterns, settings/admin UX, audit trails, loading states, multi-tenancy. Use when: designing new SaaS features, creating dashboards, planning onboarding flows, or reviewing product-level UX decisions.
6sense platform help — Signalverse intent data, Predictive Analytics (6AI Scoring), Sales Intelligence, AI Email Agents, Advertising, Orchestration, Segments, Company Identification API, People/Company Enrichment API. Use when intent scores feel like a black box, too many accounts flagged as in-market but sales can't follow up, 6QA thresholds are too loose or too tight, AI email agents aren't generating replies, LinkedIn audience sync has low match rates, segments pulling wrong companies, API calls returning errors, or comparing 6sense to Demandbase or Bombora. Do NOT use for intent strategy across multiple tools (use /sales-intent) or enrichment strategy across tools (use /sales-enrich).
Clay platform help — Waterfall Enrichment (150+ data providers), Claygent (AI Research Agents), Sculptor (workflow builder), Signals (job changes, intent), Audiences, Ad Sync (LinkedIn/Meta/Google), Email Sequencer, CRM Sync (Salesforce/HubSpot/Dynamics), HTTP API actions, webhooks. Use when enrichment data has gaps or low match rates, Claygent not returning useful research, Sculptor workflows failing or hard to build, signals missing job changes you care about, audiences not syncing to ad platforms, CRM data out of sync with Clay, or webhooks not firing. Do NOT use for enrichment strategy across tools (use /sales-enrich), cadence/sequence strategy across tools (use /sales-cadence), intent signal strategy across tools (use /sales-intent), B2B advertising strategy across tools (use /sales-b2b-advertising), or CRM data hygiene strategy across tools (use /sales-data-hygiene).
Enrich.so platform help — real-time B2B data enrichment API with 50+ data points per lookup and success-based billing. Key capabilities: reverse email lookup, LinkedIn profile enrichment, email/phone finders, company data, similar company search, employee search, IP to company, and bulk enrichment. Use when you have an email but need the LinkedIn profile behind it, a LinkedIn URL but need contact details, you need to find someone's email from just name and company, company data is missing for your leads, or the Enrich.so API isn't returning expected results. Do NOT use for cross-platform enrichment strategy (use /sales-enrich), email deliverability strategy (use /sales-deliverability), or prospect list strategy (use /sales-prospect-list).
GetResponse platform help — email marketing, autoresponders, visual marketing automation workflows, conversion funnels, landing pages, webinars (live and on-demand), course creator, premium newsletters, SMS marketing, web push notifications, live chat, signup forms, popups, website builder, e-commerce integrations (Shopify, WooCommerce), contact scoring, segmentation, paid ads, AI content generator, transactional email (MAX only), REST API. Use when autoresponders aren't triggering, automation workflows behave unexpectedly, conversion funnel drop-off is too high, webinar or course setup isn't working, contacts aren't syncing or segmenting correctly, or something in GetResponse isn't doing what you expect. Do NOT use for general email marketing strategy (use /sales-email-marketing), general funnel strategy (use /sales-funnel), general webinar strategy (use /sales-webinar), general course/membership strategy (use /sales-membership), cross-platform deliverability (use /sales-deliverability), or connecting tools generically (use /sales-integration).
Iterable platform help — cross-channel customer engagement with Studio journey builder, AI suite (Brand Affinity, STO, Predictive Goals), and Smart Ingest from 23+ data sources. Use when Studio journeys aren't triggering correctly, campaigns or experiments produce unexpected results, email/SMS/push/in-app/WhatsApp channels aren't delivering, AI features like Brand Affinity or STO aren't improving metrics, Smart Ingest or Snowflake sync is failing, or something in Iterable isn't working as expected. Do NOT use for general email marketing strategy (use /sales-email-marketing), push notification strategy (use /sales-push-notification), in-app messaging strategy (use /sales-in-app-messaging), transactional email strategy (use /sales-transactional-email), cross-platform deliverability (use /sales-deliverability), or connecting tools generically (use /sales-integration).
Lobstr.io platform help — no-code web scraping platform with 50+ ready-made scrapers for Google Maps, LinkedIn Sales Navigator, Twitter, YouTube, and more. Features cookie-based login sync, scheduled automation, multi-threading, and a full API with Python SDK and MCP Server. Use when Lobstr scraper returning empty or incomplete results, exports to Google Sheets or S3 failing, scheduled scrapes not running, API or Python SDK throwing errors, or credits draining faster than expected. Do NOT use for general prospect list strategy (use /sales-prospect-list), cross-platform enrichment strategy (use /sales-enrich), or integration strategy (use /sales-integration).
Team-wide sales methodology enablement (MEDDIC, BANT, Sandler, Challenger, SPIN, Value/Gap Selling): generates framework discovery questions, deal scorecards grounded in live HubSpot + Clari data with qualify_lead as the stakeholder source of truth, rep training plans, and HubSpot write-back (scorecard note + next-action task). Use when: "implement MEDDIC across my team", "build a BANT scorecard", "train reps on Sandler", "score this deal using [methodology]", "30/60/90 sales enablement rollout", "standardize qualification", "methodology scorecard", "create SPIN discovery questions". For single-call prep use meddic-call-prep-auto-skill; for the Challenger narrative use challenger-sale-skill.
Build a Sales Qualification Pack (ICP + disqualification rules, qualification scorecard, discovery/qualification script, CRM note template, and pipeline hygiene rules). Use to fix pipeline quality and stop wasting time on wrong leads. Category: Sales & GTM.
RB2B platform help — Person-Level Website Visitor ID, Company-Level ID, Hot Pages, Hot Leads, Traffic Insights, Identity Resolution API, integrations. Use when you know companies visit your site but not which people, the RB2B pixel isn't identifying visitors, you need person-level ID not just company-level, Hot Pages aren't flagging high-intent visits, or you're comparing RB2B vs Clearbit Reveal for visitor identification. Do NOT use for visitor identification strategy across tools (use /sales-intent), enrichment strategy across tools (use /sales-enrich), building prospect lists across tools (use /sales-prospect-list), or lead scoring strategy (use /sales-lead-score).
Track how performance changes with data size, model size, batch size, or compute, fit a scaling law, and decide where more compute will actually pay off. Use when planning larger runs, deciding whether to scale data vs. model vs. optimization, estimating performance at a bigger budget, or judging whether a curve has hit diminishing returns. Trigger on "is it worth scaling this further", "fit a scaling law", "where are the diminishing returns", "how much better at 10x compute", "should I add data or parameters", or when the user has a set of runs at different scales and wants the trend extrapolated.
Cross-cutting runtime APIs for Decentraland SDK7 scenes. Use when the user needs async operations (executeTask), HTTP requests (fetch, signedFetch), WebSocket connections, timers, realm/scene detection, restricted actions (movePlayerTo, teleportTo, triggerEmote, openExternalUrl), portable experiences, or the testing framework. Do NOT use for UI (see build-ui), multiplayer sync (see multiplayer-sync), or avatar/player data (see player-avatar).
Build and debug SceneKit scenes where one 3D object (a product, badge, coin, wheel) performs on a transparent stage inside a SwiftUI app - studio lighting, real shadows, baked keyframe choreography, hand-rolled physics, gestures and haptics, multi-scene sequencing. Use when working with SCNView or SceneView in SwiftUI, UIViewRepresentable 3D scenes, product or hero-object animation, roll or spin entrances, a first-frame hitch when a scene appears, shadows missing or wrong, metal rendering black, choreographed 3D motion that must stay interruptible, a continuous vapor stream (vent air, steam, mist) drawn as a shader-driven sheet, a liquid-metal or jelly blob (noise-deformed surface with mirror reflections and tap ripples), chrome or gold that looks cartoon-flat instead of real, HDRI image-based lighting, free trackball rotation of an actor, deterministic screenshot testing of shader-driven scenes, cutting an actor in two with a finger swipe (runtime mesh slicing with sealed cross-sections and a falling piece), a die-struck relief object (badge, coin, medallion) built from a heightfield with multiple finishes on one mesh, an actor crumbling into debris that falls and rests on the floor, reproducing a real object's motion from photos or video, or keyframed motion that stutters at its own keyframes. Not for RealityKit, ARKit, visionOS, or full game worlds.
Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences. Makes websites feel like experiences, not just pages. Use when "scroll animation, parallax, scroll storytelling, interactive story, cinematic website, scroll experience, immersive web, " mentioned.
RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.
A lightweight AI Agent harness / checkpoint-driven coding skill for strong models such as GPT-5.4 and expert users. It assumes the user has already sliced the task down to the smallest executable unit of chaos; the model decomposes, explores and pushes forward on its own, while the human keeps low-interference control through the final goal, minimal spec, restatement, checkpoints, evidence verification and write-back.
Seedance 2.0 AI video generation via EvoLink API. Three modes — text-to-video, image-to-video (1-2 images), reference-to-video (images + videos + audio). Auto audio (voice, SFX, BGM). Works with OpenClaw, Claude Code, Cursor. Powered by ByteDance Seedance 2.0.
Designing search engines and vector DBs for full-text, vector, and hybrid retrieval, including permission-aware retrieval for multi-tenant or per-role corpora. Use for search design, index optimization, the RAG retrieval layer, or deciding where ACL filtering belongs in the query path.
Guides senior software engineering across languages and stacks—system and service design, RFCs, code review, refactoring, reliability patterns, testing strategy, performance analysis, technical decomposition, and engineering leadership on delivery teams. Use when designing services or modules, writing technical specs, reviewing PRs for architecture and correctness, improving legacy code, choosing trade-offs (coupling, consistency, latency), estimating complex work, or mentoring engineers—not for stack-specific full-stack UI delivery (senior-fullstack-developer), deployment rollout strategy (deployment-strategist), infrastructure/IaC (infrastructure-engineer), dedicated perf profiling and load testing (performance-engineer), org-wide security programs (cybersecurity), or cross-system ADRs and architecture review (senior-system-architecture).
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. For AI search optimization, see ai-seo.
Optimize website content for search engine visibility and user engagement. Conduct keyword research, implement on-page SEO tactics, analyze content gaps, write compelling meta descriptions, and develop internal linking strategies.
Implement technical SEO infrastructure for Next.js apps. Use this skill when setting up sitemaps, robots.txt, meta tags, OpenGraph, structured data (JSON-LD), canonical URLs, and other technical SEO elements. Covers Next.js 15/16 App Router patterns and 2025 best practices.
Set up a Claude Code PreCompact hook that blocks compaction until a fresh handoff exists in .agents/handoffs/, so a session reaching its context limit never loses the conversation to auto-compact. Use when the user wants automatic handoff on context-limit, or to protect long sessions from compaction data loss.
One-time setup that maps direct competitors, alternatives, and category substitutes for the current project from the codebase, user input, and external research, then writes a root COMPETITORS.md. Use when the user invokes $setup-competitors-md, says "setup competitors", "create COMPETITORS.md", "competitive landscape", or asks to document rivals and differentiation for the project.
One-time setup that analyzes a project's existing copy, competitor and category messaging, and writes a root COPYWRITING.md with voice, patterns, good/bad examples, and writing rules. Use when the user invokes $setup-copywriting-md, says "setup copywriting", "create COPYWRITING.md", or asks to extract copywriting patterns, tone, or messaging guidelines for the current project.
One-time setup that derives the best ideal customer profile for the current project from the codebase, product context, and external market signals, then writes a root ICP.md. Use when the user invokes $setup-icp-md, says "setup icp", "create ICP.md", "ideal customer profile", or asks to define who the product is for.
Set up the `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain docs layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills seem to lack context about the issue tracker, triage labels, or domain docs.
Real-time sports & events data for AI agents via Shipp. Use when the user wants live scores, schedules, or game events for NBA, NFL, NCAA Football, MLB, or Soccer — especially to power prediction market trading strategies on Polymarket or Kalshi using a MoonPay wallet.
Audit a Shopify Article, research content and E-E-A-T gaps, generate a reviewable HTML candidate, and produce one audit-plus-storefront-preview report before any approved update. Use when a merchant gives an Article URL, title, or Article ID and wants safer blog SEO and reading-experience improvements.
Generates, details, splits, and maps agile user stories. Applies INVEST, 5Cs, BDD/Gherkin, "Three Amigos" approaches, NFRs/DoD assessment, 10 Story Splitting strategies, and the User Story Mapping model (Backbone, Narrative Flow, Slicing), maximizing value (Outcome) over quantity (Output).
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across iterations. Runs multiple trials per eval for statistical reliability, aggregates results into benchmark.json, and generates comparison reports between skill versions. Use when user says "benchmark skill", "measure skill performance", "skill metrics", "compare skill versions", "skill performance", "track skill improvement", "skill regression test", or "skill A/B test".
Scaffold and build Claude Code skills from plans or descriptions. Generates SKILL.md files, sub-skills, scripts, references, agents, and templates following the Agent Skills standard. Use when user says "build skill", "scaffold skill", "generate skill", "create SKILL.md", or "implement skill".
Improve and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements. Handles under/over-triggering fixes, instruction refinement, new sub-skill addition, and architecture evolution. Use when user says "improve skill", "fix skill", "skill not triggering", "skill triggers too much", "update skill", or "evolve skill".
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.